something wrong with your endcoder?
PaTricksStar opened this issue · comments
PaTricksStar commented
noise2noise-pytorch/src/unet.py
Line 82 in 7942c06
I think enconv(i), i=2,...,5 should be defined separatedly or they will share the same weights.
Devin Yang commented
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.