evaluation(on:confidenceThresholds:)
Computes evaluation metrics on annotated examples.
Declaration
func evaluation(on input: some Collection<AnnotatedFeature<MLShapedArray<Scalar>, Set<Label>>>, confidenceThresholds: [Label : Float]) throws -> MultiLabelClassificationMetrics<Label>Parameters
- input:
A collection of annotated examples.
- confidenceThresholds:
A dictionary of label and confidence threshold pairs.
Return Value
Multi-label classifier metrics.