Bump to v0.7.0 (#258)

* Bump to v0.7.0 * update date in readme.md
open-mmlab · Sep 3, 2021 · a482409 · a482409
1 parent c44b7a4
commit a482409
Show file tree

Hide file tree

Showing 8 changed files with 45 additions and 16 deletions.
diff --git a/README.md b/README.md
@@ -48,7 +48,7 @@ This project is released under the [Apache 2.0 license](LICENSE).
 
 ## Changelog
 
-v0.6.0 was released in 30/07/2021.
+v0.7.0 was released in 03/09/2021.
 Please refer to [changelog.md](docs/changelog.md) for details and release history.
 
 ## Benchmark and model zoo

diff --git a/README_zh-CN.md b/README_zh-CN.md
@@ -47,7 +47,7 @@ MMTracking是一款基于PyTorch的视频目标感知开源工具箱，是[OpenM
 
 ## 更新记录
 
-v0.6.0版本已于2021年7月30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。
+v0.7.0版本已于2021年9月3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。
 
 ## 基准测试与模型库
 
@@ -58,6 +58,7 @@ v0.6.0版本已于2021年7月30日发布，可通过查阅[更新日志](/docs/c
 - [x] [DFF](configs/vid/dff) (CVPR 2017)
 - [x] [FGFA](configs/vid/fgfa) (ICCV 2017)
 - [x] [SELSA](configs/vid/selsa) (ICCV 2019)
+- [x] [Temporal RoI Align](configs/vid/temporal_roi_align) (AAAI 2021)
 
 支持的多目标跟踪算法:
 
@@ -72,9 +73,17 @@ v0.6.0版本已于2021年7月30日发布，可通过查阅[更新日志](/docs/c
 
 请参考[安装指南](docs/install.md)进行安装。
 
-## 教程
+## 开始使用MMTracking
 
-请参考[数据集](docs/dataset.md)和[快速开始](docs/quick_run.md)了解MMTracking的基本使用。MMTracking也提供了更详细的[教程](docs/tutorials/)。
+请参考[数据集](docs/dataset.md)和[快速开始](docs/quick_run.md)了解MMTracking的基本使用。MMTracking也提供了更详细的[教程](docs/tutorials/)，比如[了解配置文件](docs/tutorials/config.md), [一个有关视频目标检测器配置文件的详细解释](docs/tutorials/config_vid.md), [一个有关多目标跟踪器配置文件的详细解释](docs/tutorials/config_mot.md), [一个有关单目标跟踪器配置文件的详细解释](docs/tutorials/config_sot.md), [自定义数据集](docs/tutorials/customize_dataset.md), [自定义数据预处理流程]](docs/tutorials/customize_data_pipeline.md), [自定义视频目标检测器](docs/tutorials/customize_vid_model.md), [自定义多目标跟踪器](docs/tutorials/customize_mot_model.md), [自定义单目标跟踪器](docs/tutorials/customize_sot_model.md), [自定义训练配置](docs/tutorials/customize_runtime.md) and [有用的工具和脚本](docs/useful_tools_scripts.md).
+
+## 参与贡献
+
+我们非常欢迎用户对于MMTracking做出的任何贡献，可以参考[贡献指南](https://github.com/open-mmlab/mmcv/blob/master/CONTRIBUTING.md)文件了解更多细节。
+
+## 致谢
+
+MMTracking是一款开源项目，我们欢迎任何贡献和反馈。我们希望该工具箱和基准测试可以为社区提供灵活的代码工具，供用户复现现有算法并开发自己新的视频目标感知方法。
 
 ## 引用
 
@@ -89,14 +98,6 @@ v0.6.0版本已于2021年7月30日发布，可通过查阅[更新日志](/docs/c
 }
 ```
 
-## 参与贡献
-
-我们非常欢迎用户对于MMTracking做出的任何贡献，可以参考[贡献指南]([/.github/CONTRIBUTING.md](https://github.com/open-mmlab/mmcv/blob/master/CONTRIBUTING.md))文件了解更多细节。
-
-## 致谢
-
-MMTracking是一款开源项目，我们欢迎任何贡献和反馈。我们希望该工具箱和基准测试可以为社区提供灵活的代码工具，供用户复现现有算法并开发自己新的视频目标感知方法。
-
 ## OpenMMLab 的其他项目
 
 - [MMCV](https://github.com/open-mmlab/mmcv)：OpenMMLab计算机视觉基础库

diff --git a/configs/vid/temporal_roi_align/metafile.yml b/configs/vid/temporal_roi_align/metafile.yml
@@ -45,4 +45,4 @@ Models:
         Dataset: ILSVRC
         Metrics:
           box [email protected]: 84.1
-    Weights: https://download.openmmlab.com/mmtracking/vid/temporal_roi_align/selsa_troialign_faster_rcnn_r101_dc5_7e_imagenetvid/selsa_troialign_faster_rcnn_r101_dc5_7e_imagenetvid_20210822_111621-22cb96b9.pth
+    Weights: https://download.openmmlab.com/mmtracking/vid/temporal_roi_align/selsa_troialign_faster_rcnn_x101_dc5_7e_imagenetvid/selsa_troialign_faster_rcnn_x101_dc5_7e_imagenetvid_20210822_164036-4471ac42.pth
diff --git a/docs/changelog.md b/docs/changelog.md
@@ -1,5 +1,31 @@
 ## Changelog
 
+### v0.7.0 (03/09/2021)
+
+#### Highlights
+
+- Release code of AAAI 2021 paper 'Temporal ROI Align for Video Object Recognition' ([#247](https://github.com/open-mmlab/mmtracking/pull/247))
+- Refactor English documentations ([#243](https://github.com/open-mmlab/mmtracking/pull/243))
+- Add Chinese documentations ([#248](https://github.com/open-mmlab/mmtracking/pull/248)), ([#250](https://github.com/open-mmlab/mmtracking/pull/250))
+
+#### New Features
+
+- Support fp16 training and testing ([#230](https://github.com/open-mmlab/mmtracking/pull/230))
+- Release model using ResNeXt-101 as backbone for all VID methods ([#254](https://github.com/open-mmlab/mmtracking/pull/254))
+- Support the results of Tracktor on MOT15, MOT16 and MOT20 datasets ([#217](https://github.com/open-mmlab/mmtracking/pull/217))
+- Support visualization for single gpu test ([#216](https://github.com/open-mmlab/mmtracking/pull/216))
+
+#### Bug Fixes
+
+- Fix a bug in MOTP evaluation ([#235](https://github.com/open-mmlab/mmtracking/pull/235))
+- Fix two bugs in reid training and testing ([#249](https://github.com/open-mmlab/mmtracking/pull/249))
+
+#### Improvements
+
+- Refactor anchor in SiameseRPN++ ([#229](https://github.com/open-mmlab/mmtracking/pull/229))
+- Unify model initialization ([#235](https://github.com/open-mmlab/mmtracking/pull/235))
+- Refactor unittest ([#231](https://github.com/open-mmlab/mmtracking/pull/231))
+
 ### v0.6.0 (30/07/2021)
 
 #### Highlights

diff --git a/docs/install.md b/docs/install.md
@@ -14,6 +14,7 @@ The compatible MMTracking, MMCV, and MMDetection versions are as below. Please i
 |:-------------------:|:------------------------:|:-----------------------------:|
 |        master       | mmcv-full>=1.3.8, <1.4.0 |       MMDetection>=2.14.0      |
 |        0.6.0        | mmcv-full>=1.3.8, <1.4.0 |       MMDetection>=2.14.0     |
+|        0.7.0        | mmcv-full>=1.3.8, <1.4.0 |       MMDetection>=2.14.0     |
 
 ## Installation
 

diff --git a/docs_zh-CN/install.md b/docs_zh-CN/install.md
@@ -14,6 +14,7 @@
 |:-------------------:|:------------------------:|:-----------------------------:|
 |        master       | mmcv-full>=1.3.8, <1.4.0 |       MMDetection>=2.14.0      |
 |        0.6.0        | mmcv-full>=1.3.8, <1.4.0 |       MMDetection>=2.14.0     |
+|        0.7.0        | mmcv-full>=1.3.8, <1.4.0 |       MMDetection>=2.14.0     |
 
 ## 安装
 

diff --git a/mmtrack/__init__.py b/mmtrack/__init__.py
@@ -60,14 +60,14 @@ def digit_version(version_str: str, length: int = 4):
 
 assert (mmcv_min_version <= mmcv_version < mmcv_max_version), \
     f'MMCV=={mmcv.__version__} is used but incompatible. ' \
-    f'Please install mmcv>={mmcv_min_version}, <{mmcv_max_version}.'
+    f'Please install mmcv>={MMCV_MIN}, <{MMCV_MAX}.'
 
 mmdet_min_version = digit_version(MMDET_MIN)
 mmdet_version = digit_version(mmdet.__version__)
 
 
 assert (mmdet_min_version <= mmdet_version), \
     f'MMDet=={mmdet.__version__} is used but incompatible. ' \
-    f'Please install mmdet>={mmdet_min_version}.'
+    f'Please install mmdet>={MMDET_MIN}.'
 
 __all__ = ['__version__', 'version_info', 'digit_version']
diff --git a/mmtrack/version.py b/mmtrack/version.py
@@ -1,6 +1,6 @@
 # Copyright (c) Open-MMLab. All rights reserved.
 
-__version__ = '0.6.0'
+__version__ = '0.7.0'
 
 
 def parse_version_info(version_str):