Bump to version v2.20.0 (#6902)

* bump to version 2.20.0

* update the commit in master

* fix comments

* Fix comments

Author: AronLin

README.md

@@ -13,10 +13,10 @@
   <img src="https://user-images.githubusercontent.com/12907710/137271636-56ba1cd2-b110-4812-8221-b4c120320aa9.png"/>
 
 
-[📘Documentation](https://mmdetection.readthedocs.io/en/v2.19.1/) |
-[🛠️Installation](https://mmdetection.readthedocs.io/en/v2.19.1/get_started.html) |
-[👀Model Zoo](https://mmdetection.readthedocs.io/en/v2.19.1/model_zoo.html) |
-[🆕Update News](https://mmdetection.readthedocs.io/en/v2.19.1/changelog.html) |
+[📘Documentation](https://mmdetection.readthedocs.io/en/v2.20.0/) |
+[🛠️Installation](https://mmdetection.readthedocs.io/en/v2.20.0/get_started.html) |
+[👀Model Zoo](https://mmdetection.readthedocs.io/en/v2.20.0/model_zoo.html) |
+[🆕Update News](https://mmdetection.readthedocs.io/en/v2.20.0/changelog.html) |
 [🚀Ongoing Projects](https://github.com/open-mmlab/mmdetection/projects) |
 [🤔Reporting Issues](https://github.com/open-mmlab/mmdetection/issues/new/choose)
 
@@ -60,11 +60,10 @@ This project is released under the [Apache 2.0 license](LICENSE).
 
 ## Changelog
 
-**2.19.1** was released in 14/12/2021:
+**2.20.0** was released in 27/12/2021:
 
-- Release [YOLOX](configs/yolox/README.md) COCO pretrained models
-- Add abstract and sketch of the papers in readmes
-- Fix some weight initialization bugs
+- Support [TOOD](configs/tood/README.md): Task-aligned One-stage Object Detection (ICCV 2021 Oral)
+- Support resuming from the latest checkpoint automatically
 
 Please refer to [changelog.md](docs/en/changelog.md) for details and release history.
 

README_zh-CN.md

@@ -13,10 +13,10 @@
   <img src="https://user-images.githubusercontent.com/12907710/137271636-56ba1cd2-b110-4812-8221-b4c120320aa9.png"/>
 
 
-[📘使用文档](https://mmdetection.readthedocs.io/zh_CN/v2.19.1/) |
-[🛠️安装教程](https://mmdetection.readthedocs.io/zh_CN/v2.19.1/get_started.html) |
-[👀模型库](https://mmdetection.readthedocs.io/zh_CN/v2.19.1/model_zoo.html) |
-[🆕更新日志](https://mmdetection.readthedocs.io/en/v2.19.1/changelog.html) |
+[📘使用文档](https://mmdetection.readthedocs.io/zh_CN/v2.20.0/) |
+[🛠️安装教程](https://mmdetection.readthedocs.io/zh_CN/v2.20.0/get_started.html) |
+[👀模型库](https://mmdetection.readthedocs.io/zh_CN/v2.20.0/model_zoo.html) |
+[🆕更新日志](https://mmdetection.readthedocs.io/en/v2.20.0/changelog.html) |
 [🚀进行中的项目](https://github.com/open-mmlab/mmdetection/projects) |
 [🤔报告问题](https://github.com/open-mmlab/mmdetection/issues/new/choose)
 
@@ -59,10 +59,9 @@ MMDetection 是一个基于 PyTorch 的目标检测开源工具箱。它是 [Ope
 
 ## 更新日志
 
-最新的 **2.19.1** 版本已经在 2021.12.14 发布:
-- 发布 [YOLOX](configs/yolox/README.md) COCO 预训练模型
-- 在自述文件中添加论文的摘要和草图
-- 修复一些权重初始化错误
+最新的 **2.20.0** 版本已经在 2021.12.27 发布:
+- 支持了 ICCV 2021 Oral 方法 [TOOD](configs/tood/README.md): Task-aligned One-stage Object Detection
+- 支持了自动从最新的存储参数节点恢复训练
 
 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/changelog.md)。
 

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="2.19.1"
+ARG MMDET="2.20.0"
 
 ENV PYTHONUNBUFFERED TRUE
 

docs/en/changelog.md

@@ -1,5 +1,32 @@
 ## Changelog
 
+### v2.20.0 (27/12/2021)
+
+#### New Features
+
+- Support [TOOD](configs/tood/README.md): Task-aligned One-stage Object Detection (ICCV 2021 Oral) (#6746)
+- Support resuming from the latest checkpoint automatically (#6727)
+
+#### Bug Fixes
+
+- Fix wrong bbox `loss_weight` of the PAA head (#6744)
+- Fix the padding value of `gt_semantic_seg` in batch collating (#6837)
+- Fix test error of lvis when using `classwise` (#6845)
+- Avoid BC-breaking of `get_local_path`  (#6719)
+- Fix bug in `sync_norm_hook` when the BN layer does not exist (#6852)
+- Use pycocotools directly no matter what platform it is (#6838)
+
+#### Improvements
+
+- Add unit test for SimOTA with no valid bbox (#6770)
+- Use precommit to check readme (#6802)
+- Support selecting GPU-ids in non-distributed testing time (#6781)
+
+#### Contributors
+
+A total of 12 developers contributed to this release.
+Thanks @ZwwWayne, @Czm369, @jshilong, @RangiLyu, @BIGWangYuDong, @hhaAndroid, @jamiechoi1995, @AronLin, @Keiku, @gkagkos, @fcakyon, @www516717402
+
 ### v2.19.1 (14/12/2021)
 
 #### New Features

docs/en/get_started.md

@@ -12,6 +12,7 @@ Compatible MMDetection and MMCV versions are shown as below. Please install the
 | MMDetection version |    MMCV version     |
 |:-------------------:|:-------------------:|
 | master              | mmcv-full>=1.3.17, <1.5.0 |
+| 2.20.0              | mmcv-full>=1.3.17, <1.5.0 |
 | 2.19.1              | mmcv-full>=1.3.17, <1.5.0 |
 | 2.19.0              | mmcv-full>=1.3.17, <1.5.0 |
 | 2.18.0              | mmcv-full>=1.3.17, <1.4.0 |

mmdet/__init__.py

@@ -16,7 +16,7 @@ def digit_version(version_str):
     return digit_version
 
 
-mmcv_minimum_version = '1.3.8'
+mmcv_minimum_version = '1.3.17'
 mmcv_maximum_version = '1.5.0'
 mmcv_version = digit_version(mmcv.__version__)
 

mmdet/version.py

@@ -1,6 +1,6 @@
 # Copyright (c) OpenMMLab. All rights reserved.
 
-__version__ = '2.19.1'
+__version__ = '2.20.0'
 short_version = __version__