bump v1.1.0 (open-mmlab#2513)

mornfairy · Jul 4, 2023 · 0855fca · 0855fca
1 parent 1681afb
commit 0855fca
Show file tree

Hide file tree

Showing 11 changed files with 132 additions and 36 deletions.
diff --git a/README.md b/README.md
@@ -97,9 +97,12 @@ https://user-images.githubusercontent.com/15977946/124654387-0fd3c500-ded1-11eb-
 
 ## What's New
 
-- We are excited to release **YOLOX-Pose**, a One-Stage multi-person pose estimation model based on YOLOX. Checkout our [project page](/projects/yolox_pose/) for more details.
+- We are glad to support 3 new datasets:
+  - (CVPR 2023) [Human-Art](https://github.com/IDEA-Research/HumanArt)
+  - (CVPR 2022) [Animal Kingdom](https://github.com/sutdcv/Animal-Kingdom)
+  - (AAAI 2020) [LaPa](https://github.com/JDAI-CV/lapa-dataset/)
 
-![yolox-pose_intro](https://user-images.githubusercontent.com/26127467/226655503-3cee746e-6e42-40be-82ae-6e7cae2a4c7e.jpg)
+![image](https://github.com/open-mmlab/mmpose/assets/13503330/c9171dbb-7e7a-4c39-98e3-c92932182efb)
 
 - Welcome to [*projects of MMPose*](/projects/README.md), where you can access to the latest features of MMPose, and share your ideas and codes with the community at once. Contribution to MMPose will be simple and smooth:
 
@@ -110,18 +113,20 @@ https://user-images.githubusercontent.com/15977946/124654387-0fd3c500-ded1-11eb-
     - [RTMPose](/projects/rtmpose/)
     - [YOLOX-Pose](/projects/yolox_pose/)
     - [MMPose4AIGC](/projects/mmpose4aigc/)
+    - [Simple Keypoints](/projects/skps/)
   - Become a contributors and make MMPose greater. Start your journey from the [example project](/projects/example_project/)
 
 <br/>
 
-- 2022-04-06: MMPose [v1.0.0](https://github.com/open-mmlab/mmpose/releases/tag/v1.0.0) is officially released, with the main updates including:
+- 2023-07-04: MMPose [v1.1.0](https://github.com/open-mmlab/mmpose/releases/tag/v1.1.0) is officially released, with the main updates including:
 
-  - Release of [YOLOX-Pose](/projects/yolox_pose/), a One-Stage multi-person pose estimation model based on YOLOX
-  - Development of [MMPose for AIGC](/projects/mmpose4aigc/) based on RTMPose, generating high-quality skeleton images for Pose-guided AIGC projects
-  - Support for OpenPose-style skeleton visualization
-  - More complete and user-friendly [documentation and tutorials](https://mmpose.readthedocs.io/en/latest/overview.html)
+  - Support new datasets: Human-Art, Animal Kingdom and LaPa.
+  - Support new config type that is more user-friendly and flexible.
+  - Improve RTMPose with better performance.
+  - Migrate 3D pose estimation models on h36m.
+  - Inference speedup and webcam inference with all demo scripts.
 
-  Please refer to the [release notes](https://github.com/open-mmlab/mmpose/releases/tag/v1.0.0) for more updates brought by MMPose v1.0.0!
+  Please refer to the [release notes](https://github.com/open-mmlab/mmpose/releases/tag/v1.1.0) for more updates brought by MMPose v1.1.0!
 
 ## 0.x / 1.x Migration
 

diff --git a/README_CN.md b/README_CN.md
@@ -95,7 +95,10 @@ https://user-images.githubusercontent.com/15977946/124654387-0fd3c500-ded1-11eb-
 
 ## 最新进展
 
-- 我们发布了 **YOLOX-Pose**，一个基于 YOLOX 的 One-Stage 多人姿态估计模型。更多信息敬请参阅 YOLOX-Pose [项目主页](/projects/yolox_pose/)
+- 我们支持了三个新的数据集:
+  - (CVPR 2023) [Human-Art](https://github.com/IDEA-Research/HumanArt)
+  - (CVPR 2022) [Animal Kingdom](https://github.com/sutdcv/Animal-Kingdom)
+  - (AAAI 2020) [LaPa](https://github.com/JDAI-CV/lapa-dataset/)
 
 ![yolox-pose_intro](https://user-images.githubusercontent.com/26127467/226655503-3cee746e-6e42-40be-82ae-6e7cae2a4c7e.jpg)
 
@@ -108,18 +111,20 @@ https://user-images.githubusercontent.com/15977946/124654387-0fd3c500-ded1-11eb-
     - [RTMPose](/projects/rtmpose/)
     - [YOLOX-Pose](/projects/yolox_pose/)
     - [MMPose4AIGC](/projects/mmpose4aigc/)
+    - [Simple Keypoints](/projects/skps/)
   - 从简单的 [示例项目](/projects/example_project/) 开启您的 MMPose 代码贡献者之旅吧，让我们共同打造更好用的 MMPose！
 
 <br/>
 
-- 2022-04-06：MMPose [v1.0.0](https://github.com/open-mmlab/mmpose/releases/tag/v1.0.0) 正式发布了，主要更新包括:
+- 2023-07-04：MMPose [v1.1.0](https://github.com/open-mmlab/mmpose/releases/tag/v1.1.0) 正式发布了，主要更新包括:
 
-  - 发布了 [YOLOX-Pose](/projects/yolox_pose/)，一个基于 YOLOX 的 One-Stage 多人姿态估计模型
-  - 基于 RTMPose 开发的 [MMPose for AIGC](/projects/mmpose4aigc/)，生成高质量骨架图片用于 Pose-guided AIGC 项目
-  - 支持 OpenPose 风格的骨架可视化
-  - 更加完善、友好的 [文档和教程](https://mmpose.readthedocs.io/zh_CN/latest/overview.html)
+  - 支持新数据集：Human-Art、Animal Kingdom、LaPa。
+  - 支持新的配置文件风格，支持 IDE 跳转和搜索。
+  - 提供更强性能的 RTMPose 模型。
+  - 迁移 3D 姿态估计算法。
+  - 加速推理脚本，全部 demo 脚本支持摄像头推理。
 
-  请查看完整的 [版本说明](https://github.com/open-mmlab/mmpose/releases/tag/v1.0.0) 以了解更多 MMPose v1.0.0 带来的更新!
+  请查看完整的 [版本说明](https://github.com/open-mmlab/mmpose/releases/tag/v1.1.0) 以了解更多 MMPose v1.1.0 带来的更新!
 
 ## 0.x / 1.x 迁移
 

diff --git a/docs/en/dataset_zoo/2d_animal_keypoint.md b/docs/en/dataset_zoo/2d_animal_keypoint.md
@@ -480,8 +480,7 @@ mmpose
 </div>
 
 ```bibtex
-@InProceedings{
-    Ng_2022_CVPR,
+@inproceedings{Ng_2022_CVPR,
     author    = {Ng, Xun Long and Ong, Kian Eng and Zheng, Qichen and Ni, Yun and Yeo, Si Yong and Liu, Jun},
     title     = {Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},

diff --git a/docs/en/faq.md b/docs/en/faq.md
@@ -19,6 +19,7 @@ Detailed compatible MMPose and MMCV versions are shown as below. Please choose t
 
 | MMPose version |      MMCV/MMEngine version      |
 | :------------: | :-----------------------------: |
+|     1.1.0      |  mmcv>=2.0.1, mmengine>=0.8.0   |
 |     1.0.0      |  mmcv>=2.0.0, mmengine>=0.7.0   |
 |    1.0.0rc1    | mmcv>=2.0.0rc4, mmengine>=0.6.0 |
 |    1.0.0rc0    | mmcv>=2.0.0rc0, mmengine>=0.0.1 |

diff --git a/docs/en/installation.md b/docs/en/installation.md
@@ -23,7 +23,7 @@ We recommend that users follow our best practices to install MMPose. However, th
 
 In this section we demonstrate how to prepare an environment with PyTorch.
 
-MMPose works on Linux, Windows and macOS. It requires Python 3.7+, CUDA 9.2+ and PyTorch 1.6+.
+MMPose works on Linux, Windows and macOS. It requires Python 3.7+, CUDA 9.2+ and PyTorch 1.8+.
 
 If you are experienced with PyTorch and have already installed it, you can skip this part and jump to the [MMPose Installation](#install-mmpose). Otherwise, you can follow these steps for the preparation.
 
@@ -59,13 +59,13 @@ conda install pytorch torchvision cpuonly -c pytorch
 ```shell
 pip install -U openmim
 mim install mmengine
-mim install "mmcv>=2.0.0"
+mim install "mmcv>=2.0.1"
 ```
 
 Note that some of the demo scripts in MMPose require [MMDetection](https://github.com/open-mmlab/mmdetection) (mmdet)  for human detection. If you want to run these demo scripts with mmdet, you can easily install mmdet as a dependency by running:
 
 ```shell
-mim install "mmdet>=3.0.0"
+mim install "mmdet>=3.1.0"
 ```
 
 ## Best Practices
@@ -89,7 +89,7 @@ pip install -v -e .
 To use mmpose as a dependency or third-party package, install it with pip:
 
 ```shell
-mim install "mmpose>=1.0.0"
+mim install "mmpose>=1.1.0"
 ```
 
 ## Verify the installation
@@ -173,7 +173,7 @@ To install MMCV with pip instead of MIM, please follow [MMCV installation guides
 For example, the following command install mmcv built for PyTorch 1.10.x and CUDA 11.3.
 
 ```shell
-pip install 'mmcv>=2.0.0' -f https://download.openmmlab.com/mmcv/dist/cu113/torch1.10/index.html
+pip install 'mmcv>=2.0.1' -f https://download.openmmlab.com/mmcv/dist/cu113/torch1.10/index.html
 ```
 
 ### Install on CPU-only platforms
@@ -192,7 +192,7 @@ thus we only need to install MMEngine, MMCV and MMPose with the following comman
 ```shell
 !pip3 install openmim
 !mim install mmengine
-!mim install "mmcv>=2.0.0"
+!mim install "mmcv>=2.0.1"
 ```
 
 **Step 2.** Install MMPose from the source.
@@ -208,7 +208,7 @@ thus we only need to install MMEngine, MMCV and MMPose with the following comman
 ```python
 import mmpose
 print(mmpose.__version__)
-# Example output: 1.0.0
+# Example output: 1.1.0
 ```
 
 ```{note}

diff --git a/docs/src/papers/datasets/animalkingdom.md b/docs/src/papers/datasets/animalkingdom.md
@@ -6,8 +6,7 @@
 <summary align="right"><a href="https://arxiv.org/abs/2204.08129">Animal Kingdom (CVPR'2022)</a></summary>
 
 ```bibtex
-@InProceedings{
-    Ng_2022_CVPR,
+@InProceedings{Ng_2022_CVPR,
     author    = {Ng, Xun Long and Ong, Kian Eng and Zheng, Qichen and Ni, Yun and Yeo, Si Yong and Liu, Jun},
     title     = {Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},

diff --git a/docs/zh_cn/dataset_zoo/2d_animal_keypoint.md b/docs/zh_cn/dataset_zoo/2d_animal_keypoint.md
@@ -490,8 +490,7 @@ mmpose
 </div>
 
 ```bibtex
-@InProceedings{
-    Ng_2022_CVPR,
+@inproceedings{Ng_2022_CVPR,
     author    = {Ng, Xun Long and Ong, Kian Eng and Zheng, Qichen and Ni, Yun and Yeo, Si Yong and Liu, Jun},
     title     = {Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},

diff --git a/docs/zh_cn/faq.md b/docs/zh_cn/faq.md
@@ -19,6 +19,7 @@ Detailed compatible MMPose and MMCV versions are shown as below. Please choose t
 
 | MMPose version |      MMCV/MMEngine version      |
 | :------------: | :-----------------------------: |
+|     1.1.0      |  mmcv>=2.0.1, mmengine>=0.8.0   |
 |     1.0.0      |  mmcv>=2.0.0, mmengine>=0.7.0   |
 |    1.0.0rc1    | mmcv>=2.0.0rc4, mmengine>=0.6.0 |
 |    1.0.0rc0    | mmcv>=2.0.0rc0, mmengine>=0.0.1 |

diff --git a/docs/zh_cn/installation.md b/docs/zh_cn/installation.md
@@ -21,7 +21,7 @@
 
 在本节中，我们将演示如何准备 PyTorch 相关的依赖环境。
 
-MMPose 适用于 Linux、Windows 和 macOS。它需要 Python 3.7+、CUDA 9.2+ 和 PyTorch 1.6+。
+MMPose 适用于 Linux、Windows 和 macOS。它需要 Python 3.7+、CUDA 9.2+ 和 PyTorch 1.8+。
 
 如果您对配置 PyTorch 环境已经很熟悉，并且已经完成了配置，可以直接进入下一节：[安装](#安装-mmpose)。否则，请依照以下步骤完成配置。
 
@@ -57,13 +57,13 @@ conda install pytorch torchvision cpuonly -c pytorch
 ```shell
 pip install -U openmim
 mim install mmengine
-mim install "mmcv>=2.0.0"
+mim install "mmcv>=2.0.1"
 ```
 
 请注意，MMPose 中的一些推理示例脚本需要使用 [MMDetection](https://github.com/open-mmlab/mmdetection) (mmdet) 检测人体。如果您想运行这些示例脚本，可以通过运行以下命令安装 mmdet:
 
 ```shell
-mim install "mmdet>=3.0.0"
+mim install "mmdet>=3.1.0"
 ```
 
 ## 最佳实践
@@ -88,7 +88,7 @@ pip install -v -e .
 如果只是希望调用 MMPose 的接口，或者在自己的项目中导入 MMPose 中的模块。直接使用 mim 安装即可。
 
 ```shell
-mim install "mmpose>=1.0.0"
+mim install "mmpose>=1.1.0"
 ```
 
 ## 验证安装
@@ -180,7 +180,7 @@ MMCV 包含 C++ 和 CUDA 扩展，因此其对 PyTorch 的依赖比较复杂。M
 举个例子，如下命令将会安装基于 PyTorch 1.10.x 和 CUDA 11.3 编译的 mmcv。
 
 ```shell
-pip install 'mmcv>=2.0.0' -f https://download.openmmlab.com/mmcv/dist/cu113/torch1.10/index.html
+pip install 'mmcv>=2.0.1' -f https://download.openmmlab.com/mmcv/dist/cu113/torch1.10/index.html
 ```
 
 ### 在 CPU 环境中安装
@@ -198,7 +198,7 @@ MMPose 可以仅在 CPU 环境中安装，在 CPU 模式下，您可以完成训
 ```shell
 !pip3 install openmim
 !mim install mmengine
-!mim install "mmcv>=2.0.0"
+!mim install "mmcv>=2.0.1"
 ```
 
 **第 2 步** 从源码安装 mmpose
@@ -214,7 +214,7 @@ MMPose 可以仅在 CPU 环境中安装，在 CPU 模式下，您可以完成训
 ```python
 import mmpose
 print(mmpose.__version__)
-# 预期输出： 1.0.0
+# 预期输出： 1.1.0
 ```
 
 ```{note}