kohya-ss / kohya-ss/sd-scripts
Implement exponential moving averages (EMA)
Open
- Dominant language
- Python
- Stars
- 7.2k
- Forks
- 1.2k
- Avg merge
- 11m
- Merged PRs (30d)
- 2
Description
using EMA during training often leads to better results, and is a standard technique these days in training models.
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue only requests exponential moving averages during training and names no files, tests, or entry points. Start by locating the training loop and how model state is currently saved or updated. Done should include a defined EMA integration and tests or validation showing it is applied during model training.
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