Sampling of Training Dataset via WeightedRandomSampler for Imbalanced Classes

[mosala777]

Hello, I wanted to ask if it is possible to use weighted random sampling for cases of imbalanced datasets? I tried replacing the sampling methods but the tensor dataset for training_dataset is not matching correctly and gives the error: "IndexError: too many indices for tensor of dimension 2."

I think I am missing something in the script. Would appreciate if you could help.

Thank you!