taigw

@PoonamZ Is that because you didn't provide arguments when running train.py? You should provide a configure file as the argument, for example: python train.py config17/train_wt_ax.txt

@PoonamZ Have you checked out the latest code? in util/data_loader.py, line 121 should be: label, _ = self.__load_one_volume(self.patient_names[i], self.label_postfix)

@PoonamZ @WesSurento1 Have you solved the problem? I guess the path of training images was not set correctly.

Hi, I'm not sure about what problems you have faced. Can you provide more information?

@1160914483 , these are hyperparameters. I tried different configurations and found the optimal values.

Hi, the data_shape in the configure file is the size of randomly cropped patch.

Hi, During training time, I randomly selected N volumes from the training set, and then randomly cropped one patch from each volume. During testing time, the patch size is larger...

Hi, the reason for that is just to make the testing shape adapted to the testing image, so that the testing can be faster. For example, if the testing image...

The pre-trained models released here are not exactly the ones I used in the paper. To release the repository, I re-organized the code to make it clearer to understand, then...

The code was based on Tensorflow 1.4. It should be updated to support the latest version.