Class ExplanationMetadata.InputMetadata (1.2.0)

publicstaticfinalclass ExplanationMetadata.InputMetadataextendsGeneratedMessageV3implementsExplanationMetadata.InputMetadataOrBuilder

Metadata of the input of a feature.

Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.

Protobuf type google.cloud.vertexai.v1.ExplanationMetadata.InputMetadata

Inheritance

Object > AbstractMessageLite<MessageType,BuilderType> > AbstractMessage > GeneratedMessageV3 > ExplanationMetadata.InputMetadata

Implements

ExplanationMetadata.InputMetadataOrBuilder

Inherited Members

publicstaticfinalintDENSE_SHAPE_TENSOR_NAME_FIELD_NUMBER

publicstaticfinalintENCODED_BASELINES_FIELD_NUMBER

publicstaticfinalintENCODED_TENSOR_NAME_FIELD_NUMBER

publicstaticfinalintENCODING_FIELD_NUMBER

publicstaticfinalintFEATURE_VALUE_DOMAIN_FIELD_NUMBER

publicstaticfinalintGROUP_NAME_FIELD_NUMBER

publicstaticfinalintINDEX_FEATURE_MAPPING_FIELD_NUMBER

publicstaticfinalintINDICES_TENSOR_NAME_FIELD_NUMBER

publicstaticfinalintINPUT_BASELINES_FIELD_NUMBER

publicstaticfinalintINPUT_TENSOR_NAME_FIELD_NUMBER

publicstaticfinalintMODALITY_FIELD_NUMBER

publicstaticfinalintVISUALIZATION_FIELD_NUMBER

publicstaticExplanationMetadata.InputMetadatagetDefaultInstance()

publicstaticfinalDescriptors.DescriptorgetDescriptor()

publicstaticExplanationMetadata.InputMetadata.BuildernewBuilder()

publicstaticExplanationMetadata.InputMetadata.BuildernewBuilder(ExplanationMetadata.InputMetadataprototype)

publicstaticExplanationMetadata.InputMetadataparseDelimitedFrom(InputStreaminput)

publicstaticExplanationMetadata.InputMetadataparseDelimitedFrom(InputStreaminput,ExtensionRegistryLiteextensionRegistry)

publicstaticExplanationMetadata.InputMetadataparseFrom(byte[]data)

publicstaticExplanationMetadata.InputMetadataparseFrom(byte[]data,ExtensionRegistryLiteextensionRegistry)

publicstaticExplanationMetadata.InputMetadataparseFrom(ByteStringdata)

publicstaticExplanationMetadata.InputMetadataparseFrom(ByteStringdata,ExtensionRegistryLiteextensionRegistry)

publicstaticExplanationMetadata.InputMetadataparseFrom(CodedInputStreaminput)

publicstaticExplanationMetadata.InputMetadataparseFrom(CodedInputStreaminput,ExtensionRegistryLiteextensionRegistry)

publicstaticExplanationMetadata.InputMetadataparseFrom(InputStreaminput)

publicstaticExplanationMetadata.InputMetadataparseFrom(InputStreaminput,ExtensionRegistryLiteextensionRegistry)

publicstaticExplanationMetadata.InputMetadataparseFrom(ByteBufferdata)

publicstaticExplanationMetadata.InputMetadataparseFrom(ByteBufferdata,ExtensionRegistryLiteextensionRegistry)

publicstaticParser<ExplanationMetadata.InputMetadata>parser()

publicbooleanequals(Objectobj)

AbstractMessage.equals(Object other)

publicExplanationMetadata.InputMetadatagetDefaultInstanceForType()

publicStringgetDenseShapeTensorName()

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.

string dense_shape_tensor_name = 7;

publicByteStringgetDenseShapeTensorNameBytes()

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.

string dense_shape_tensor_name = 7;

publicValuegetEncodedBaselines(intindex)

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.

repeated .google.protobuf.Value encoded_baselines = 10;

publicintgetEncodedBaselinesCount()

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.

repeated .google.protobuf.Value encoded_baselines = 10;

publicList<Value>getEncodedBaselinesList()

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.

repeated .google.protobuf.Value encoded_baselines = 10;

publicValueOrBuildergetEncodedBaselinesOrBuilder(intindex)

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.

repeated .google.protobuf.Value encoded_baselines = 10;

publicList<?extendsValueOrBuilder>getEncodedBaselinesOrBuilderList()

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.

repeated .google.protobuf.Value encoded_baselines = 10;

publicStringgetEncodedTensorName()

Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable.

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

string encoded_tensor_name = 9;

publicByteStringgetEncodedTensorNameBytes()

Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable.

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

string encoded_tensor_name = 9;

publicExplanationMetadata.InputMetadata.EncodinggetEncoding()

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

.google.cloud.vertexai.v1.ExplanationMetadata.InputMetadata.Encoding encoding = 3;

publicintgetEncodingValue()

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

.google.cloud.vertexai.v1.ExplanationMetadata.InputMetadata.Encoding encoding = 3;

publicExplanationMetadata.InputMetadata.FeatureValueDomaingetFeatureValueDomain()

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

.google.cloud.vertexai.v1.ExplanationMetadata.InputMetadata.FeatureValueDomain feature_value_domain = 5;

publicExplanationMetadata.InputMetadata.FeatureValueDomainOrBuildergetFeatureValueDomainOrBuilder()

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

.google.cloud.vertexai.v1.ExplanationMetadata.InputMetadata.FeatureValueDomain feature_value_domain = 5;

publicStringgetGroupName()

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, keyed by the group name.

string group_name = 12;

publicByteStringgetGroupNameBytes()

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, keyed by the group name.

string group_name = 12;

publicStringgetIndexFeatureMapping(intindex)

A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.

repeated string index_feature_mapping = 8;

publicByteStringgetIndexFeatureMappingBytes(intindex)

A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.

repeated string index_feature_mapping = 8;

publicintgetIndexFeatureMappingCount()

A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.

repeated string index_feature_mapping = 8;

publicProtocolStringListgetIndexFeatureMappingList()

A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.

repeated string index_feature_mapping = 8;

publicStringgetIndicesTensorName()

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.

string indices_tensor_name = 6;

publicByteStringgetIndicesTensorNameBytes()

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.

string indices_tensor_name = 6;

publicValuegetInputBaselines(intindex)

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.

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[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.

repeated .google.protobuf.Value input_baselines = 1;

publicintgetInputBaselinesCount()

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.

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[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.

repeated .google.protobuf.Value input_baselines = 1;

publicList<Value>getInputBaselinesList()

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.

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[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.

repeated .google.protobuf.Value input_baselines = 1;

publicValueOrBuildergetInputBaselinesOrBuilder(intindex)

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.

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[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.

repeated .google.protobuf.Value input_baselines = 1;

publicList<?extendsValueOrBuilder>getInputBaselinesOrBuilderList()

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.

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[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.

repeated .google.protobuf.Value input_baselines = 1;

publicStringgetInputTensorName()

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

string input_tensor_name = 2;

publicByteStringgetInputTensorNameBytes()

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

string input_tensor_name = 2;

publicStringgetModality()

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

string modality = 4;

publicByteStringgetModalityBytes()

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

string modality = 4;

publicParser<ExplanationMetadata.InputMetadata>getParserForType()

GeneratedMessageV3.getParserForType()

publicintgetSerializedSize()

GeneratedMessageV3.getSerializedSize()

publicExplanationMetadata.InputMetadata.VisualizationgetVisualization()

Visualization configurations for image explanation.

.google.cloud.vertexai.v1.ExplanationMetadata.InputMetadata.Visualization visualization = 11;

publicExplanationMetadata.InputMetadata.VisualizationOrBuildergetVisualizationOrBuilder()

Visualization configurations for image explanation.

.google.cloud.vertexai.v1.ExplanationMetadata.InputMetadata.Visualization visualization = 11;

publicbooleanhasFeatureValueDomain()

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

.google.cloud.vertexai.v1.ExplanationMetadata.InputMetadata.FeatureValueDomain feature_value_domain = 5;

publicbooleanhasVisualization()

Visualization configurations for image explanation.

.google.cloud.vertexai.v1.ExplanationMetadata.InputMetadata.Visualization visualization = 11;

publicinthashCode()

AbstractMessage.hashCode()

protectedGeneratedMessageV3.FieldAccessorTableinternalGetFieldAccessorTable()

GeneratedMessageV3.internalGetFieldAccessorTable()

publicfinalbooleanisInitialized()

GeneratedMessageV3.isInitialized()

publicExplanationMetadata.InputMetadata.BuildernewBuilderForType()

protectedExplanationMetadata.InputMetadata.BuildernewBuilderForType(GeneratedMessageV3.BuilderParentparent)

GeneratedMessageV3.newBuilderForType(GeneratedMessageV3.BuilderParent parent)

protectedObjectnewInstance(GeneratedMessageV3.UnusedPrivateParameterunused)

GeneratedMessageV3.newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)

publicExplanationMetadata.InputMetadata.BuildertoBuilder()

publicvoidwriteTo(CodedOutputStreamoutput)

GeneratedMessageV3.writeTo(CodedOutputStream output)