Squashed commit of the following:

commit e9cae2d Author: Haian Huang(深度眸) <huanghaian@sensetime.com> Date: Tue Feb 28 10:17:10 2023 +0800 Bump version to v2.28.2 (open-mmlab#9820) commit 6a904c5 Author: RangiLyu <lyuchqi@gmail.com> Date: Wed Feb 22 14:51:40 2023 +0800 [Maintain]: Update .owners.yml (open-mmlab#9818) commit d8d03bf Author: chenxujun <co63oc@users.noreply.github.com> Date: Sun Feb 19 21:45:08 2023 +0800 [Doc]: update customize_runtime.md (open-mmlab#9797) commit 56a3485 Author: Ginray <ginray0215@gmail.com> Date: Fri Feb 17 18:42:34 2023 +0800 [Doc] Fix the configuration file and log path of centernet. (open-mmlab#9791) commit 0379d4d Author: vansin <msnode@163.com> Date: Thu Feb 16 09:55:56 2023 +0800 [Doc]: Add twitter discord medium youtube link (open-mmlab#9774) commit 831ba64 Author: RangiLyu <lyuchqi@gmail.com> Date: Tue Feb 7 20:02:56 2023 +0800 [Fix] Fix WIDERFace SSD loss NAN. (open-mmlab#9734) commit e7cedcd Author: RangiLyu <lyuchqi@gmail.com> Date: Mon Feb 6 20:38:57 2023 +0800 [Doc]: fix readthedoc (open-mmlab#9729)
papercatnku · Apr 7, 2023 · 3d13273 · 3d13273
1 parent 62d805f
commit 3d13273
Show file tree

Hide file tree

Showing 13 changed files with 61 additions and 23 deletions.
diff --git a/.owners.yml b/.owners.yml
@@ -6,8 +6,8 @@ assign:
   assignees:
     - Czm369
     - hhaAndroid
-    - zytx121
+    - zwhus
     - RangiLyu
     - BIGWangYuDong
-    - chhluo
+    - ZwwWayne
     - ZwwWayne
diff --git a/.readthedocs.yml b/.readthedocs.yml
@@ -3,7 +3,7 @@ version: 2
 formats: all
 
 python:
-  version: 3.7
+  version: 3.8
   install:
     - requirements: requirements/docs.txt
     - requirements: requirements/readthedocs.txt
diff --git a/README.md b/README.md
@@ -41,6 +41,19 @@ English | [简体中文](README_zh-CN.md)
 
 </div>
 
+<div align="center">
+  <a href="https://openmmlab.medium.com/" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218352562-cdded397-b0f3-4ca1-b8dd-a60df8dca75b.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://discord.gg/raweFPmdzG" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218347213-c080267f-cbb6-443e-8532-8e1ed9a58ea9.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://twitter.com/OpenMMLab" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218346637-d30c8a0f-3eba-4699-8131-512fb06d46db.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://www.youtube.com/openmmlab" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218346691-ceb2116a-465a-40af-8424-9f30d2348ca9.png" width="3%" alt="" /></a>
+</div>
 ## Introduction
 
 MMDetection is an open source object detection toolbox based on PyTorch. It is
@@ -77,11 +90,9 @@ Apart from MMDetection, we also released a library [mmcv](https://github.com/ope
 
 ### 💎 Stable version
 
-**2.28.1** was released in 1/2/2023:
+**2.28.2** was released in 27/2/2023:
 
-- Support Objects365 Dataset, and Separated and Occluded COCO metric
-- Support acceleration of RetinaNet and SSD on Ascend
-- Deprecate the support of Python 3.6 and fix some bugs of 2.28.0
+- Fixed some known documentation, configuration and linking error issues
 
 Please refer to [changelog.md](docs/en/changelog.md) for details and release history.
 
@@ -107,10 +118,14 @@ We are excited to announce our latest work on real-time object recognition tasks
 <img src="https://user-images.githubusercontent.com/12907710/208044554-1e8de6b5-48d8-44e4-a7b5-75076c7ebb71.png"/>
 </div>
 
-A brand new version of **MMDetection v3.0.0rc5** was released in 26/12/2022:
+A brand new version of **MMDetection v3.0.0rc6** was released in 27/2/2023:
 
-- Support [RTMDet](https://arxiv.org/abs/2212.07784) instance segmentation models. The technical report of RTMDet is on [arxiv](https://arxiv.org/abs/2212.07784)
-- Support SSHContextModule in paper [SSH: Single Stage Headless Face Detector](https://arxiv.org/abs/1708.03979)
+- Support [Boxinst](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/boxinst), [Objects365 Dataset](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/objects365), and [Separated and Occluded COCO metric](https://github.com/open-mmlab/mmdetection/tree/3.x/docs/en/user_guides/useful_tools.md#coco-separated--occluded-mask-metric)
+- Support [ConvNeXt-V2](https://github.com/open-mmlab/mmdetection/tree/3.x/projects/ConvNeXt-V2), [DiffusionDet](https://github.com/open-mmlab/mmdetection/tree/3.x/projects/DiffusionDet), and inference of [EfficientDet](https://github.com/open-mmlab/mmdetection/tree/3.x/projects/EfficientDet) and [Detic](https://github.com/open-mmlab/mmdetection/tree/3.x/projects/Detic) in `Projects`
+- Refactor [DETR](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/detr) series and support [Conditional-DETR](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/conditional_detr), [DAB-DETR](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/dab_detr), and [DINO](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/dino)
+- Support DetInferencer, Test Time Augmentation, and auto import modules from registry
+- Support RTMDet-Ins ONNXRuntime and TensorRT [deployment](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet/README.md#deployment-tutorial)
+- Support [calculating FLOPs of detectors](https://github.com/open-mmlab/mmdetection/tree/3.x/docs/en/user_guides/useful_tools.md#Model-Complexity)
 
 Find more new features in [3.x branch](https://github.com/open-mmlab/mmdetection/tree/3.x). Issues and PRs are welcome!
 

diff --git a/README_zh-CN.md b/README_zh-CN.md
@@ -76,11 +76,9 @@ MMDetection 是一个基于 PyTorch 的目标检测开源工具箱。它是 [Ope
 
 ### 💎 稳定版本
 
-最新的 **2.28.1** 版本已经在 2023.2.1 发布:
+最新的 **2.28.2** 版本已经在 2023.2.27 发布:
 
-- 支持 Object365 数据集和遮挡物检测的 benchmark
-- 支持 SSD 和 RetinaNet 算法在昇腾芯片上的加速
-- 不再保证对 Python 3.6 的支持并修复了 2.28.0 的一些 bug
+- 修复了一些已知的文档、配置和链接错误问题
 
 如果想了解更多版本更新细节和历史信息，请阅读[更新日志](docs/en/changelog.md)。
 
@@ -106,10 +104,14 @@ MMDetection 是一个基于 PyTorch 的目标检测开源工具箱。它是 [Ope
 <img src="https://user-images.githubusercontent.com/12907710/208044554-1e8de6b5-48d8-44e4-a7b5-75076c7ebb71.png"/>
 </div>
 
-全新的 **v3.0.0rc5** 版本已经在 2022.12.26 发布：
+全新的 **v3.0.0rc6** 版本已经在 2023.2.27 发布：
 
-- 支持了 [RTMDet](https://arxiv.org/abs/2212.07784) 的实例分割模型。RTMDet 的技术报告发布在了 [arxiv](https://arxiv.org/abs/2212.07784) 上。
-- 支持了 [SSH: Single Stage Headless Face Detector](https://arxiv.org/abs/1708.03979) 论文中的 SSHContextModule
+- 支持了 [Boxinst](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/boxinst), [Objects365 Dataset](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/objects365) 和 [Separated and Occluded COCO metric](https://github.com/open-mmlab/mmdetection/tree/3.x/docs/zh_cn/user_guides/useful_tools.md#coco-分离和遮挡实例分割性能评估)
+- 在 `Projects` 中支持了 [ConvNeXt-V2](https://github.com/open-mmlab/mmdetection/tree/3.x/projects/ConvNeXt-V2), [DiffusionDet](https://github.com/open-mmlab/mmdetection/tree/3.x/projects/DiffusionDet) 和 [EfficientDet](https://github.com/open-mmlab/mmdetection/tree/3.x/projects/EfficientDet), [Detic](https://github.com/open-mmlab/mmdetection/tree/3.x/projects/Detic) 的推理
+- 重构了 [DETR](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/detr) 系列并支持了 [Conditional-DETR](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/conditional_detr), [DAB-DETR](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/dab_detr) 和 [DINO](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/dino)
+- 支持了 DetInferencer, Test Time Augmentation 以及从注册表 (registry) 自动导入模块
+- 支持了 RTMDet-Ins 的 ONNXRuntime 和 TensorRT [部署](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet/README.md#deployment-tutorial)
+- 支持了检测器[计算 FLOPS](https://github.com/open-mmlab/mmdetection/tree/3.x/docs/zh_cn/user_guides/useful_tools.md#模型复杂度)
 
 ## 安装
 

diff --git a/configs/wider_face/ssd300_wider_face.py b/configs/wider_face/ssd300_wider_face.py
@@ -5,7 +5,7 @@
 model = dict(bbox_head=dict(num_classes=1))
 # optimizer
 optimizer = dict(type='SGD', lr=0.012, momentum=0.9, weight_decay=5e-4)
-optimizer_config = dict()
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
 # learning policy
 lr_config = dict(
     policy='step',

diff --git a/docker/serve/Dockerfile b/docker/serve/Dockerfile
@@ -4,7 +4,7 @@ ARG CUDNN="7"
 FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel
 
 ARG MMCV="1.3.17"
-ARG MMDET="2.28.1"
+ARG MMDET="2.28.2"
 
 ENV PYTHONUNBUFFERED TRUE
 

diff --git a/docs/en/changelog.md b/docs/en/changelog.md
@@ -1,5 +1,23 @@
 ## Changelog
 
+### v2.28.2 (24/2/2023)
+
+#### New Features and Improvements
+
+- Add Twitter, Discord, Medium and YouTube link (#9774)
+- Update `customize_runtime.md` (#9797)
+
+#### Bug Fixes
+
+- Fix `WIDERFace SSD` loss for Nan problem (#9734)
+- Fix missing API documentation in Readthedoc (#9729)
+- Fix the configuration file and log path of CenterNet (#9791)
+
+#### Contributors
+
+A total of 4 developers contributed to this release.
+Thanks @co63oc, @Ginray, @vansin, @RangiLyu
+
 ### v2.28.1 (1/2/2023)
 
 #### Bug Fixes

diff --git a/docs/en/faq.md b/docs/en/faq.md
@@ -11,6 +11,7 @@ We list some common troubles faced by many users and their corresponding solutio
 | MMDetection version |        MMCV version        |
 | :-----------------: | :------------------------: |
 |       master        | mmcv-full>=1.3.17, \<1.8.0 |
+|       2.28.2        | mmcv-full>=1.3.17, \<1.8.0 |
 |       2.28.1        | mmcv-full>=1.3.17, \<1.8.0 |
 |       2.28.0        | mmcv-full>=1.3.17, \<1.8.0 |
 |       2.27.0        | mmcv-full>=1.3.17, \<1.8.0 |

diff --git a/docs/en/tutorials/customize_runtime.md b/docs/en/tutorials/customize_runtime.md
@@ -287,7 +287,7 @@ There are some common hooks that are not registered through `custom_hooks`, they
 
 In those hooks, only the logger hook has the `VERY_LOW` priority, others' priority are `NORMAL`.
 The above-mentioned tutorials already covers how to modify `optimizer_config`, `momentum_config`, and `lr_config`.
-Here we reveals how what we can do with `log_config`, `checkpoint_config`, and `evaluation`.
+Here we reveal how what we can do with `log_config`, `checkpoint_config`, and `evaluation`.
 
 #### Checkpoint config
 
@@ -297,7 +297,7 @@ The MMCV runner will use `checkpoint_config` to initialize [`CheckpointHook`](ht
 checkpoint_config = dict(interval=1)
 ```
 
-The users could set `max_keep_ckpts` to only save only small number of checkpoints or decide whether to store state dict of optimizer by `save_optimizer`. More details of the arguments are [here](https://mmcv.readthedocs.io/en/latest/api.html#mmcv.runner.CheckpointHook)
+The users could set `max_keep_ckpts` to save only small number of checkpoints or decide whether to store state dict of optimizer by `save_optimizer`. More details of the arguments are [here](https://mmcv.readthedocs.io/en/latest/api.html#mmcv.runner.CheckpointHook)
 
 #### Log config
 

diff --git a/docs/zh_cn/device/npu.md b/docs/zh_cn/device/npu.md
@@ -27,7 +27,7 @@ python tools/train.py configs/ssd/ssd300_coco.py
 | [retinanet-r50](<>)  |  36.6  |   ---   | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/retinanet/retinanet_r50_fpn_fp16_1x_coco.py)           | [log](https://download.openmmlab.com/mmdetection/v2.0/npu/retinanet_r50_fpn_1x_coco.log.json)                |
 |   [yolov3-608](<>)   |  34.7  |   ---   | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/yolo/yolov3_d53_fp16_mstrain-608_273e_coco.py)         | [log](https://download.openmmlab.com/mmdetection/v2.0/npu/yolov3_d53_fp16_mstrain-608_273e_coco.log.json)    |
 |  [yolox-s\*\*](<>)   |  39.9  |   ---   | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/yolox/yolox_s_8x8_300e_coco.py)                        | [log](https://download.openmmlab.com/mmdetection/v2.0/npu/yolox_s_8x8_300e_coco.log.json)                    |
-| [centernet-r18](<>)  |  26.1  |   ---   | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/centernet/centernet_resnet18_140e_cocoo.py)            | [log](https://download.openmmlab.com/mmdetection/v2.0/npu/centernet_resnet18_140e_coco.log.jsonn)            |
+| [centernet-r18](<>)  |  26.1  |   ---   | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/centernet/centernet_resnet18_140e_coco.py)             | [log](https://download.openmmlab.com/mmdetection/v2.0/npu/centernet_resnet18_140e_coco.log.json)             |
 |   [fcos-r50\*](<>)   |  36.1  |   ---   | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/fcos/fcos_r50_caffe_fpn_gn-head_fp16_1x_bs8x8_coco.py) | [log](https://download.openmmlab.com/mmdetection/v2.0/npu/fcos_r50_caffe_fpn_gn-head_1x_coco_bs8x8.log.json) |
 |   [solov2-r50](<>)   |  ---   |  34.7   | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/solov2/solov2_r50_fpn_1x_coco.py)                      | [log](https://download.openmmlab.com/mmdetection/v2.0/npu/solov2_r50_fpn_1x_coco.log.json)                   |
 

diff --git a/docs/zh_cn/get_started.md b/docs/zh_cn/get_started.md
@@ -12,6 +12,7 @@ MMDetection 和 MMCV 版本兼容性如下所示，需要安装正确的 MMCV
 | MMDetection 版本 |         MMCV 版本          |
 | :--------------: | :------------------------: |
 |      master      | mmcv-full>=1.3.17, \<1.8.0 |
+|      2.28.2      | mmcv-full>=1.3.17, \<1.8.0 |
 |      2.28.1      | mmcv-full>=1.3.17, \<1.8.0 |
 |      2.28.0      | mmcv-full>=1.3.17, \<1.8.0 |
 |      2.27.0      | mmcv-full>=1.3.17, \<1.8.0 |

diff --git a/mmdet/version.py b/mmdet/version.py
@@ -1,6 +1,6 @@
 # Copyright (c) OpenMMLab. All rights reserved.
 
-__version__ = '2.28.1'
+__version__ = '2.28.2'
 short_version = __version__
 
 

diff --git a/requirements/readthedocs.txt b/requirements/readthedocs.txt
@@ -1,3 +1,4 @@
 mmcv
+scipy
 torch
 torchvision