You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In this file, we list the algorithms with other licenses instead of Apache 2.0. Users should be careful about adopting these algorithms in any commercial matters.
-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:
106
+
-Support for four new algorithms:
108
107
109
-
- Provide an easy and agile way to integrate algorithms, features and applications into MMPose
110
-
- Allow flexible code structure and style; only need a short code review process
111
-
- Build individual projects with full power of MMPose but not bound up with heavy frameworks
- Released the first whole-body pose estimation model, RTMW, with accuracy exceeding 70 AP on COCO-Wholebody. For details, refer to [RTMPose](/projects/rtmpose/). [Try it now!](https://openxlab.org.cn/apps/detail/mmpose/RTMPose)
- Welcome to use the [*MMPose project*](/projects/README.md). Here, you can discover the latest features and algorithms in MMPose and quickly share your ideas and code implementations with the community. Adding new features to MMPose has become smoother:
118
+
119
+
- Provides a simple and fast way to add new algorithms, features, and applications to MMPose.
120
+
- More flexible code structure and style, fewer restrictions, and a shorter code review process.
121
+
- Utilize the powerful capabilities of MMPose in the form of independent projects without being constrained by the code framework.
122
+
- Newly added projects include:
113
123
-[RTMPose](/projects/rtmpose/)
114
124
-[YOLOX-Pose](/projects/yolox_pose/)
115
125
-[MMPose4AIGC](/projects/mmpose4aigc/)
116
126
-[Simple Keypoints](/projects/skps/)
117
-
- Become a contributors and make MMPose greater. Start your journey from the [example project](/projects/example_project/)
127
+
-[Just Dance](/projects/just_dance/)
128
+
-[Uniformer](/projects/uniformer/)
129
+
- Start your journey as an MMPose contributor with a simple [example project](/projects/example_project/), and let's build a better MMPose together!
118
130
119
131
<br/>
120
132
121
-
- 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:
133
+
-October 12, 2023: MMPose [v1.2.0](https://github.com/open-mmlab/mmpose/releases/tag/v1.2.0)has been officially released, with major updates including:
122
134
123
-
- Support new datasets: Human-Art, Animal Kingdom and LaPa.
124
-
- Support new config type that is more user-friendly and flexible.
125
-
-Improve RTMPose with better performance.
126
-
-Migrate 3D pose estimation models on h36m.
127
-
-Inference speedup and webcam inference with all demo scripts.
135
+
- Support for new datasets: UBody, 300W-LP.
136
+
- Support for new algorithms: MotionBERT, DWPose, EDPose, Uniformer.
137
+
-Migration of Associate Embedding, InterNet, YOLOX-Pose algorithms.
138
+
-Migration of the DeepFashion2 dataset.
139
+
-Support for Badcase visualization analysis, multi-dataset evaluation, and keypoint visibility prediction features.
128
140
129
-
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!
141
+
Please check the complete [release notes](https://github.com/open-mmlab/mmpose/releases/tag/v1.2.0) for more details on the updates brought by MMPose v1.2.0!
130
142
131
143
## 0.x / 1.x Migration
132
144
133
-
MMPose v1.0.0 is a major update, including many API and config file changes. Currently, a part of the algorithms have been migrated to v1.0.0, and the remaining algorithms will be completed in subsequent versions. We will show the migration progress in the following list.
| Associative Embedding (NIPS 2017) | in progress |
161
-
| VoxelPose (ECCV 2020) ||
162
-
| RSN (ECCV 2020) | done |
163
-
| CID (CVPR 2022) | done |
164
-
| CPM (CVPR 2016) | done |
165
-
| HRNet (CVPR 2019) | done |
166
-
| HRNetv2 (TPAMI 2019) | done |
167
-
| SCNet (CVPR 2020) | done |
168
-
169
-
</details>
145
+
MMPose v1.0.0 is a major update, including many API and config file changes. Currently, a part of the algorithms have been migrated to v1.0.0, and the remaining algorithms will be completed in subsequent versions. We will show the migration progress in this [Roadmap](https://github.com/open-mmlab/mmpose/issues/2258).
170
146
171
147
If your algorithm has not been migrated, you can continue to use the [0.x branch](https://github.com/open-mmlab/mmpose/tree/0.x) and [old documentation](https://mmpose.readthedocs.io/en/0.x/).
172
148
@@ -186,6 +162,9 @@ We provided a series of tutorials about the basic usage of MMPose for new users:
0 commit comments