I am working on pose estimation for hands and face using OpenPose (https://github.com/CMU-Perceptual-Computing-Lab/openpose) on Google Colab.
I have hundred videos in my dataset, right now I am able to run OpenPose on each video individually.
Is there a way to process all hundred videos simultaneously to extract the coordinates using subprocess.call?.
subprocess.call fails to execute on a Colab GPU (cell runs fine but no output generated)
Can anyone suggest similar pose estimation tools with comparable performance and option to batch process multiple videos?
Please do let me know, thanks.
