In this dataset, masks for classes may overlap. By default fastai wants to see one class per pixel, in one channel. This is likely causing your probem. You’ll need to alter fastai to handle one channel per class. By kaggle rules, any such code discussion and examples should be discussed on kaggle forums. But if you want to talk in generic terms without reference to a challenge, this thread is tackling the same problem 
Create databunch with multiple segmentation mask as label
3 Likes