Closed FRunyang closed 4 years ago
Oh, I do。我做好了,我发现有的帧腿就没了
The image sample you tested above seems easy, what scale configurations did you use? For single scale inference, 768 length is better than 512: https://github.com/jialee93/Improved-Body-Parts/blob/316e71fa93e1dc444b1cfd4fc312c21c13bfe93f/utils/config#L36
And lower threshold thre1=thre2=0.08 is better for more keypoint detection if the background is not very complexed: https://github.com/jialee93/Improved-Body-Parts/blob/316e71fa93e1dc444b1cfd4fc312c21c13bfe93f/utils/config#L16
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
hello,I want to inference my videos, what should i do?