Vegetebird / MHFormer

[CVPR 2022] MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
MIT License
530 stars 85 forks source link

About demo/vis.py hrnet output foramt #118

Open hellos0032 opened 1 month ago

hellos0032 commented 1 month ago

Thank you for your great work!

In the demo/vis.py codes, there is a hrnet_pose function. As I know, HRNet is trained with COCO data, and the output format is COCO style. However the output of the HRNet's format in your code is H36m style. How did you make this ?

Thank you