LAION-AI / LAION-AI/CLIP_benchmark
Variation in the benchmark
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 814
- Forks
- 103
- PR merge metrics
- No merged PRs in 30d
Description
Seems there is some variation in the numbers of few datasets/models after re-running the benchmark, might be due to AMP. It happens on few datasets on zero-shot classification, diabetic retinopathy being the worse. Retrieval is fine.
See #56, where it was first detected.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by rerunning the benchmark described in the issue, comparing zero-shot classification—especially diabetic retinopathy—across the affected datasets and models; retrieval is reported as stable. Investigate whether AMP accounts for the variation, and consider the issue resolved when repeated runs produce consistent results or the source of the variation is identified.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, testing-qa
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100