Package com.google.cloud.aiplatform.v1

Interface ExplanationMetadata.InputMetadataOrBuilder

All Superinterfaces:
com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder
All Known Implementing Classes:
ExplanationMetadata.InputMetadata, ExplanationMetadata.InputMetadata.Builder
Enclosing class:
ExplanationMetadata
public static interface ExplanationMetadata.InputMetadataOrBuilder extends com.google.protobuf.MessageOrBuilder

  • Method Details

    • getInputBaselinesList

      List<com.google.protobuf.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][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].
      repeated .google.protobuf.Value input_baselines = 1;

    • getInputBaselines

      com.google.protobuf.Value getInputBaselines(int index)
       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].
      repeated .google.protobuf.Value input_baselines = 1;

    • getInputBaselinesCount

      int getInputBaselinesCount()
       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].
      repeated .google.protobuf.Value input_baselines = 1;

    • getInputBaselinesOrBuilderList

      List<? extends com.google.protobuf.ValueOrBuilder> 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][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].
      repeated .google.protobuf.Value input_baselines = 1;

    • getInputBaselinesOrBuilder

      com.google.protobuf.ValueOrBuilder getInputBaselinesOrBuilder(int index)
       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].
      repeated .google.protobuf.Value input_baselines = 1;

    • getInputTensorName

      String getInputTensorName()
       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;
      Returns:
      The inputTensorName.

    • getInputTensorNameBytes

      com.google.protobuf.ByteString getInputTensorNameBytes()
       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;
      Returns:
      The bytes for inputTensorName.

    • getEncodingValue

      int getEncodingValue()
       Defines how the feature is encoded into the input tensor. Defaults to
 IDENTITY.
      .google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata.Encoding encoding = 3;
      Returns:
      The enum numeric value on the wire for encoding.

    • getEncoding

      ExplanationMetadata.InputMetadata.Encoding getEncoding()
       Defines how the feature is encoded into the input tensor. Defaults to
 IDENTITY.
      .google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata.Encoding encoding = 3;
      Returns:
      The encoding.

    • getModality

      String getModality()
       Modality of the feature. Valid values are: numeric, image. Defaults to
 numeric.
      string modality = 4;
      Returns:
      The modality.

    • getModalityBytes

      com.google.protobuf.ByteString getModalityBytes()
       Modality of the feature. Valid values are: numeric, image. Defaults to
 numeric.
      string modality = 4;
      Returns:
      The bytes for modality.

    • hasFeatureValueDomain

      boolean hasFeatureValueDomain()
       The domain details of the input feature value. Like min/max, original
 mean or standard deviation if normalized.
      .google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata.FeatureValueDomain feature_value_domain = 5;
      Returns:
      Whether the featureValueDomain field is set.

    • getFeatureValueDomain

      ExplanationMetadata.InputMetadata.FeatureValueDomain getFeatureValueDomain()
       The domain details of the input feature value. Like min/max, original
 mean or standard deviation if normalized.
      .google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata.FeatureValueDomain feature_value_domain = 5;
      Returns:
      The featureValueDomain.

    • getFeatureValueDomainOrBuilder

      ExplanationMetadata.InputMetadata.FeatureValueDomainOrBuilder getFeatureValueDomainOrBuilder()
       The domain details of the input feature value. Like min/max, original
 mean or standard deviation if normalized.
      .google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata.FeatureValueDomain feature_value_domain = 5;

    • getIndicesTensorName

      String getIndicesTensorName()
       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;
      Returns:
      The indicesTensorName.

    • getIndicesTensorNameBytes

      com.google.protobuf.ByteString getIndicesTensorNameBytes()
       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;
      Returns:
      The bytes for indicesTensorName.

    • getDenseShapeTensorName

      String getDenseShapeTensorName()
       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;
      Returns:
      The denseShapeTensorName.

    • getDenseShapeTensorNameBytes

      com.google.protobuf.ByteString getDenseShapeTensorNameBytes()
       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;
      Returns:
      The bytes for denseShapeTensorName.

    • getIndexFeatureMappingList

      List<String> getIndexFeatureMappingList()
       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.
      repeated string index_feature_mapping = 8;
      Returns:
      A list containing the indexFeatureMapping.

    • getIndexFeatureMappingCount

      int getIndexFeatureMappingCount()
       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.
      repeated string index_feature_mapping = 8;
      Returns:
      The count of indexFeatureMapping.

    • getIndexFeatureMapping

      String getIndexFeatureMapping(int index)
       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.
      repeated string index_feature_mapping = 8;
      Parameters:
      index - The index of the element to return.
      Returns:
      The indexFeatureMapping at the given index.

    • getIndexFeatureMappingBytes

      com.google.protobuf.ByteString getIndexFeatureMappingBytes(int index)
       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.
      repeated string index_feature_mapping = 8;
      Parameters:
      index - The index of the value to return.
      Returns:
      The bytes of the indexFeatureMapping at the given index.

    • getEncodedTensorName

      String getEncodedTensorName()
       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.
      string encoded_tensor_name = 9;
      Returns:
      The encodedTensorName.

    • getEncodedTensorNameBytes

      com.google.protobuf.ByteString getEncodedTensorNameBytes()
       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.
      string encoded_tensor_name = 9;
      Returns:
      The bytes for encodedTensorName.

    • getEncodedBaselinesList

      List<com.google.protobuf.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;

    • getEncodedBaselines

      com.google.protobuf.Value getEncodedBaselines(int index)
       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;

    • getEncodedBaselinesCount

      int getEncodedBaselinesCount()
       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;

    • getEncodedBaselinesOrBuilderList

      List<? extends com.google.protobuf.ValueOrBuilder> 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;

    • getEncodedBaselinesOrBuilder

      com.google.protobuf.ValueOrBuilder getEncodedBaselinesOrBuilder(int index)
       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;

    • hasVisualization

      boolean hasVisualization()
       Visualization configurations for image explanation.
      .google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata.Visualization visualization = 11;
      Returns:
      Whether the visualization field is set.

    • getVisualization

      ExplanationMetadata.InputMetadata.Visualization getVisualization()
       Visualization configurations for image explanation.
      .google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata.Visualization visualization = 11;
      Returns:
      The visualization.

    • getVisualizationOrBuilder

      ExplanationMetadata.InputMetadata.VisualizationOrBuilder getVisualizationOrBuilder()
       Visualization configurations for image explanation.
      .google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata.Visualization visualization = 11;

    • getGroupName

      String getGroupName()
       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.
      string group_name = 12;
      Returns:
      The groupName.

    • getGroupNameBytes

      com.google.protobuf.ByteString getGroupNameBytes()
       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.
      string group_name = 12;
      Returns:
      The bytes for groupName.