Contents

averageOfMeanAveragePrecisionAtVariedThresholds(predictions:annotations:confidenceThresholds:)

Calculates the average of mean average precision, computed at varied bounding box overlap thresholds. The overlap thresholds range is from [0.05, 0.95] with a stride of 0.05.

Declaration

func averageOfMeanAveragePrecisionAtVariedThresholds<Scalar>(predictions: [[DetectedObject<Label>]], annotations: [ObjectDetectionAnnotation<Label>], confidenceThresholds: [Label : Float] = [:]) -> Scalar where Scalar : BinaryFloatingPoint

Parameters

  • predictions:

    A list of all the predictions from an object detection model. Each element in the list is a list of predictions from one image.

  • annotations:

    A list of all the annotations. Each element is an ObjectDetectionAnnotation object from one image.

  • confidenceThresholds:

    Confidence thresholds for each label. The values will always be between 0.0 and 1.0. If any label does not have a threshold, the defaultConfidenceThreshold is used for that label. The default value is [:].

Return Value

The average of mean average precision, computed at varied bounding box overlap thresholds.

See Also

Calculating the precision