bugs here
Closed this issue · 3 comments
pytorch-pose/pose/utils/transforms.py
Line 18 in b8dc3b3
It seems a bug in color_normalization
t.sub_(m).div_(s)
Hi @bertjiazheng . It seems that original hourglass network didn't subtract mean.
I follow the implementation of convolutional pose machine to subtract mean only: https://github.com/shihenw/convolutional-pose-machines-release/blob/afda94fe0d53eb77c5fe948e607f199791f4073c/testing/src/applyModel.m#L94
You may also try to divide the std and see whether it helps improve the performance. Feedbacks are always welcome!
Hi @bearpaw, why don't you use original hourglass network that didn't subtract mean? I also see your hg-8
training log and find your accuracy increase more slowly than original paper. Does this result from nomalization i.e.image subtracting mean?
@wangziren1 Please try so if you are interested and give us a feedback. Thanks very much!