NVlabs/DeepInversion

feature_statistics not used

cyang-cityu opened this issue · 1 comments

Why you define a list feature_statistics in imagenet_inversion.py but never use it in the code?

Great observation! In the beginning, we implemented the r_feature loss via feature_statistics list and were outputting mean and variance of channels via the forward function. Later we found that it can be implemented more efficiently with forward hooks but forgot to remove feature_statistics.