CurricularFace icon indicating copy to clipboard operation
CurricularFace copied to clipboard

Published 20 hours ago • verified publisher icon HuangYG123

batch_norm parameters issue

Open konioyxgq opened this issue 4 years ago • 2 comments

On line 104 of train.py, you write "separate batch_norm parameters from others; do not do weight decay for batch_norm parameters to improve the generalizability"https://github.com/HuangYG123/CurricularFace/blob/8b2f47318117995aa05490c05b455b113489917e/train.py#L104 Is this the conclusion you got from the experiment? Or is the conclusion of a certain paper? Can you explain the reason for this?

konioyxgq avatar Jun 11 '20 07:06 konioyxgq

We follow this setting as https://github.com/ZhaoJ9014/face.evoLVe.PyTorch.

HuangYG123 avatar Jun 11 '20 08:06 HuangYG123

Okay thank you. What do you think is the reason for this?

konioyxgq avatar Jun 11 '20 08:06 konioyxgq