Modification of focal loss for it to works with mix-up augmentation?

[rtxbae]

I'm trying to train on relatively small datasets, mix-up is one way to reduce it from overfitting, but it seems like focal loss is not designed to works with label with probabilities. It seems that this line https://github.com/xlliu7/TadTR/blob/3af0abcb17a20210ddd04d2c7e212a024ea0fedc/models/tadtr.py#L274 specifically designed for binary classification.

Do you have any idea how to modify focal loss for label with probabilities?