Recognition demo

[lamezkua]

trafficstars

@yysijie Hi, Are there any news about the recognition demo? Thanks!

@Ai-is-light, @Hunkzer Hi, the old ST-GCN demo requires some heavy dependencies such as Openpose and Caffe. MMSkeleton has included other powerful pose estimators (e.g. HR-NET). Thus, we will release a light demo soon to replace the old one. Thank you for your interest in our works.

Originally posted by @yysijie in https://github.com/open-mmlab/mmskeleton/issues/237#issuecomment-541088935

[zjr666]

I want to ask the same question

[wwdok]

me too, i would like to see the demo that this model take video or webcam as input, and output action recognition result, that will make me have a better intuitive sense.

[MaarufB]

I also would like to see the demo for reognition.