Out of Distribution data in MIA
Ouverte
- Langage dominant
- Python
- Étoiles
- 23
- Forks
- 28
- Merge moyen
- 4 j 12 h
- PR mergées (30 j)
- 5
Description
# Feature
## Desired Behavior / Functionality
Handling out-of-distribution data for creating shadow models.
Out-of-distribution (OoD) data can be either:
- A dataset different from the target model's dataset, or
- The same dataset divided based on a specific feature (not randomly).
## What Needs to Be Done
## How Can It Be Tested
Guide de contribution
Ouvrir le guide de contribution
Évaluation
Cette issue n'a pas encore été évaluée.