LAION-AI / LAION-AI/CLIP_benchmark
Make a training companion eval script
Open
Nobody has claimed this yet.
important
UX
- Dominant language
- Python
- Stars
- 814
- Forks
- 103
- PR merge metrics
- No merged PRs in 30d
Description
It would automatically evaluate on all datasets each checkpoint during training of an openclip training and report results to wandb.
I'm doing it
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 tracing the OpenCLIP training flow around checkpoint creation and the dataset evaluation process. Determine how evaluations should run during training and how results should be reported to Weights & Biases; done means every checkpoint is evaluated across all datasets and the results appear in wandb.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100