ContinualAI/avalanche

remove benchmarks `reproducibility_data`

Open

#1,273 opened on Jan 9, 2023

View on GitHub
 (0 comments) (0 reactions) (0 assignees)Python (258 forks)batch import
Benchmarksgood first issue

Repository metrics

Stars
 (1,516 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

reproducibility_data is an old serialization mechanism. With the current state of benchmarks it is easier and more efficient to save the benchmark arguments and fix a random seed to guarantee reproducibility (this is not guaranteed to work for different avalanche versions). Alternatively, it is possible to use serialization.

Therefore, we should remove reproducibility_data and and encourage other reproducibility solutions.

Contributor guide

Research direction
Identify all occurrences of `reproducibility data` in the codebase and replace them with fixed random seeds or serialization approaches.
Tech stack
python
Domain
machine learningai
Issue type
Refactor
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
Python
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
65