🚀 The feature

Followup to #6323

Addition of Dice Loss to torchvision.

Motivation, pitch

Mainly Dice loss is used for semantic segmentation.

I want to understand the technical aspects of adding it to torchvision. Are we going to support boolean tensors or outputs from the semantic segmentation models?

Few references.

pytorch/pytorch#1249 (comment)

https://github.com/rogertrullo/pytorch/blob/rogertrullo-dice_loss/torch/nn/functional.py#L708

MONOAI

https://docs.monai.io/en/stable/_modules/monai/losses/dice.html#DiceLoss

https://kornia.readthedocs.io/en/latest/_modules/kornia/losses/dice.html#dice_loss

Alternatives

No response

Additional context

No response