ContinualAI / ContinualAI/avalanche
Incremental classification strategy and best practices
Open
Feature - Low Priority
Training
- Dominant language
- Python
- Stars
- 2.1k
- Forks
- 321
- PR merge metrics
- No merged PRs in 30d
Description
Following our discussion in #306.
It would be nice to encode best practices inside avalanche strategies. Things such as incremental classifiers that do not assume the number of classes, using/not using task labels, model selection and so on.
I don't think we are ready yet to completely tackle this but I'm leaving this issue open to discuss it for a future implementation and to understand what we need.
Contributor guide
Assessment
This issue has not been assessed yet.