Giters

HRNet / HRNet-Human-Pose-Estimation

This repo is copied from https://github.com/leoxiaobin/deep-high-resolution-net.pytorch

Home Page:https://github.com/leoxiaobin/deep-high-resolution-net.pytorch

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Cannot reproduce the results for COCO HRNet_w32

asanakoy opened this issue · comments

commented

Thanks for the amazing work and the source code!

I'm trying to train HRNet_w32 on COCO dataset.
But currently I cannot reproduce the results reported in the paper. I barely get AP=12.0 when using the config w32_256x192_adam_lr1e-3.yaml and training on 4 GPUs.

Are the provide hyperparameters correct? Any tips what could go wrong?
Have anybody successfully reproduced the results?

Best,
Artsiom

commented

OK. Looks like I have found the problem.

If you reimplement the training loop yourself, make sure so set weight_decay=0. In the codebase it is just confusing that WD param from the config is used only with SGD, and for Adam the weigh_decay is hardcoded to 0.0 (the default value).