adamatch icon indicating copy to clipboard operation
adamatch copied to clipboard

About Batch Normalization Statistics When using Domain Adaptation Setting

Open jiangzhengkai opened this issue 2 years ago • 1 comments

Hi, thanks for your wonderful work. From the paper, the batch normalization statistics updates for combined source and target images, and keep fixed when computing source images for the second time. However, from https://github.com/google-research/adamatch/blob/main/domain_adaptation/adamatch.py#L63 and L67, the model keeps training states. I am not familiar with Jax. Would you mind giving some explanations?

jiangzhengkai avatar Jul 21 '21 11:07 jiangzhengkai

Good point. @jiangzhengkai I am also confused with the same. Did you figured it out?

shreejalt avatar Jan 29 '22 07:01 shreejalt