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

don't want to group (including training) #108

Open mywordwin opened 1 year ago

mywordwin commented 1 year ago

Hello, how to modify if you don't want to group (including training), but only need joint detection? Is it to change all the with_ae_loss in the configuration file to false? or how? Please advise, I wish a happy life!