Class PredictResponse

Response message for [PredictionService.Predict][google.cloud.automl.v1.PredictionService.Predict].

Inheritance

System.Object

PredictResponse

Implements

IMessage<PredictResponse>

System.IEquatable<PredictResponse>

IDeepCloneable<PredictResponse>

Google.Protobuf.IBufferMessage

IMessage

Inherited Members

System.Object.ToString()

System.Object.GetHashCode()

System.Object.GetType()

System.Object.MemberwiseClone()

Namespace: Google.Cloud.AutoML.V1

Assembly: Google.Cloud.AutoML.V1.dll

Syntax

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

Constructors

PredictResponse()

Declaration

public PredictResponse()

PredictResponse(PredictResponse)

Declaration

public PredictResponse(PredictResponse other)

Parameters

Type	Name	Description
PredictResponse	other

Properties

Metadata

Additional domain-specific prediction response metadata.

AutoML Vision Object Detection

max_bounding_box_count : (int64) The maximum number of bounding boxes to return per image.

AutoML Natural Language Sentiment Analysis

sentiment_score : (float, deprecated) A value between -1 and 1, -1 maps to least positive sentiment, while 1 maps to the most positive one and the higher the score, the more positive the sentiment in the document is. Yet these values are relative to the training data, so e.g. if all data was positive then -1 is also positive (though the least). sentiment_score is not the same as "score" and "magnitude" from Sentiment Analysis in the Natural Language API.

Declaration

public MapField<string, string> Metadata { get; }

Property Value

Type	Description
MapField<System.String, System.String>

Payload

Prediction result. AutoML Translation and AutoML Natural Language Sentiment Analysis return precisely one payload.

Declaration

public RepeatedField<AnnotationPayload> Payload { get; }

Property Value

Type	Description
RepeatedField<AnnotationPayload>

PreprocessedInput

The preprocessed example that AutoML actually makes prediction on. Empty if AutoML does not preprocess the input example.

For AutoML Natural Language (Classification, Entity Extraction, and Sentiment Analysis), if the input is a document, the recognized text is returned in the [document_text][google.cloud.automl.v1.Document.document_text] property.

Declaration

public ExamplePayload PreprocessedInput { get; set; }

Property Value

Type	Description
ExamplePayload