lightly-ai / lightly-ai/lightly
Add multi-modal loss
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.8k
- Forks
- 367
- Avg merge
- 3d 22h
- Merged PRs (30d)
- 5
Description
# Add multi-modal loss
As discussed in #249, adding the loss function as described in [CLIP](https://arxiv.org/pdf/2103.00020.pdf) would enable users to work with multi-modal datasets.
The pseudo-code (from the paper) is:
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 with the discussion in issue #249 and the linked CLIP paper, since no implementation file, test, or entry point is identified here. Define the loss behavior for multi-modal datasets from the paper's pseudocode, then verify that the resulting implementation supports the intended user workflow.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100