joeylitalien / noise2noise-pytorch

PyTorch Implementation of Noise2Noise (Lehtinen et al., 2018)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

something wrong with your endcoder?

PaTricksStar opened this issue · comments

pool2 = self._block2(pool1)

I think enconv(i), i=2,...,5 should be defined separatedly or they will share the same weights.

Same issue and this All convolutions use padding mode “same”, and except for the last layer are followed by leaky ReLU in original paper should mean only last conv use ReLU I think.