Haohao Xu

I have the same question!

Thanks, I know exactly what the problem is too. Pytorch nn.CrossEntropyLoss() requires input dimension is (N,C,H,W), target dimension is (N,H,W). So the mask must be pre-processed as a single channel....

@chuhuan88 The supervision version is too low. I tried updating to the latest version to solve the problem. pip uninstall supervision pip install supervision