ContinualAI / ContinualAI/avalanche
feature request: support gradually changing distributions
Open
Feature - Medium Priority
- Dominant language
- Python
- Stars
- 2.1k
- Forks
- 321
- PR merge metrics
- No merged PRs in 30d
Description
It would be very helpful to support smoothly changing distributions, as illustrated below
(from [FOO-VB ](https://arxiv.org/pdf/2010.00373.pdf)paper, which uses permuted mnist).
Contributor guide
Research direction
The issue names no repository files, tests, or entry points. Start by reading the linked FOO-VB paper and clarifying how smoothly changing distributions should be represented in Avalanche; done would require an agreed implementation scope and corresponding tests.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100