I've been using NiftyNet and it has been working before, but recently I've encountered this problem with it not recognizing the T1 or T2 images I think? There is a valueerror raised because the filename list column passed to [T1] is empty, but from the picture you can see that it recognizes 16 subjects, it used to be 8
I have also included an image of what it was before. The difference is that now I broke my image into 1 label per label file as opposed to the 10 labels per label file it had before: when it worked
the only changes I made in the config file were 1) I changed the segmentation num_classes value from 11 to 2, and 2) I changed where the path_to_search in my T1, T2, and Label sections to where I put the edited images
Check again the path of T1. This error is often raised when there are no files on that path. Also be sure that the names are correct. They should be the same as before. If you changed the name you should also change them in the datasplit file. Also make sure that the filename of input image and its ground truth are matching.
These are some of the first things that you should check.