LeeJunHyun / Image_Segmentation

Pytorch implementation of U-Net, R2U-Net, Attention U-Net, and Attention R2U-Net.
2.75k stars 602 forks source link

A question in solver.py file #62

Closed jiudawn closed 1 year ago

jiudawn commented 4 years ago

For training process, line 148 SR = self.unet(images), SR_probs = F.sigmoid(SR), why just use SR_probs for loss computing. But for ACC, F1 etc. metrics just use SR. But for evaluating process, line 209 SR = F.sigmoid(self.unet(images)), just directly use SR_probs for computing. Is there something wrong?