public static interface ExplanationMetadata.InputMetadataOrBuilder
extends com.google.protobuf.MessageOrBuilder
| Modifier and Type | Method and Description |
|---|---|
String |
getDenseShapeTensorName()
Specifies the shape of the values of the input if the input is a sparse
representation.
|
com.google.protobuf.ByteString |
getDenseShapeTensorNameBytes()
Specifies the shape of the values of the input if the input is a sparse
representation.
|
com.google.protobuf.Value |
getEncodedBaselines(int index)
A list of baselines for the encoded tensor.
|
int |
getEncodedBaselinesCount()
A list of baselines for the encoded tensor.
|
List<com.google.protobuf.Value> |
getEncodedBaselinesList()
A list of baselines for the encoded tensor.
|
com.google.protobuf.ValueOrBuilder |
getEncodedBaselinesOrBuilder(int index)
A list of baselines for the encoded tensor.
|
List<? extends com.google.protobuf.ValueOrBuilder> |
getEncodedBaselinesOrBuilderList()
A list of baselines for the encoded tensor.
|
String |
getEncodedTensorName()
Encoded tensor is a transformation of the input tensor.
|
com.google.protobuf.ByteString |
getEncodedTensorNameBytes()
Encoded tensor is a transformation of the input tensor.
|
ExplanationMetadata.InputMetadata.Encoding |
getEncoding()
Defines how the feature is encoded into the input tensor.
|
int |
getEncodingValue()
Defines how the feature is encoded into the input tensor.
|
ExplanationMetadata.InputMetadata.FeatureValueDomain |
getFeatureValueDomain()
The domain details of the input feature value.
|
ExplanationMetadata.InputMetadata.FeatureValueDomainOrBuilder |
getFeatureValueDomainOrBuilder()
The domain details of the input feature value.
|
String |
getGroupName()
Name of the group that the input belongs to.
|
com.google.protobuf.ByteString |
getGroupNameBytes()
Name of the group that the input belongs to.
|
String |
getIndexFeatureMapping(int index)
A list of feature names for each index in the input tensor.
|
com.google.protobuf.ByteString |
getIndexFeatureMappingBytes(int index)
A list of feature names for each index in the input tensor.
|
int |
getIndexFeatureMappingCount()
A list of feature names for each index in the input tensor.
|
List<String> |
getIndexFeatureMappingList()
A list of feature names for each index in the input tensor.
|
String |
getIndicesTensorName()
Specifies the index of the values of the input tensor.
|
com.google.protobuf.ByteString |
getIndicesTensorNameBytes()
Specifies the index of the values of the input tensor.
|
com.google.protobuf.Value |
getInputBaselines(int index)
Baseline inputs for this feature.
|
int |
getInputBaselinesCount()
Baseline inputs for this feature.
|
List<com.google.protobuf.Value> |
getInputBaselinesList()
Baseline inputs for this feature.
|
com.google.protobuf.ValueOrBuilder |
getInputBaselinesOrBuilder(int index)
Baseline inputs for this feature.
|
List<? extends com.google.protobuf.ValueOrBuilder> |
getInputBaselinesOrBuilderList()
Baseline inputs for this feature.
|
String |
getInputTensorName()
Name of the input tensor for this feature.
|
com.google.protobuf.ByteString |
getInputTensorNameBytes()
Name of the input tensor for this feature.
|
String |
getModality()
Modality of the feature.
|
com.google.protobuf.ByteString |
getModalityBytes()
Modality of the feature.
|
ExplanationMetadata.InputMetadata.Visualization |
getVisualization()
Visualization configurations for image explanation.
|
ExplanationMetadata.InputMetadata.VisualizationOrBuilder |
getVisualizationOrBuilder()
Visualization configurations for image explanation.
|
boolean |
hasFeatureValueDomain()
The domain details of the input feature value.
|
boolean |
hasVisualization()
Visualization configurations for image explanation.
|
findInitializationErrors, getAllFields, getDefaultInstanceForType, getDescriptorForType, getField, getInitializationErrorString, getOneofFieldDescriptor, getRepeatedField, getRepeatedFieldCount, getUnknownFields, hasField, hasOneofList<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;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;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;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;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;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;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;int getEncodingValue()
Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.
.google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata.Encoding encoding = 3;
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;
String getModality()
Modality of the feature. Valid values are: numeric, image. Defaults to numeric.
string modality = 4;com.google.protobuf.ByteString getModalityBytes()
Modality of the feature. Valid values are: numeric, image. Defaults to numeric.
string modality = 4;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;
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;
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;
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;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;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;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;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;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;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;index - The index of the element to return.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;index - The index of the value to return.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;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;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;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;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;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;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;boolean hasVisualization()
Visualization configurations for image explanation.
.google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata.Visualization visualization = 11;
ExplanationMetadata.InputMetadata.Visualization getVisualization()
Visualization configurations for image explanation.
.google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata.Visualization visualization = 11;
ExplanationMetadata.InputMetadata.VisualizationOrBuilder getVisualizationOrBuilder()
Visualization configurations for image explanation.
.google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata.Visualization visualization = 11;
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;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;Copyright © 2023 Google LLC. All rights reserved.