f-dangel / f-dangel/backpack

Extending BCEWithLogitsLoss to non-scalar outputs (multi label)

Open
#345 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
617
Forks
57
PR merge metrics
No merged PRs in 30d

Description

Hi,

currently BCEWithLogitsLoss supports only binary classification:
https://github.com/f-dangel/backpack/blob/8aad99d50ce9d6cb8b4924535f262a99eab22cad/backpack/core/derivatives/bcewithlogitsloss.py#L78

I have the VQAv2 taks, which is multi label, but also has soft labels i.e. multiple correct labels. Thus, I think currently it does not work with this library, because of:
- https://github.com/f-dangel/backpack/issues/281
- And because only scalar outputs are supported

What would be necessary to support my setup here?

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.