ContinualAI / ContinualAI/avalanche

Incremental classification strategy and best practices

Open
#329 0 comments 1 reaction 0 assignees View on GitHub
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

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.