jax

JAX implementation of Metrics.

Note

There is no JaxSingletonCredalSet or JaxDiscreteCredalSet in probly.representation.credal_set.jax; for those semantics, use the numpy-side NumpySingletonCredalSet / NumpyDiscreteCredalSet types. The remaining jax credal sets (Convex, DistanceBased, ProbabilityIntervals, DirichletLevelSet) all use the interval-dominance rule via their lower() / upper() envelopes.

Functions

jax_accuracy	Compute top-1 classification accuracy for JAX arrays.
jax_auc	Compute area under a curve using the trapezoid rule.
jax_average_precision_score	Compute average precision for JAX arrays.
jax_classwise_ece	Compute the classwise expected calibration error for JAX arrays.
jax_expected_calibration_error	Compute the confidence expected calibration error for JAX arrays.
jax_false_negative_rate	Compute the false negative rate for JAX arrays.
jax_false_positive_rate	Compute the false positive rate for JAX arrays.
jax_precision_recall_curve	Compute precision-recall curve along the last axis.
jax_roc_auc_score	Compute area under the ROC curve for JAX arrays.
jax_roc_curve	Compute ROC curve along the last axis.