Jose Dolz

Hi, @antdelmas is right with the tree folders. In each image-type folder you should add all the images belonging to that modality. For example, if you have 10 training patients,...

Hi, to adapt to 2 modalities you need to modify the code of the IVD_Net_asym, which is quite easy. Basically you have to change the torch.cat operations from 4 to...

Hi, it is a long time since last time I used this code, but I recall that this comes from the fact that there are 0 samples to process (typically...

Hi, can you be more precise so that I can understand better the error? Did you just clone the repository and run the code? Or did you modify something? Which...

Hi, Can you try in another machine? We have tried to reproduce the error in different machines and environments and it doesn’t appear. Jose

Hi, for the last error we have seen it in several computers. The workaround for it is to run the code with some Theano flags, like this: ``` THEANO_FLAGS='floatX=float32' python...

Hi @QingchenF Can you reformulate your questions please? I do not get your points.

Hi @QingchenF The data I put in the repository is just to be sure that the network can run. The only thing you have to do is to change the...

Hi @franciscoferreira34 Sorry for my late answer, I have been quite busy. I didn't pre-process that data directly, but I know that a student from the lab employed FreeSurfer for...

Hi @franciscoferreira34 Maybe you can optimize the sampling process. Currently, at each sub-epoch all the volumes are loaded and sampled for that specific epoch. You could either load all the...