Cloud AI Platform v1 API - Class ExplanationMetadata.Types.OutputMetadata (2.13.0) 

public sealed class ExplanationMetadata.Types.OutputMetadata : IMessage<ExplanationMetadata.Types.OutputMetadata>, IEquatable<ExplanationMetadata.Types.OutputMetadata>, IDeepCloneable<ExplanationMetadata.Types.OutputMetadata>, IBufferMessage, IMessage

Reference documentation and code samples for the Cloud AI Platform v1 API class ExplanationMetadata.Types.OutputMetadata.

Metadata of the prediction output to be explained.

Inheritance

object > ExplanationMetadata.Types.OutputMetadata

Namespace

GoogleCloudGoogle.Cloud.AIPlatformV1

Assembly

Google.Cloud.AIPlatform.V1.dll

Constructors

OutputMetadata()

public OutputMetadata()

OutputMetadata(OutputMetadata)

public OutputMetadata(ExplanationMetadata.Types.OutputMetadata other)
Parameter
NameDescription
otherExplanationMetadataTypesOutputMetadata

Properties

DisplayNameMappingCase

public ExplanationMetadata.Types.OutputMetadata.DisplayNameMappingOneofCase DisplayNameMappingCase { get; }
Property Value
TypeDescription
ExplanationMetadataTypesOutputMetadataDisplayNameMappingOneofCase

DisplayNameMappingKey

public string DisplayNameMappingKey { get; set; }

Specify a field name in the prediction to look for the display name.

Use this if the prediction contains the display names for the outputs.

The display names in the prediction must have the same shape of the outputs, so that it can be located by [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index] for a specific output.

Property Value
TypeDescription
string

IndexDisplayNameMapping

public Value IndexDisplayNameMapping { get; set; }

Static mapping between the index and display name.

Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values.

The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The [Attribution.output_display_name][google.cloud.aiplatform.v1.Attribution.output_display_name] is populated by locating in the mapping with [Attribution.output_index][google.cloud.aiplatform.v1.Attribution.output_index].

Property Value
TypeDescription
Value

OutputTensorName

public string OutputTensorName { get; set; }

Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.

Property Value
TypeDescription
string