torch¶

PyTorch implementation of Metrics.

Note

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

Functions¶

`auc_torch`	Compute area under a curve using the trapezoid rule.
`average_precision_score_torch`	Compute average precision for PyTorch tensors.
`precision_recall_curve_torch`	Compute precision-recall curve along the last axis.
`roc_auc_score_torch`	Compute area under the ROC curve for PyTorch tensors.
`roc_curve_torch`	Compute ROC curve along the last axis.