pytorch / pytorch/vision

New Feature: Dice Loss

Open
#6,435 8 comments 2 reactions 1 assignee View on GitHub

@oke-aditya is already working on this.

Since Aug 17, 2022.

  • #6960 by @pri1311 — open
module: ops new feature
Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

🚀 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.

https://github.com/pytorch/pytorch/issues/1249#issuecomment-305088398

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

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.