Yining Li

Hi, would you like to raise an issue in MMDeploy to seek more professional suggestions?

Yes, you can remove the node for animal pose estimation to speed up the pipeline. Specifically, you can remove these [lines](https://github.com/open-mmlab/mmpose/blob/master/demo/webcam_cfg/pose_estimation.py#L46-L55), and change the input buffer of the downstream `ObjectAssignerNode`...

Hi, thanks for using mmpose. We would recommend installing mmpose following the documents: https://mmpose.readthedocs.io/en/latest/install.html#installation In short, it is commended to install mmpose via pip if you plan to use it...

In MMActoin2 we provided a demo to use MMDetection, MMPose, and MMAction2 to perform human detection, pose estimation, and skeleton-based action recognition. The documentation can be found [here](https://mmaction2.readthedocs.io/en/1.x/user_guides/3_inference.html#inference-with-skeleton-based-action-recognition-models).

Hi, sorry for the late reply. There are updates in mmpose-1.x as well as upstream codebases like mmcv and mmengine in the past months. So would you like to install...

Hi, sorry for the late reply. Could you please provide the MMPose version and the config file?

@Ben-Louis Could you please have a look at this issue?

Hi, in a typical top-down pose estimation algorithm, human or object bounding boxes are first obtained from the input or by a detector, and the image area within the bbox...

Thank you very much for your contribution. This PR will be reviewed asap.

@17862923747 Hi, thank you very much for your help! Could you please sign the CLA so we can accept your contribution? This PR will be reviewed asap.