Interpretation object errorand Category wise accuracy for Multil-label classification

[jayrodge]

1. I have trained a Multi-label Image classifier on Google Colab. But when I try to use the ClassificationInterpretation object I’m getting error.

For pIot_top_losses() I get this error:

For plot_confusion_matrix, I get this error:

Here’s my definition for data bunch:

I also tried this solution but while training it throws an error : Error (pytorch?): Expected object of scalar type Long but got scalar type Float for argument #2 'other

2. How to get category wise accuracy for the multi-label classification?

Let me know if you need any other information.
Thanks in advance!