search

LeeJunHyun / Image_Segmentation

Pytorch implementation of U-Net, R2U-Net, Attention U-Net, and Attention R2U-Net.
2.68k stars 595 forks source link

Is it a bug in RRCNN #1

Closed qinhui99 closed 5 years ago

qinhui99 commented 6 years ago

I check this function and see the x has been changed by x = self.Conv_1x1(x). So "return x+x1" maybe a bug.
def forward(self,x): x = self.Conv_1x1(x) x1 = self.RCNN(x) return x+x1

LeeJunHyun commented 5 years ago

Dear @qinhui99 , I apologize for late response. self.Conv_1x1 layer was added to fit the channel depth of x. you can remove self.Conv_1x1 if the channel depth of x is same with the channel depth of x1

LeeJunHyun commented 5 years ago

If you have no further questions, I will close the issue. I hope my answer was helpful.