Cloud AI Platform v1 API - Class ExplanationMetadata.Types.InputMetadata (2.18.0)

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

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

Metadata of the input of a feature.

Fields other than [InputMetadata.input_baselines][google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata.input_baselines] are applicable only for Models that are using Vertex AI-provided images for Tensorflow.

Inheritance

object > ExplanationMetadata.Types.InputMetadata

Namespace

Google.Cloud.AIPlatform.V1

Assembly

Google.Cloud.AIPlatform.V1.dll

Constructors

InputMetadata()

public InputMetadata()

InputMetadata(InputMetadata)

public InputMetadata(ExplanationMetadata.Types.InputMetadata other)
Parameter
NameDescription
otherExplanationMetadataTypesInputMetadata

Properties

DenseShapeTensorName

public string DenseShapeTensorName { get; set; }

Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.

Property Value
TypeDescription
string

EncodedBaselines

public RepeatedField<Value> EncodedBaselines { get; }

A list of baselines for the encoded tensor.

The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.

Property Value
TypeDescription
RepeatedFieldValue

EncodedTensorName

public string EncodedTensorName { get; set; }

Encoded tensor is a transformation of the input tensor. Must be provided if choosing [Integrated Gradients attribution][google.cloud.aiplatform.v1.ExplanationParameters.integrated_gradients_attribution] or [XRAI attribution][google.cloud.aiplatform.v1.ExplanationParameters.xrai_attribution] and the input tensor is not differentiable.

An encoded tensor is generated if the input tensor is encoded by a lookup table.

Property Value
TypeDescription
string

Encoding

public ExplanationMetadata.Types.InputMetadata.Types.Encoding Encoding { get; set; }

Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.

Property Value
TypeDescription
ExplanationMetadataTypesInputMetadataTypesEncoding

FeatureValueDomain

public ExplanationMetadata.Types.InputMetadata.Types.FeatureValueDomain FeatureValueDomain { get; set; }

The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.

Property Value
TypeDescription
ExplanationMetadataTypesInputMetadataTypesFeatureValueDomain

GroupName

public string GroupName { get; set; }

Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in [Attribution.feature_attributions][google.cloud.aiplatform.v1.Attribution.feature_attributions], keyed by the group name.

Property Value
TypeDescription
string

IndexFeatureMapping

public RepeatedField<string> IndexFeatureMapping { get; }

A list of feature names for each index in the input tensor. Required when the input [InputMetadata.encoding][google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata.encoding] is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.

Property Value
TypeDescription
RepeatedFieldstring

IndicesTensorName

public string IndicesTensorName { get; set; }

Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.

Property Value
TypeDescription
string

InputBaselines

public RepeatedField<Value> InputBaselines { get; }

Baseline inputs for this feature.

If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in [Attribution.feature_attributions][google.cloud.aiplatform.v1.Attribution.feature_attributions].

For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor.

For custom images, the element of the baselines must be in the same format as the feature's input in the [instance][google.cloud.aiplatform.v1.ExplainRequest.instances][]. The schema of any single instance may be specified via Endpoint's DeployedModels' [Model's][google.cloud.aiplatform.v1.DeployedModel.model] [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata] [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri].

Property Value
TypeDescription
RepeatedFieldValue

InputTensorName

public string InputTensorName { get; set; }

Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.

Property Value
TypeDescription
string

Modality

public string Modality { get; set; }

Modality of the feature. Valid values are: numeric, image. Defaults to numeric.

Property Value
TypeDescription
string

Visualization

public ExplanationMetadata.Types.InputMetadata.Types.Visualization Visualization { get; set; }

Visualization configurations for image explanation.

Property Value
TypeDescription
ExplanationMetadataTypesInputMetadataTypesVisualization