microsoft / microsoft/foldingdiff
Where is wrapped gaussian sampling done during noising?
Open
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 568
- Forks
- 74
- Avg merge
- 20h 2m
- Merged PRs (30d)
- 1
Description
The only code where I see a loop over k is in ScoreMatchingNoisedAnglesDataset class.
I am not sure that I was able to find the use of the wrapped gaussian during generation of the noised samples. Can you point me to the relevant code where this is being done?
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 ScoreMatchingNoisedAnglesDataset class and its loop over k, then search the noising and generation entry points for wrapped Gaussian sampling. Done means identifying the relevant code path and documenting where the wrapped Gaussian is used.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 1/5
- Estimated time
- Under an hour
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100