Show / Hide Table of Contents

Class PrCurve.Types.ConfidenceMetricsEntry

Inheritance
System.Object
PrCurve.Types.ConfidenceMetricsEntry
Implements
IMessage<PrCurve.Types.ConfidenceMetricsEntry>
System.IEquatable<PrCurve.Types.ConfidenceMetricsEntry>
IDeepCloneable<PrCurve.Types.ConfidenceMetricsEntry>
Google.Protobuf.IBufferMessage
IMessage
Inherited Members
System.Object.ToString()
System.Object.GetHashCode()
System.Object.GetType()
System.Object.MemberwiseClone()
Namespace: Google.Cloud.DataLabeling.V1Beta1
Assembly: Google.Cloud.DataLabeling.V1Beta1.dll
Syntax
public sealed class ConfidenceMetricsEntry : IMessage<PrCurve.Types.ConfidenceMetricsEntry>, IEquatable<PrCurve.Types.ConfidenceMetricsEntry>, IDeepCloneable<PrCurve.Types.ConfidenceMetricsEntry>, IBufferMessage, IMessage

Constructors

ConfidenceMetricsEntry()

Declaration
public ConfidenceMetricsEntry()

ConfidenceMetricsEntry(PrCurve.Types.ConfidenceMetricsEntry)

Declaration
public ConfidenceMetricsEntry(PrCurve.Types.ConfidenceMetricsEntry other)
Parameters
Type Name Description
PrCurve.Types.ConfidenceMetricsEntry other

Properties

ConfidenceThreshold

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)](/vision/automl/object-detection/docs/evaluate#intersection-over-union) threshold for the context of this point on the PR curve.

Declaration
public float ConfidenceThreshold { get; set; }
Property Value
Type Description
System.Single

F1Score

Harmonic mean of recall and precision.

Declaration
public float F1Score { get; set; }
Property Value
Type Description
System.Single

F1ScoreAt1

The harmonic mean of [recall_at1][google.cloud.datalabeling.v1beta1.PrCurve.ConfidenceMetricsEntry.recall_at1] and [precision_at1][google.cloud.datalabeling.v1beta1.PrCurve.ConfidenceMetricsEntry.precision_at1].

Declaration
public float F1ScoreAt1 { get; set; }
Property Value
Type Description
System.Single

F1ScoreAt5

The harmonic mean of [recall_at5][google.cloud.datalabeling.v1beta1.PrCurve.ConfidenceMetricsEntry.recall_at5] and [precision_at5][google.cloud.datalabeling.v1beta1.PrCurve.ConfidenceMetricsEntry.precision_at5].

Declaration
public float F1ScoreAt5 { get; set; }
Property Value
Type Description
System.Single

Precision

Precision value.

Declaration
public float Precision { get; set; }
Property Value
Type Description
System.Single

PrecisionAt1

Precision value for entries with label that has highest score.

Declaration
public float PrecisionAt1 { get; set; }
Property Value
Type Description
System.Single

PrecisionAt5

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

Declaration
public float PrecisionAt5 { get; set; }
Property Value
Type Description
System.Single

Recall

Recall value.

Declaration
public float Recall { get; set; }
Property Value
Type Description
System.Single

RecallAt1

Recall value for entries with label that has highest score.

Declaration
public float RecallAt1 { get; set; }
Property Value
Type Description
System.Single

RecallAt5

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

Declaration
public float RecallAt5 { get; set; }
Property Value
Type Description
System.Single
Back to top