threestudio-project/threestudio

Reproducibility

Open

#219 opened on Jul 10, 2023

View on GitHub
 (3 comments) (0 reactions) (0 assignees)Python (395 forks)batch import
help wanted

Repository metrics

Stars
 (4,771 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

Although we have a configured seed for each experiment, I still observe different results from the same configuration. I suspect there exist some modules out of the seed_everything control. Does anyone have any inspiration for this?

Contributor guide

Research direction
Inspect the codebase to identify all sources of randomness. Check data loading, augmentation, model initialization, and any custom operations that might bypass the seed control. Look for modules that use random functions from Python's random module, numpy, or torch outside of seed everything calls.
Tech stack
python
Domain
computer graphicsmachine learning
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
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.
Mostly clear
Prerequisites
PythonGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60