LAION-AI / LAION-AI/CLAP

a little bug about loss

Open
#115 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2.3k
Forks
213
PR merge metrics
No merged PRs in 30d

Description

At CLAP loss: logits_per_text = logit_scale_a * text_features @ audio_features.T
I think logit_scale_a should be logit_scale_t??

https://github.com/LAION-AI/CLAP/blob/776b7dc95f2dc71775e9dc9804876e23265285b7/src/laion_clap/clap_module/loss.py#L194C1-L195C1

Thanks a lot and Great work!!

Contributor guide

No contributing guide indexed for this repository

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.

Research direction

Start in src/laion_clap/clap_module/loss.py at the linked lines around the CLAP loss calculation. Trace how logit_scale_a and logit_scale_t are defined and used, then determine which scale belongs in logits_per_text. Done means confirming the intended behavior and adding the corresponding regression coverage.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.