Evann Courdier

I got the same curves - Did you find an explanation ? May the pytorch version make a difference ?

@lightas I contacted the owner and he said that he froze batch norm during training. Be careful however that the --freeze-bn parameter **doesn't work** currently in the code ! Since...

@lightas The freeze-bn parameter puts BatchNorn into eval mode at model initialization. But then in the training you do model.train(), which sets the BatchNorm back to training mode...

Up! I would need this feature too.