UncertaintyQuery

class probly.evaluation.active_learning.strategies.UncertaintyQuery[source]

Bases: object

Selects samples with the highest estimator-provided uncertainty scores.

Delegates scoring to estimator.uncertainty_scores(). Suitable for any probly UQ method that provides its own per-sample scoring (e.g. mutual information or any other UQ-based measure).

select(estimator: UncertaintyEstimator, pool: ActiveLearningPool, n: int) → ArrayLike[source]

Return n indices with the highest uncertainty scores from the estimator.

Examples using probly.evaluation.active_learning.strategies.UncertaintyQuery

Active Learning with sklearn - Margin vs Random

Active Learning with sklearn - Margin vs Random

Active Learning with PyTorch - BADGE Selection

Active Learning with PyTorch - BADGE Selection