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

what about model's inference #7

Closed gmk11 closed 1 year ago

gmk11 commented 1 year ago

@Gengzigang how did you do the model's inferecence for a single image ? is there a file that miss in your repository? i checked the one of mmpose but it doesn't worked for me , can you share your working environment for the inference?

Gengzigang commented 1 year ago

You can try: https://github.com/Gengzigang/PCT#demo.

gmk11 commented 1 year ago

thanks it worked for me but you have to correct something in demo_img_with_mmdet.py line 137: you wrote wrong the parameter bbox_inches you put bbox_inckes

it's plt.savefig(out_file + '.pdf', format='pdf', bbox_inches='tight', dpi=100), rather than plt.savefig(out_file + '.pdf', format='pdf', bbox_inckes='tight', dpi=100)

Gengzigang commented 1 year ago

Thanks, I have fixed it.