Interface PrCurve.ConfidenceMetricsEntryOrBuilder (0.134.0)

public static interface PrCurve.ConfidenceMetricsEntryOrBuilder extends MessageOrBuilder

Implements

MessageOrBuilder

Methods

getConfidenceThreshold()

public abstract float getConfidenceThreshold()

Threshold used for this entry. For classification tasks, this is a classification threshold: a predicted label is categorized as positive or negative (in the context of this point on the PR curve) based on whether the label's score meets this threshold. For image object detection (bounding box) tasks, this is the intersection-over-union (IOU) threshold for the context of this point on the PR curve.

float confidence_threshold = 1;

Returns
Type	Description
`float`	The confidenceThreshold.

getF1Score()

public abstract float getF1Score()

Harmonic mean of recall and precision.

float f1_score = 4;

Returns
Type	Description
`float`	The f1Score.

getF1ScoreAt1()

public abstract float getF1ScoreAt1()

The harmonic mean of recall_at1 and precision_at1.

float f1_score_at1 = 7;

Returns
Type	Description
`float`	The f1ScoreAt1.

getF1ScoreAt5()

public abstract float getF1ScoreAt5()

The harmonic mean of recall_at5 and precision_at5.

float f1_score_at5 = 10;

Returns
Type	Description
`float`	The f1ScoreAt5.

getPrecision()

public abstract float getPrecision()

Precision value.

float precision = 3;

Returns
Type	Description
`float`	The precision.

getPrecisionAt1()

public abstract float getPrecisionAt1()

Precision value for entries with label that has highest score.

float precision_at1 = 6;

Returns
Type	Description
`float`	The precisionAt1.

getPrecisionAt5()

public abstract float getPrecisionAt5()

Precision value for entries with label that has highest 5 scores.

float precision_at5 = 9;

Returns
Type	Description
`float`	The precisionAt5.

getRecall()

public abstract float getRecall()

Recall value.

float recall = 2;

Returns
Type	Description
`float`	The recall.

getRecallAt1()

public abstract float getRecallAt1()

Recall value for entries with label that has highest score.

float recall_at1 = 5;

Returns
Type	Description
`float`	The recallAt1.

getRecallAt5()

public abstract float getRecallAt5()

Recall value for entries with label that has highest 5 scores.

float recall_at5 = 8;

Returns
Type	Description
`float`	The recallAt5.