search

jianpengz / ConResNet

[IEEE-TMI2020] Inter-slice Context Residual Learning for 3D Medical Image Segmentation
GNU General Public License v3.0
50 stars 16 forks source link

BCELossBoud should add a softmax layer! #7

Open Yanfeng-Zhou opened 2 years ago

Yanfeng-Zhou commented 2 years ago

In your code ConResNet/utils/loss.py

class BCELossBoud(nn.Module):
    ...
   def forward(self, predict, target):
         predict = torch.softmax(predict, 1)

in forward section, I think we should add predict = torch.softmax(predict, 1)