search

LeeJunHyun / Image_Segmentation

Pytorch implementation of U-Net, R2U-Net, Attention U-Net, and Attention R2U-Net.
2.66k stars 594 forks source link

edge pixel weight map #75

Closed helenxxz closed 1 year ago

helenxxz commented 3 years ago

hey, everyone! How do you implement the edge pixel weighting in the code? I only see this: self.criterion = torch.nn.BCELoss() loss = self.criterion(SR_flat,GT_flat) Hope to get your answers, thank you!