Yining Li

Thanks for using mmpose. Could you please share the full configs used in the experiment? And could you please check if the bounding boxes obtained by either Label Studio or...

@wusize Could you please help?

1. MMPose v0.x (latest version is v0.29.0) and v1.x (latest version is v1.0.0rc1) are maintained in parallel now and the next year. New features will be supported in v1.x first....

Please refer to sections 1.2 and 1.3 of https://cocodataset.org/#keypoints-eval about the description of $\sigma$. Actually, I would suggest leaving the sigmas along and using other metrics. To change the input...

Sigmas indicate the difference among multiple annotations (from different subjects) of the same keypoint. So you need to collect multiple annotations for each object in your dataset to calculate sigmas.

You can use MMPose as a 3rd-party dependency of your projects and directly use MMPose's inference API. Or you can export MMPose models to onnx and use onnx-runtime for inference...

Thanks for using MMPose. Please note that `pytorch2onnx.py` is deprecated in MMPose and will be removed from 1.x. The model export and deployment are supported by [MMDepoly](https://github.com/open-mmlab/mmdeploy). Please refer to...

Yes, MMPose 1.0 introduced major refactoring and unavoidable breaking changes. We have prepared a document to introduce the design of MMPose 1.0 and how to migrate from the old version....

Hi, thanks for using MMPose v1.x. We are still working on refactoring the 3d part and it will be added to 1.x next month.

It seems that MMCV is not properly installed. Please uninstall MMCV and reinstall it following the documentation. We suggest installing MMPose 1.0 and its dependencies in a clean environment (without...