Detectron.pytorch
Detectron.pytorch copied to clipboard
Why freeze all bn (affine) layers?
https://github.com/roytseng-tw/Detectron.pytorch/blob/8315af319cd29b8884a7c0382c4700a96bf35bbc/lib/modeling/ResNet.py#L76
def _init_modules(self):
# Freeze all bn (affine) layers !!!
self.apply(lambda m: freeze_params(m) if isinstance(m, mynn.AffineChannel2d) else None)