How to fine-tune for multi-label classification tasks

[Bentonmaster]

Thank you for your outstanding work
I would like to know whether your fine-tuning framework supports training and fine-tuning for multi-label image classification tasks.
If possible, could you provide an example of constructing a dataset?

[2U1]

The code is not for multi-label so you need to tweak a bit in the cls_dataset.py.