wk

You can use torchsummary check whether your input shape is valid with net architecture.

Yes, the data on the official website is no longer valid. If you need, you can contact me by email.

You can contact me by email.

Maybe you can reference to model.py/get_model function.  The number of categories we use in the model definition is the actual number of categories plus one (including undefined data). Actually,...

So the confusion matrix contains a row of all zero vectors (actually the target does not contain undefined categories), and the prediction contains the actual number of categories +1.

In my opinion,at main.py line 170 N_CLASSES = len(LABEL_VALUES) which include the undefined label . at model.py line 33 n_classes = kwargs['n_classes'] so our model try to learn actual classes+...

This project is designed to construct a common framework, so it is designed to be compatible with the requirements of full supervision and semi-supervised learning, so it is not as...

Sorry, it took so long to reply. I will verify the current code and fix the problem as soon as possible.

display the ground truth label of the data to see if the labelmiss area has reached the edge?

In my opinion,at main.py line 170 `N_CLASSES = len(LABEL_VALUES)` which include the undefined label . at model.py line 33 `n_classes = kwargs['n_classes']` so our model try to learn actual classes+...