ContinualAI / ContinualAI/avalanche
Multi-Run Support for Avalanche Experiments
Open
Evaluation
Feature - Medium Priority
- Dominant language
- Python
- Stars
- 2.1k
- Forks
- 321
- PR merge metrics
- No merged PRs in 30d
Description
We should support averaging results across multiple runs. This is related to #300.
Contributor guide
Research direction
Start by reading the related issue #300 and tracing how Avalanche experiments currently collect and report results. Define the expected behavior for averaging results across multiple runs, then verify that experiment outputs consistently produce the intended aggregate.
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