LAION-AI / LAION-AI/temporal-embedding-aggregation
remove mean embedding of dataset as preprocessing
Open
Nobody has claimed this yet.
research
- Dominant language
- Python
- Stars
- 32
- Forks
- 4
- PR merge metrics
- No merged PRs in 30d
Description
maybe this will slightly help overfitting to stock video distribution
need to find a way to efficiently take zero_masks in training and eval since the way I tried is super slow
Contributor guide
No contributing guide indexed for this repository
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
No files or tests are named. Start by locating the training and evaluation paths that handle dataset mean embeddings and zero_masks, then compare their current preprocessing behavior. Done means removing the dataset mean embedding and providing an efficient zero_masks path in both training and evaluation without the current slowdown.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Refactor
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100