In your code, you don't use all fraems but set fps to the one of your original
video.
fps = int(cap.get(cv2.CAP_PROP_FPS))
result = cv2.VideoWriter(folder_result + 'demo_' + video_fname,
fourcc, fps, size)
So the output video becomes shorter, I think.
You should use all frames in your original video.
This line is not needed.
`cap.set(cv2.CAP_PROP_POS_FRAMES, round(fps * sec))`
---
[Visit
Topic](https://discuss.mxnet.apache.org/t/how-to-run-pose-estimation-alphapose-with-video-instead-of-cam/6645/6)
or reply to this email to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.mxnet.apache.org/email/unsubscribe/eff8cbc087e05a9bbcdea47180b16fe3fd3dadc9364ad75c0d7b879092154952).
