[FR] LayerRotation indicator
Open
Nobody has claimed this yet.
enhancement
help wanted
- Dominant language
- Python
- Stars
- 4.8k
- Forks
- 726
- Avg merge
- 5d 21h
- Merged PRs (30d)
- 5
Description
Following "Layer rotation: a surprisingly powerful indicator of generalization in deep networks?" paper, layer rotation indicator provides quantative measure on generalization. We can integrate a LayerRotation indicator handler based on this implementation into contrib.
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 reading the linked paper and the referenced code/handlers/layer_rotation.py implementation, then inspect existing handlers in the contrib area of PyTorch Ignite. The work is done when a LayerRotation indicator is integrated into contrib and provides the quantitative generalization-related measure described by the issue.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100