Bump version to v0.13.0 (#777)

* Bump version to v0.13.0

* polish changelog

* Update changelog.md

* Update changelog.md

Co-authored-by: lizz <[email protected]>

README.md

@@ -55,7 +55,7 @@ The master branch works with **PyTorch 1.3+**.
 
 ## Changelog
 
-v0.12.0 was released in 28/02/2021. Please refer to [changelog.md](docs/changelog.md) for details and release history.
+v0.13.0 was released in 31/03/2021. Please refer to [changelog.md](docs/changelog.md) for details and release history.
 
 ## Benchmark
 

README_zh-CN.md

@@ -49,7 +49,7 @@ MMAction2 是一款基于 PyTorch 的视频理解开源工具箱，是 [OpenMMLa
 
 ## 更新记录
 
-v0.12.0 版本已于 2021 年 2 月 28 日发布，可通过查阅 [更新日志](/docs/changelog.md) 了解更多细节以及发布历史
+v0.13.0 版本已于 2021 年 3 月 31 日发布，可通过查阅 [更新日志](/docs/changelog.md) 了解更多细节以及发布历史
 
 ## 基准测试
 
@@ -88,6 +88,7 @@ v0.12.0 版本已于 2021 年 2 月 28 日发布，可通过查阅 [更新日志
 - ✅ [X3D](/configs/recognition/x3d/README.md) (CVPR'2020)
 - ✅ [OmniSource](/configs/recognition/omnisource/README.md) (ECCV'2020)
 - ✅ [MultiModality: Audio](/configs/recognition_audio/resnet/README.md) (ArXiv'2020)
+- ✅ [TANet](configs/recognition/tanet/README.md) (ArXiv'2020)
 
 </details>
 
@@ -109,6 +110,7 @@ v0.12.0 版本已于 2021 年 2 月 28 日发布，可通过查阅 [更新日志
 
 - ✅ [SlowOnly+Fast R-CNN](/configs/detection/ava/README.md) (ICCV'2019)
 - ✅ [SlowFast+Fast R-CNN](/configs/detection/ava/README.md) (ICCV'2019)
+- ✅ [Long-Term Feature Bank](configs/detection/lfb/README.md) (CVPR'2019)
 
 </details>
 

docs/changelog.md

@@ -6,7 +6,7 @@
 
 - Support LFB
 - Support using backbone from MMCls/TorchVision
-- Support Chinese documentation
+- Add Chinese documentation
 
 **New Features**
 
@@ -20,11 +20,11 @@
 
 - Add slowfast config/json/log/ckpt for training custom classes of AVA ([#678](https://github.com/open-mmlab/mmaction2/pull/678))
 - Set RandAugment as Imgaug default transforms ([#585](https://github.com/open-mmlab/mmaction2/pull/585))
-- Add `--test-last` & `--test-best` for `tools/train.py` to test checkpoints after training ([#608](https://github.com/open-mmlab/mmaction2/pull/608)
+- Add `--test-last` & `--test-best` for `tools/train.py` to test checkpoints after training ([#608](https://github.com/open-mmlab/mmaction2/pull/608))
 - Add fcn_testing in TPN ([#684](https://github.com/open-mmlab/mmaction2/pull/684))
 - Remove redundant recall functions ([#741](https://github.com/open-mmlab/mmaction2/pull/741))
 - Recursively remove pretrained step for testing ([#695](https://github.com/open-mmlab/mmaction2/pull/695))
-- Add limiter for demo ([#668](https://github.com/open-mmlab/mmaction2/pull/668))
+- Improve demo by limiting inference fps ([#668](https://github.com/open-mmlab/mmaction2/pull/668))
 
 **Bug and Typo Fixes**
 
@@ -35,9 +35,9 @@
 **ModelZoo**
 
 - Add LFB for AVA2.1 ([#553](https://github.com/open-mmlab/mmaction2/pull/553))
-- Add slowonly_nl_embedded_gaussian_r50_4x16x1_150e_kinetics400_rgb ([#690](https://github.com/open-mmlab/mmaction2/pull/690))
 - Add TSN with ResNeXt-101-32x4d backbone as an example for using MMCls backbones ([#679](https://github.com/open-mmlab/mmaction2/pull/679))
 - Add TSN with Densenet161 backbone as an example for using TorchVision backbones ([#720](https://github.com/open-mmlab/mmaction2/pull/720))
+- Add slowonly_nl_embedded_gaussian_r50_4x16x1_150e_kinetics400_rgb ([#690](https://github.com/open-mmlab/mmaction2/pull/690))
 - Add slowonly_nl_embedded_gaussian_r50_8x8x1_150e_kinetics400_rgb ([#704](https://github.com/open-mmlab/mmaction2/pull/704))
 - Add slowonly_nl_kinetics_pretrained_r50_4x16x1(8x8x1)_20e_ava_rgb ([#730](https://github.com/open-mmlab/mmaction2/pull/730))
 

mmaction/version.py

@@ -1,6 +1,6 @@
 # Copyright (c) Open-MMLab. All rights reserved.
 
-__version__ = '0.12.0'
+__version__ = '0.13.0'
 
 
 def parse_version_info(version_str):