Help for data or data format

[ALEXdwt]

Thanks for your work!

A dataset by myself was used to test your code, but it comes:
Traceback (most recent call last):
File "E:\dwt\BrainExtract\PythonUnet\Unet-Segmentation-Pytorch-Nest-of-Unets-master\pytorch_run.py", line 251, in
for x, y in train_loader:
File "F:\pythontool\lib\site-packages\torch\utils\data\dataloader.py", line 628, in next
data = self._next_data()
File "F:\pythontool\lib\site-packages\torch\utils\data\dataloader.py", line 671, in _next_data
data = self.dataset_fetcher.fetch(index) # may raise StopIteration
File "F:\pythontool\lib\site-packages\torch\utils\data_utils\fetch.py", line 58, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "F:\pythontool\lib\site-packages\torch\utils\data_utils\fetch.py", line 58, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "E:\dwt\BrainExtract\PythonUnet\Unet-Segmentation-Pytorch-Nest-of-Unets-master\Data_Loader.py", line 104, in getitem
img = self.tx(i1)
File "F:\pythontool\lib\site-packages\torchvision\transforms\transforms.py", line 95, in call
img = t(img)
File "F:\pythontool\lib\site-packages\torch\nn\modules\module.py", line 1190, in call_impl
return forward_call(*input, **kwargs)
File "F:\pythontool\lib\site-packages\torchvision\transforms\transforms.py", line 270, in forward
return F.normalize(tensor, self.mean, self.std, self.inplace)
File "F:\pythontool\lib\site-packages\torchvision\transforms\functional.py", line 360, in normalize
return F_t.normalize(tensor, mean=mean, std=std, inplace=inplace)
File "F:\pythontool\lib\site-packages\torchvision\transforms\functional_tensor.py", line 940, in normalize
return tensor.sub(mean).div(std)
RuntimeError: output with shape [1, 96, 96] doesn't match the broadcast shape [3, 96, 96]

I cut the 3D MRI data into 2D images (size 256*256), and save them as png format, then put some of the pngs into the data folder separately, is there any problem?

[bigmb]

Input to the model in pytorch run is of shape 3 and not 1.
So you can either change the shape of the model input in pytorch_run or make your image into 3 channel.