neuropoly / neuropoly/SmaugLab
New Augmentations
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 8
- Forks
- 0
- Avg merge
- 5d 2h
- Merged PRs (30d)
- 11
Description
Piece by piece add new augmentations, verifying each time that they actually give benefits:
- Different noise augmentations (salt and pepper, snow, ...)
- Better Random Convolution augmentation (apply multiple times with same kernel, ...)
- Artifact transforms (spike, ghosting, ...)
- https://github.com/KaiyangZhou/mixstyle-release
- https://openreview.net/pdf?id=LB5F02kwAv
- TBD
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
The issue does not name implementation files, tests, or entry points. Start by locating the repository's augmentation code and evaluation workflow, then choose and scope one checklist item, including the MRI training comparison needed to verify that it provides a benefit.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100