ContinualAI / ContinualAI/avalanche
Define early stopping's patience in terms of number of iterations instead of epochs
Open
Training
- Dominant language
- Python
- Stars
- 2.1k
- Forks
- 321
- PR merge metrics
- No merged PRs in 30d
Description
See #670 for a possible usecase.
Add an option to the early stopping plugin to use the number of iterations instead of epochs.
Contributor guide
Assessment
This issue has not been assessed yet.