how to inferencce on video？

hellojialee / Improved-Body-Parts

Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation

https://arxiv.org/abs/1911.10529

258 stars 42 forks source link

how to inferencce on video？ #14

Closed FRunyang closed 4 years ago

FRunyang commented 4 years ago

hello，I want to inference my videos， what should i do？

FRunyang commented 4 years ago

Oh， I do。我做好了，我发现有的帧腿就没了

FRunyang commented 4 years ago

hellojialee commented 4 years ago

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

stale[bot] commented 4 years ago

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.