pykao / BraTS2018-tumor-segmentation

We provide DeepMedic and 3D UNet in pytorch for brain tumore segmentation. We also integrate location information with DeepMedic and 3D UNet by adding additional brain parcellation with original MR images.

https://www.researchgate.net/publication/326549702_Brain_Tumor_Segmentation_and_Tractographic_Feature_Extraction_from_Structural_MR_Images_for_Overall_Survival_Prediction?_sg=Omb1yK0vXPLUJ0Xx70tsfv1nTplmWLNvrZExSDIVnyVDNm3CLLGwEgUB7qjJ-MrwC6VqUvoNt-kPdQ.2

Problem in UNet Architecture

thanhhau097 opened this issue 5 years ago · comments

Thanh Hau Nguyen commented 5 years ago

I found a variable y wasn't used in this line: https://github.com/pykao/BraTS2018-tumor-segmentation/blob/master/models/unet.py#L43
Could you consider this case?

Antoine Yang commented 4 years ago

Shouldn't it be y = self.bn3(self.conv3(y)) at line 46 ?