search

Gengzigang / PCT

This is an official implementation of our CVPR 2023 paper "Human Pose as Compositional Tokens" (https://arxiv.org/pdf/2303.11638.pdf)
MIT License
311 stars 20 forks source link

score of each keypoint is same #22

Open HappyFaceFriend opened 11 months ago

HappyFaceFriend commented 11 months ago

Hi, thanks for opening such a great project.

I ran multiple inferences using your pretrained swin_large model, and the scores of each keypoint are same, even if it doesn't seem right.

How can I fix this so that I can seek out keypoints that are not in the image?