Anybody try the paf or other grouping method in this work ?

HRNet / HigherHRNet-Human-Pose-Estimation

This is an official implementation of our CVPR 2020 paper "HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation" (https://arxiv.org/abs/1908.10357)

MIT License

1.35k stars 272 forks source link

Anybody try the paf or other grouping method in this work ? #14

Open frankite opened 4 years ago

tensorboy commented 4 years ago

@frankite I tried CenterNet at here: https://github.com/tensorboy/centerpose

H19012 commented 4 years ago

@frankite I tried CenterNet at here: https://github.com/tensorboy/centerpose

Can you tell me how to edit the joint connections for HRNET? Say, if I'd wanted to train using a different style of skeleton?