[Datasets] Add Mapillary Vistas Datasets to MMSeg Core Package.

README.md

@@ -181,6 +181,7 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
 - [x] [Potsdam](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/user_guides/2_dataset_prepare.md#isprs-potsdam)
 - [x] [Vaihingen](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/user_guides/2_dataset_prepare.md#isprs-vaihingen)
 - [x] [iSAID](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/user_guides/2_dataset_prepare.md#isaid)
+- [x] [Mapillary Vistas](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/user_guides/2_dataset_prepare.md#mapillary-vistas-datasets)
 
 </details>
 

README_zh-CN.md

@@ -162,6 +162,7 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
 - [x] [Potsdam](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/zh_cn/dataset_prepare.md#isprs-potsdam)
 - [x] [Vaihingen](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/zh_cn/dataset_prepare.md#isprs-vaihingen)
 - [x] [iSAID](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/zh_cn/dataset_prepare.md#isaid)
+- [x] [Mapillary Vistas](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/user_guides/2_dataset_prepare.md#mapillary-vistas-datasets)
 
 </details>
 

projects/mapillary_dataset/configs/_base_/datasets/mapillary_v1_2.py → configs/_base_/datasets/mapillary_v1.py

@@ -1,5 +1,5 @@
 # dataset settings
-dataset_type = 'MapillaryDataset_v1_2'
+dataset_type = 'MapillaryDataset_v1'
 data_root = 'data/mapillary/'
 crop_size = (512, 1024)
 train_pipeline = [
@@ -48,8 +48,7 @@
         type=dataset_type,
         data_root=data_root,
         data_prefix=dict(
-            img_path='training/images',
-            seg_map_path='training/v1.2/labels_mask'),
+            img_path='training/images', seg_map_path='training/v1.2/labels'),
         pipeline=train_pipeline))
 val_dataloader = dict(
     batch_size=1,
@@ -61,7 +60,7 @@
         data_root=data_root,
         data_prefix=dict(
             img_path='validation/images',
-            seg_map_path='validation/v1.2/labels_mask'),
+            seg_map_path='validation/v1.2/labels'),
         pipeline=test_pipeline))
 test_dataloader = val_dataloader
 

configs/_base_/datasets/mapillary_v1_65.py

@@ -0,0 +1,37 @@
+# dataset settings
+_base_ = './mapillary_v1.py'
+metainfo = dict(
+    classes=('Bird', 'Ground Animal', 'Curb', 'Fence', 'Guard Rail', 'Barrier',
+             'Wall', 'Bike Lane', 'Crosswalk - Plain', 'Curb Cut', 'Parking',
+             'Pedestrian Area', 'Rail Track', 'Road', 'Service Lane',
+             'Sidewalk', 'Bridge', 'Building', 'Tunnel', 'Person', 'Bicyclist',
+             'Motorcyclist', 'Other Rider', 'Lane Marking - Crosswalk',
+             'Lane Marking - General', 'Mountain', 'Sand', 'Sky', 'Snow',
+             'Terrain', 'Vegetation', 'Water', 'Banner', 'Bench', 'Bike Rack',
+             'Billboard', 'Catch Basin', 'CCTV Camera', 'Fire Hydrant',
+             'Junction Box', 'Mailbox', 'Manhole', 'Phone Booth', 'Pothole',
+             'Street Light', 'Pole', 'Traffic Sign Frame', 'Utility Pole',
+             'Traffic Light', 'Traffic Sign (Back)', 'Traffic Sign (Front)',
+             'Trash Can', 'Bicycle', 'Boat', 'Bus', 'Car', 'Caravan',
+             'Motorcycle', 'On Rails', 'Other Vehicle', 'Trailer', 'Truck',
+             'Wheeled Slow', 'Car Mount', 'Ego Vehicle'),
+    palette=[[165, 42, 42], [0, 192, 0], [196, 196, 196], [190, 153, 153],
+             [180, 165, 180], [90, 120, 150], [102, 102, 156], [128, 64, 255],
+             [140, 140, 200], [170, 170, 170], [250, 170, 160], [96, 96, 96],
+             [230, 150, 140], [128, 64, 128], [110, 110, 110], [244, 35, 232],
+             [150, 100, 100], [70, 70, 70], [150, 120, 90], [220, 20, 60],
+             [255, 0, 0], [255, 0, 100], [255, 0, 200], [200, 128, 128],
+             [255, 255, 255], [64, 170, 64], [230, 160, 50], [70, 130, 180],
+             [190, 255, 255], [152, 251, 152], [107, 142, 35], [0, 170, 30],
+             [255, 255, 128], [250, 0, 30], [100, 140, 180], [220, 220, 220],
+             [220, 128, 128], [222, 40, 40], [100, 170, 30], [40, 40, 40],
+             [33, 33, 33], [100, 128, 160], [142, 0, 0], [70, 100, 150],
+             [210, 170, 100], [153, 153, 153], [128, 128, 128], [0, 0, 80],
+             [250, 170, 30], [192, 192, 192], [220, 220, 0], [140, 140, 20],
+             [119, 11, 32], [150, 0, 255], [0, 60, 100], [0, 0, 142],
+             [0, 0, 90], [0, 0, 230], [0, 80, 100], [128, 64, 64], [0, 0, 110],
+             [0, 0, 70], [0, 0, 192], [32, 32, 32], [120, 10, 10]])
+
+train_dataloader = dict(dataset=dict(metainfo=metainfo))
+val_dataloader = dict(dataset=dict(metainfo=metainfo))
+test_dataloader = val_dataloader

projects/mapillary_dataset/configs/_base_/datasets/mapillary_v2_0.py → configs/_base_/datasets/mapillary_v2.py

@@ -1,5 +1,5 @@
 # dataset settings
-dataset_type = 'MapillaryDataset_v2_0'
+dataset_type = 'MapillaryDataset_v2'
 data_root = 'data/mapillary/'
 crop_size = (512, 1024)
 train_pipeline = [
@@ -48,8 +48,7 @@
         type=dataset_type,
         data_root=data_root,
         data_prefix=dict(
-            img_path='training/images',
-            seg_map_path='training/v2.0/labels_mask'),
+            img_path='training/images', seg_map_path='training/v2.0/labels'),
         pipeline=train_pipeline))
 val_dataloader = dict(
     batch_size=1,
@@ -61,7 +60,7 @@
         data_root=data_root,
         data_prefix=dict(
             img_path='validation/images',
-            seg_map_path='validation/v2.0/labels_mask'),
+            seg_map_path='validation/v2.0/labels'),
         pipeline=test_pipeline))
 test_dataloader = val_dataloader
 

configs/_base_/schedules/schedule_240k.py

@@ -0,0 +1,25 @@
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optim_wrapper = dict(type='OptimWrapper', optimizer=optimizer, clip_grad=None)
+# learning policy
+param_scheduler = [
+    dict(
+        type='PolyLR',
+        eta_min=1e-4,
+        power=0.9,
+        begin=0,
+        end=240000,
+        by_epoch=False)
+]
+# training schedule for 240k
+train_cfg = dict(
+    type='IterBasedTrainLoop', max_iters=240000, val_interval=24000)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+default_hooks = dict(
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=50, log_metric_by_epoch=False),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(type='CheckpointHook', by_epoch=False, interval=24000),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    visualization=dict(type='SegVisualizationHook'))

configs/deeplabv3plus/README.md

@@ -124,6 +124,12 @@ Spatial pyramid pooling module or encode-decoder structure are used in deep neur
 | DeepLabV3+ | R-18-D8  | 896x896   |   80000 | 6.19     | 24.81          | 61.35 |         62.61 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r18-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid_20220110_180526-7059991d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid/deeplabv3plus_r18-d8_4x4_896x896_80k_isaid_20220110_180526.log.json) |
 | DeepLabV3+ | R-50-D8  | 896x896   |   80000 | 21.45    | 8.42           | 67.06 |         68.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_isaid-896x896.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526-598be439.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526.log.json) |
 
+### Mapillary Vistas v1.2
+
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                                               | download                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| DeepLabV3+ | R-50-D8  | 1280x1280 |  300000 | 24.04    | 17.92          | A100   | 47.35 |             - | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280_20230301_110504-655f8e43.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280_20230301_110504.json) |
+
 Note:
 
 - `D-8`/`D-16` here corresponding to the output stride 8/16 setting for DeepLab series.

configs/deeplabv3plus/deeplabv3plus.yml

@@ -11,6 +11,7 @@ Collections:
     - Potsdam
     - Vaihingen
     - iSAID
+    - Mapillary Vistas v1.2
   Paper:
     URL: https://arxiv.org/abs/1802.02611
     Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
@@ -848,3 +849,24 @@ Models:
       mIoU(ms+flip): 68.02
   Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb4-80k_isaid-896x896.py
   Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid/deeplabv3plus_r50-d8_4x4_896x896_80k_isaid_20220110_180526-598be439.pth
+- Name: deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280
+  In Collection: DeepLabV3+
+  Metadata:
+    backbone: R-50-D8
+    crop size: (1280,1280)
+    lr schd: 300000
+    inference time (ms/im):
+    - value: 55.8
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (1280,1280)
+    Training Memory (GB): 24.04
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Mapillary Vistas v1.2
+    Metrics:
+      mIoU: 47.35
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280_20230301_110504-655f8e43.pth

configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-300k_mapillay_v1_65-1280x1280.py

@@ -0,0 +1,58 @@
+_base_ = [
+    '../_base_/models/deeplabv3plus_r50-d8.py',
+    '../_base_/datasets/mapillary_v1_65.py',
+    '../_base_/default_runtime.py',
+]
+
+crop_size = (1280, 1280)
+data_preprocessor = dict(size=crop_size)
+model = dict(
+    data_preprocessor=data_preprocessor,
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(depth=50),
+    decode_head=dict(num_classes=65),
+    auxiliary_head=dict(num_classes=65))
+
+iters = 300000
+# optimizer
+optimizer = dict(
+    type='AdamW', lr=0.0001, betas=(0.9, 0.999), weight_decay=0.0001)
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=optimizer,
+    clip_grad=dict(max_norm=0.01, norm_type=2),
+    paramwise_cfg=dict(
+        custom_keys={'backbone': dict(lr_mult=0.1, decay_mult=1.0)}))
+param_scheduler = [
+    dict(
+        type='PolyLR',
+        eta_min=0,
+        power=0.9,
+        begin=0,
+        end=iters,
+        by_epoch=False)
+]
+
+# training schedule for 300k
+train_cfg = dict(
+    type='IterBasedTrainLoop', max_iters=iters, val_interval=iters // 10)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+default_hooks = dict(
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=50, log_metric_by_epoch=False),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(
+        type='CheckpointHook', by_epoch=False, interval=iters // 10),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    visualization=dict(type='SegVisualizationHook'))
+
+train_dataloader = dict(batch_size=2)
+
+# Default setting for scaling LR automatically
+#   - `enable` means enable scaling LR automatically
+#       or not by default.
+#   - `base_batch_size` = (4 GPUs) x (2 samples per GPU).
+auto_scale_lr = dict(enable=False, base_batch_size=8)

docs/en/user_guides/2_dataset_prepare.md

@@ -154,6 +154,29 @@ mmsegmentation
 │   │   │   ├── training
 │   │   │   ├── validation
 │   │   │   ├── test
+│   ├── mapillary
+│   │   ├── training
+│   │   │   ├── images
+│   │   │   ├── v1.2
+|   │   │   │   ├── instances
+|   │   │   │   ├── labels
+|   │   │   │   └── panoptic
+│   │   │   ├── v2.0
+|   │   │   │   ├── instances
+|   │   │   │   ├── labels
+|   │   │   │   ├── panoptic
+|   │   │   │   └── polygons
+│   │   ├── validation
+│   │   │   ├── images
+|   │   │   ├── v1.2
+|   │   │   │   ├── instances
+|   │   │   │   ├── labels
+|   │   │   │   └── panoptic
+│   │   │   ├── v2.0
+|   │   │   │   ├── instances
+|   │   │   │   ├── labels
+|   │   │   │   ├── panoptic
+|   │   │   │   └── polygons
 ```
 
 ### Cityscapes
@@ -551,3 +574,54 @@ The script will make directory structure below:
 ```
 
 It includes 400 images for training, 400 images for validation and 400 images for testing which is the same as REFUGE 2018 dataset.
+
+## Mapillary Vistas Datasets
+
+- The dataset could be download [here](https://www.mapillary.com/dataset/vistas) after registration.
+
+- Mapillary Vistas Dataset use 8-bit with color-palette to store labels. No conversion operation is required.
+
+- Assumption you have put the dataset zip file in `mmsegmentation/data/mapillary`
+
+- Please run the following commands to unzip dataset.
+
+  ```bash
+  cd data/mapillary
+  unzip An-ZjB1Zm61yAZG0ozTymz8I8NqI4x0MrYrh26dq7kPgfu8vf9ImrdaOAVOFYbJ2pNAgUnVGBmbue9lTgdBOb5BbKXIpFs0fpYWqACbrQDChAA2fdX0zS9PcHu7fY8c-FOvyBVxPNYNFQuM.zip
+  ```
+
+- After unzip, you will get Mapillary Vistas Dataset like this structure. Semantic segmentation mask labels in `labels` folder.
+
+  ```none
+  mmsegmentation
+  ├── mmseg
+  ├── tools
+  ├── configs
+  ├── data
+  │   ├── mapillary
+  │   │   ├── training
+  │   │   │   ├── images
+  │   │   │   ├── v1.2
+  |   │   │   │   ├── instances
+  |   │   │   │   ├── labels
+  |   │   │   │   └── panoptic
+  │   │   │   ├── v2.0
+  |   │   │   │   ├── instances
+  |   │   │   │   ├── labels
+  |   │   │   │   ├── panoptic
+  |   │   │   │   └── polygons
+  │   │   ├── validation
+  │   │   │   ├── images
+  |   │   │   ├── v1.2
+  |   │   │   │   ├── instances
+  |   │   │   │   ├── labels
+  |   │   │   │   └── panoptic
+  │   │   │   ├── v2.0
+  |   │   │   │   ├── instances
+  |   │   │   │   ├── labels
+  |   │   │   │   ├── panoptic
+  |   │   │   │   └── polygons
+  ```
+
+- You could set Datasets version with `MapillaryDataset_v1` and `MapillaryDataset_v2` in your configs.
+  View the Mapillary Vistas Datasets config file here [V1.2](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v1.py) and  [V2.0](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/_base_/datasets/mapillary_v2.py)

mmseg/datasets/__init__.py

@@ -14,6 +14,7 @@
 from .isprs import ISPRSDataset
 from .lip import LIPDataset
 from .loveda import LoveDADataset
+from .mapillary import MapillaryDataset_v1, MapillaryDataset_v2
 from .night_driving import NightDrivingDataset
 from .pascal_context import PascalContextDataset, PascalContextDataset59
 from .potsdam import PotsdamDataset
@@ -49,5 +50,6 @@
     'DecathlonDataset', 'LIPDataset', 'ResizeShortestEdge',
     'BioMedicalGaussianNoise', 'BioMedicalGaussianBlur',
     'BioMedicalRandomGamma', 'BioMedical3DPad', 'RandomRotFlip',
-    'SynapseDataset', 'REFUGEDataset'
+    'SynapseDataset', 'REFUGEDataset', 'MapillaryDataset_v1',
+    'MapillaryDataset_v2'
 ]