Class ClassificationEvaluationMetrics

public sealed class ClassificationEvaluationMetrics : IMessage<ClassificationEvaluationMetrics>, IEquatable<ClassificationEvaluationMetrics>, IDeepCloneable<ClassificationEvaluationMetrics>, IBufferMessage, IMessage

Model evaluation metrics for classification problems. Note: For Video Classification this metrics only describe quality of the Video Classification predictions of "segment_classification" type.

Inheritance

Object > ClassificationEvaluationMetrics

Namespace

Google.Cloud.AutoML.V1

Assembly

Google.Cloud.AutoML.V1.dll

Constructors

ClassificationEvaluationMetrics()

public ClassificationEvaluationMetrics()

ClassificationEvaluationMetrics(ClassificationEvaluationMetrics)

public ClassificationEvaluationMetrics(ClassificationEvaluationMetrics other)
Parameter
TypeNameDescription
ClassificationEvaluationMetricsother

Properties

AnnotationSpecId

public RepeatedField<string> AnnotationSpecId { get; }

Output only. The annotation spec ids used for this evaluation.

Property Value
TypeDescription
RepeatedField<String>

AuPrc

public float AuPrc { get; set; }

Output only. The Area Under Precision-Recall Curve metric. Micro-averaged for the overall evaluation.

Property Value
TypeDescription
Single

AuRoc

public float AuRoc { get; set; }

Output only. The Area Under Receiver Operating Characteristic curve metric. Micro-averaged for the overall evaluation.

Property Value
TypeDescription
Single

ConfidenceMetricsEntry

public RepeatedField<ClassificationEvaluationMetrics.Types.ConfidenceMetricsEntry> ConfidenceMetricsEntry { get; }

Output only. Metrics for each confidence_threshold in 0.00,0.05,0.10,...,0.95,0.96,0.97,0.98,0.99 and position_threshold = INT32_MAX_VALUE. ROC and precision-recall curves, and other aggregated metrics are derived from them. The confidence metrics entries may also be supplied for additional values of position_threshold, but from these no aggregated metrics are computed.

Property Value
TypeDescription
RepeatedField<ClassificationEvaluationMetrics.Types.ConfidenceMetricsEntry>

ConfusionMatrix

public ClassificationEvaluationMetrics.Types.ConfusionMatrix ConfusionMatrix { get; set; }

Output only. Confusion matrix of the evaluation. Only set for MULTICLASS classification problems where number of labels is no more than 10. Only set for model level evaluation, not for evaluation per label.

Property Value
TypeDescription
ClassificationEvaluationMetrics.Types.ConfusionMatrix

LogLoss

public float LogLoss { get; set; }

Output only. The Log Loss metric.

Property Value
TypeDescription
Single

Implements