GengDavid/pytorch-cpn

About the structure of refineNet

hellojialee opened this issue · 0 comments

hellojialee commented

pytorch-cpn/networks/refineNet.py

Line 65 in 48696a9

def _predict(self, input_channel, num_class):

Why the final layer appends a BN layer? Why the output is normalized?
Could you give me a hint? Thank you!