Class ExplanationMetadata.InputMetadata.Builder (3.41.0)

public static final class ExplanationMetadata.InputMetadata.Builder extends GeneratedMessageV3.Builder<ExplanationMetadata.InputMetadata.Builder> implements ExplanationMetadata.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.aiplatform.v1.ExplanationMetadata.InputMetadata

Static Methods

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()
Returns
TypeDescription
Descriptor

Methods

addAllEncodedBaselines(Iterable<? extends Value> values)

public ExplanationMetadata.InputMetadata.Builder addAllEncodedBaselines(Iterable<? extends Value> values)

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;

Parameter
NameDescription
valuesIterable<? extends com.google.protobuf.Value>
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

addAllIndexFeatureMapping(Iterable<String> values)

public ExplanationMetadata.InputMetadata.Builder addAllIndexFeatureMapping(Iterable<String> values)

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;

Parameter
NameDescription
valuesIterable<String>

The indexFeatureMapping to add.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

addAllInputBaselines(Iterable<? extends Value> values)

public ExplanationMetadata.InputMetadata.Builder addAllInputBaselines(Iterable<? extends Value> values)

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;

Parameter
NameDescription
valuesIterable<? extends com.google.protobuf.Value>
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

addEncodedBaselines(Value value)

public ExplanationMetadata.InputMetadata.Builder addEncodedBaselines(Value value)

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;

Parameter
NameDescription
valueValue
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

addEncodedBaselines(Value.Builder builderForValue)

public ExplanationMetadata.InputMetadata.Builder addEncodedBaselines(Value.Builder builderForValue)

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;

Parameter
NameDescription
builderForValueBuilder
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

addEncodedBaselines(int index, Value value)

public ExplanationMetadata.InputMetadata.Builder addEncodedBaselines(int index, Value value)

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;

Parameters
NameDescription
indexint
valueValue
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

addEncodedBaselines(int index, Value.Builder builderForValue)

public ExplanationMetadata.InputMetadata.Builder addEncodedBaselines(int index, Value.Builder builderForValue)

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;

Parameters
NameDescription
indexint
builderForValueBuilder
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

addEncodedBaselinesBuilder()

public Value.Builder addEncodedBaselinesBuilder()

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;

Returns
TypeDescription
Builder

addEncodedBaselinesBuilder(int index)

public Value.Builder addEncodedBaselinesBuilder(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;

Parameter
NameDescription
indexint
Returns
TypeDescription
Builder

addIndexFeatureMapping(String value)

public ExplanationMetadata.InputMetadata.Builder addIndexFeatureMapping(String value)

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;

Parameter
NameDescription
valueString

The indexFeatureMapping to add.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

addIndexFeatureMappingBytes(ByteString value)

public ExplanationMetadata.InputMetadata.Builder addIndexFeatureMappingBytes(ByteString value)

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;

Parameter
NameDescription
valueByteString

The bytes of the indexFeatureMapping to add.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

addInputBaselines(Value value)

public ExplanationMetadata.InputMetadata.Builder addInputBaselines(Value value)

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;

Parameter
NameDescription
valueValue
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

addInputBaselines(Value.Builder builderForValue)

public ExplanationMetadata.InputMetadata.Builder addInputBaselines(Value.Builder builderForValue)

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;

Parameter
NameDescription
builderForValueBuilder
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

addInputBaselines(int index, Value value)

public ExplanationMetadata.InputMetadata.Builder addInputBaselines(int index, Value value)

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;

Parameters
NameDescription
indexint
valueValue
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

addInputBaselines(int index, Value.Builder builderForValue)

public ExplanationMetadata.InputMetadata.Builder addInputBaselines(int index, Value.Builder builderForValue)

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;

Parameters
NameDescription
indexint
builderForValueBuilder
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

addInputBaselinesBuilder()

public Value.Builder addInputBaselinesBuilder()

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;

Returns
TypeDescription
Builder

addInputBaselinesBuilder(int index)

public Value.Builder addInputBaselinesBuilder(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.

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;

Parameter
NameDescription
indexint
Returns
TypeDescription
Builder

addRepeatedField(Descriptors.FieldDescriptor field, Object value)

public ExplanationMetadata.InputMetadata.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Parameters
NameDescription
fieldFieldDescriptor
valueObject
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder
Overrides

build()

public ExplanationMetadata.InputMetadata build()
Returns
TypeDescription
ExplanationMetadata.InputMetadata

buildPartial()

public ExplanationMetadata.InputMetadata buildPartial()
Returns
TypeDescription
ExplanationMetadata.InputMetadata

clear()

public ExplanationMetadata.InputMetadata.Builder clear()
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder
Overrides

clearDenseShapeTensorName()

public ExplanationMetadata.InputMetadata.Builder clearDenseShapeTensorName()

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
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

clearEncodedBaselines()

public ExplanationMetadata.InputMetadata.Builder clearEncodedBaselines()

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;

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

clearEncodedTensorName()

public ExplanationMetadata.InputMetadata.Builder clearEncodedTensorName()

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;

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

clearEncoding()

public ExplanationMetadata.InputMetadata.Builder clearEncoding()

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

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

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

clearFeatureValueDomain()

public ExplanationMetadata.InputMetadata.Builder clearFeatureValueDomain()

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
TypeDescription
ExplanationMetadata.InputMetadata.Builder

clearField(Descriptors.FieldDescriptor field)

public ExplanationMetadata.InputMetadata.Builder clearField(Descriptors.FieldDescriptor field)
Parameter
NameDescription
fieldFieldDescriptor
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder
Overrides

clearGroupName()

public ExplanationMetadata.InputMetadata.Builder clearGroupName()

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;

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

clearIndexFeatureMapping()

public ExplanationMetadata.InputMetadata.Builder clearIndexFeatureMapping()

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;

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

clearIndicesTensorName()

public ExplanationMetadata.InputMetadata.Builder clearIndicesTensorName()

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
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

clearInputBaselines()

public ExplanationMetadata.InputMetadata.Builder clearInputBaselines()

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;

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

clearInputTensorName()

public ExplanationMetadata.InputMetadata.Builder clearInputTensorName()

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
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

clearModality()

public ExplanationMetadata.InputMetadata.Builder clearModality()

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

string modality = 4;

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

clearOneof(Descriptors.OneofDescriptor oneof)

public ExplanationMetadata.InputMetadata.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Parameter
NameDescription
oneofOneofDescriptor
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder
Overrides

clearVisualization()

public ExplanationMetadata.InputMetadata.Builder clearVisualization()

Visualization configurations for image explanation.

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

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

clone()

public ExplanationMetadata.InputMetadata.Builder clone()
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder
Overrides

getDefaultInstanceForType()

public ExplanationMetadata.InputMetadata getDefaultInstanceForType()
Returns
TypeDescription
ExplanationMetadata.InputMetadata

getDenseShapeTensorName()

public 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
TypeDescription
String

The denseShapeTensorName.

getDenseShapeTensorNameBytes()

public 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
TypeDescription
ByteString

The bytes for denseShapeTensorName.

getDescriptorForType()

public Descriptors.Descriptor getDescriptorForType()
Returns
TypeDescription
Descriptor
Overrides

getEncodedBaselines(int index)

public 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;

Parameter
NameDescription
indexint
Returns
TypeDescription
Value

getEncodedBaselinesBuilder(int index)

public Value.Builder getEncodedBaselinesBuilder(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;

Parameter
NameDescription
indexint
Returns
TypeDescription
Builder

getEncodedBaselinesBuilderList()

public List<Value.Builder> getEncodedBaselinesBuilderList()

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;

Returns
TypeDescription
List<Builder>

getEncodedBaselinesCount()

public 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;

Returns
TypeDescription
int

getEncodedBaselinesList()

public List<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;

Returns
TypeDescription
List<Value>

getEncodedBaselinesOrBuilder(int index)

public 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;

Parameter
NameDescription
indexint
Returns
TypeDescription
ValueOrBuilder

getEncodedBaselinesOrBuilderList()

public List<? extends 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;

Returns
TypeDescription
List<? extends com.google.protobuf.ValueOrBuilder>

getEncodedTensorName()

public String getEncodedTensorName()

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;

Returns
TypeDescription
String

The encodedTensorName.

getEncodedTensorNameBytes()

public ByteString getEncodedTensorNameBytes()

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;

Returns
TypeDescription
ByteString

The bytes for encodedTensorName.

getEncoding()

public 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
TypeDescription
ExplanationMetadata.InputMetadata.Encoding

The encoding.

getEncodingValue()

public 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
TypeDescription
int

The enum numeric value on the wire for encoding.

getFeatureValueDomain()

public 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
TypeDescription
ExplanationMetadata.InputMetadata.FeatureValueDomain

The featureValueDomain.

getFeatureValueDomainBuilder()

public ExplanationMetadata.InputMetadata.FeatureValueDomain.Builder getFeatureValueDomainBuilder()

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
TypeDescription
ExplanationMetadata.InputMetadata.FeatureValueDomain.Builder

getFeatureValueDomainOrBuilder()

public 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;

Returns
TypeDescription
ExplanationMetadata.InputMetadata.FeatureValueDomainOrBuilder

getGroupName()

public 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, keyed by the group name.

string group_name = 12;

Returns
TypeDescription
String

The groupName.

getGroupNameBytes()

public 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, keyed by the group name.

string group_name = 12;

Returns
TypeDescription
ByteString

The bytes for groupName.

getIndexFeatureMapping(int index)

public String getIndexFeatureMapping(int index)

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;

Parameter
NameDescription
indexint

The index of the element to return.

Returns
TypeDescription
String

The indexFeatureMapping at the given index.

getIndexFeatureMappingBytes(int index)

public ByteString getIndexFeatureMappingBytes(int index)

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;

Parameter
NameDescription
indexint

The index of the value to return.

Returns
TypeDescription
ByteString

The bytes of the indexFeatureMapping at the given index.

getIndexFeatureMappingCount()

public int getIndexFeatureMappingCount()

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;

Returns
TypeDescription
int

The count of indexFeatureMapping.

getIndexFeatureMappingList()

public ProtocolStringList getIndexFeatureMappingList()

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;

Returns
TypeDescription
ProtocolStringList

A list containing the indexFeatureMapping.

getIndicesTensorName()

public 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
TypeDescription
String

The indicesTensorName.

getIndicesTensorNameBytes()

public 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
TypeDescription
ByteString

The bytes for indicesTensorName.

getInputBaselines(int index)

public 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.

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;

Parameter
NameDescription
indexint
Returns
TypeDescription
Value

getInputBaselinesBuilder(int index)

public Value.Builder getInputBaselinesBuilder(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.

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;

Parameter
NameDescription
indexint
Returns
TypeDescription
Builder

getInputBaselinesBuilderList()

public List<Value.Builder> getInputBaselinesBuilderList()

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;

Returns
TypeDescription
List<Builder>

getInputBaselinesCount()

public 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.

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;

Returns
TypeDescription
int

getInputBaselinesList()

public List<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;

Returns
TypeDescription
List<Value>

getInputBaselinesOrBuilder(int index)

public 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.

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;

Parameter
NameDescription
indexint
Returns
TypeDescription
ValueOrBuilder

getInputBaselinesOrBuilderList()

public List<? extends 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.

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;

Returns
TypeDescription
List<? extends com.google.protobuf.ValueOrBuilder>

getInputTensorName()

public 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
TypeDescription
String

The inputTensorName.

getInputTensorNameBytes()

public 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
TypeDescription
ByteString

The bytes for inputTensorName.

getModality()

public String getModality()

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

string modality = 4;

Returns
TypeDescription
String

The modality.

getModalityBytes()

public ByteString getModalityBytes()

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

string modality = 4;

Returns
TypeDescription
ByteString

The bytes for modality.

getVisualization()

public ExplanationMetadata.InputMetadata.Visualization getVisualization()

Visualization configurations for image explanation.

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

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Visualization

The visualization.

getVisualizationBuilder()

public ExplanationMetadata.InputMetadata.Visualization.Builder getVisualizationBuilder()

Visualization configurations for image explanation.

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

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Visualization.Builder

getVisualizationOrBuilder()

public ExplanationMetadata.InputMetadata.VisualizationOrBuilder getVisualizationOrBuilder()

Visualization configurations for image explanation.

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

Returns
TypeDescription
ExplanationMetadata.InputMetadata.VisualizationOrBuilder

hasFeatureValueDomain()

public 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
TypeDescription
boolean

Whether the featureValueDomain field is set.

hasVisualization()

public boolean hasVisualization()

Visualization configurations for image explanation.

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

Returns
TypeDescription
boolean

Whether the visualization field is set.

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
TypeDescription
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
TypeDescription
boolean
Overrides

mergeFeatureValueDomain(ExplanationMetadata.InputMetadata.FeatureValueDomain value)

public ExplanationMetadata.InputMetadata.Builder mergeFeatureValueDomain(ExplanationMetadata.InputMetadata.FeatureValueDomain value)

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;

Parameter
NameDescription
valueExplanationMetadata.InputMetadata.FeatureValueDomain
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

mergeFrom(ExplanationMetadata.InputMetadata other)

public ExplanationMetadata.InputMetadata.Builder mergeFrom(ExplanationMetadata.InputMetadata other)
Parameter
NameDescription
otherExplanationMetadata.InputMetadata
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public ExplanationMetadata.InputMetadata.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
inputCodedInputStream
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder
Overrides
Exceptions
TypeDescription
IOException

mergeFrom(Message other)

public ExplanationMetadata.InputMetadata.Builder mergeFrom(Message other)
Parameter
NameDescription
otherMessage
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder
Overrides

mergeUnknownFields(UnknownFieldSet unknownFields)

public final ExplanationMetadata.InputMetadata.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Parameter
NameDescription
unknownFieldsUnknownFieldSet
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder
Overrides

mergeVisualization(ExplanationMetadata.InputMetadata.Visualization value)

public ExplanationMetadata.InputMetadata.Builder mergeVisualization(ExplanationMetadata.InputMetadata.Visualization value)

Visualization configurations for image explanation.

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

Parameter
NameDescription
valueExplanationMetadata.InputMetadata.Visualization
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

removeEncodedBaselines(int index)

public ExplanationMetadata.InputMetadata.Builder removeEncodedBaselines(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;

Parameter
NameDescription
indexint
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

removeInputBaselines(int index)

public ExplanationMetadata.InputMetadata.Builder removeInputBaselines(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.

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;

Parameter
NameDescription
indexint
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

setDenseShapeTensorName(String value)

public ExplanationMetadata.InputMetadata.Builder setDenseShapeTensorName(String value)

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;

Parameter
NameDescription
valueString

The denseShapeTensorName to set.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

setDenseShapeTensorNameBytes(ByteString value)

public ExplanationMetadata.InputMetadata.Builder setDenseShapeTensorNameBytes(ByteString value)

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;

Parameter
NameDescription
valueByteString

The bytes for denseShapeTensorName to set.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

setEncodedBaselines(int index, Value value)

public ExplanationMetadata.InputMetadata.Builder setEncodedBaselines(int index, Value value)

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;

Parameters
NameDescription
indexint
valueValue
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

setEncodedBaselines(int index, Value.Builder builderForValue)

public ExplanationMetadata.InputMetadata.Builder setEncodedBaselines(int index, Value.Builder builderForValue)

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;

Parameters
NameDescription
indexint
builderForValueBuilder
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

setEncodedTensorName(String value)

public ExplanationMetadata.InputMetadata.Builder setEncodedTensorName(String value)

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;

Parameter
NameDescription
valueString

The encodedTensorName to set.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

setEncodedTensorNameBytes(ByteString value)

public ExplanationMetadata.InputMetadata.Builder setEncodedTensorNameBytes(ByteString value)

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;

Parameter
NameDescription
valueByteString

The bytes for encodedTensorName to set.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

setEncoding(ExplanationMetadata.InputMetadata.Encoding value)

public ExplanationMetadata.InputMetadata.Builder setEncoding(ExplanationMetadata.InputMetadata.Encoding value)

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

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

Parameter
NameDescription
valueExplanationMetadata.InputMetadata.Encoding

The encoding to set.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

setEncodingValue(int value)

public ExplanationMetadata.InputMetadata.Builder setEncodingValue(int value)

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

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

Parameter
NameDescription
valueint

The enum numeric value on the wire for encoding to set.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

setFeatureValueDomain(ExplanationMetadata.InputMetadata.FeatureValueDomain value)

public ExplanationMetadata.InputMetadata.Builder setFeatureValueDomain(ExplanationMetadata.InputMetadata.FeatureValueDomain value)

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;

Parameter
NameDescription
valueExplanationMetadata.InputMetadata.FeatureValueDomain
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

setFeatureValueDomain(ExplanationMetadata.InputMetadata.FeatureValueDomain.Builder builderForValue)

public ExplanationMetadata.InputMetadata.Builder setFeatureValueDomain(ExplanationMetadata.InputMetadata.FeatureValueDomain.Builder builderForValue)

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;

Parameter
NameDescription
builderForValueExplanationMetadata.InputMetadata.FeatureValueDomain.Builder
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

setField(Descriptors.FieldDescriptor field, Object value)

public ExplanationMetadata.InputMetadata.Builder setField(Descriptors.FieldDescriptor field, Object value)
Parameters
NameDescription
fieldFieldDescriptor
valueObject
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder
Overrides

setGroupName(String value)

public ExplanationMetadata.InputMetadata.Builder setGroupName(String value)

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;

Parameter
NameDescription
valueString

The groupName to set.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

setGroupNameBytes(ByteString value)

public ExplanationMetadata.InputMetadata.Builder setGroupNameBytes(ByteString value)

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;

Parameter
NameDescription
valueByteString

The bytes for groupName to set.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

setIndexFeatureMapping(int index, String value)

public ExplanationMetadata.InputMetadata.Builder setIndexFeatureMapping(int index, String value)

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;

Parameters
NameDescription
indexint

The index to set the value at.

valueString

The indexFeatureMapping to set.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

setIndicesTensorName(String value)

public ExplanationMetadata.InputMetadata.Builder setIndicesTensorName(String value)

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;

Parameter
NameDescription
valueString

The indicesTensorName to set.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

setIndicesTensorNameBytes(ByteString value)

public ExplanationMetadata.InputMetadata.Builder setIndicesTensorNameBytes(ByteString value)

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;

Parameter
NameDescription
valueByteString

The bytes for indicesTensorName to set.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

setInputBaselines(int index, Value value)

public ExplanationMetadata.InputMetadata.Builder setInputBaselines(int index, Value value)

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;

Parameters
NameDescription
indexint
valueValue
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

setInputBaselines(int index, Value.Builder builderForValue)

public ExplanationMetadata.InputMetadata.Builder setInputBaselines(int index, Value.Builder builderForValue)

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;

Parameters
NameDescription
indexint
builderForValueBuilder
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

setInputTensorName(String value)

public ExplanationMetadata.InputMetadata.Builder setInputTensorName(String value)

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;

Parameter
NameDescription
valueString

The inputTensorName to set.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

setInputTensorNameBytes(ByteString value)

public ExplanationMetadata.InputMetadata.Builder setInputTensorNameBytes(ByteString value)

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;

Parameter
NameDescription
valueByteString

The bytes for inputTensorName to set.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

setModality(String value)

public ExplanationMetadata.InputMetadata.Builder setModality(String value)

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

string modality = 4;

Parameter
NameDescription
valueString

The modality to set.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

setModalityBytes(ByteString value)

public ExplanationMetadata.InputMetadata.Builder setModalityBytes(ByteString value)

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

string modality = 4;

Parameter
NameDescription
valueByteString

The bytes for modality to set.

Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

This builder for chaining.

setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)

public ExplanationMetadata.InputMetadata.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Parameters
NameDescription
fieldFieldDescriptor
indexint
valueObject
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder
Overrides

setUnknownFields(UnknownFieldSet unknownFields)

public final ExplanationMetadata.InputMetadata.Builder setUnknownFields(UnknownFieldSet unknownFields)
Parameter
NameDescription
unknownFieldsUnknownFieldSet
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder
Overrides

setVisualization(ExplanationMetadata.InputMetadata.Visualization value)

public ExplanationMetadata.InputMetadata.Builder setVisualization(ExplanationMetadata.InputMetadata.Visualization value)

Visualization configurations for image explanation.

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

Parameter
NameDescription
valueExplanationMetadata.InputMetadata.Visualization
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder

setVisualization(ExplanationMetadata.InputMetadata.Visualization.Builder builderForValue)

public ExplanationMetadata.InputMetadata.Builder setVisualization(ExplanationMetadata.InputMetadata.Visualization.Builder builderForValue)

Visualization configurations for image explanation.

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

Parameter
NameDescription
builderForValueExplanationMetadata.InputMetadata.Visualization.Builder
Returns
TypeDescription
ExplanationMetadata.InputMetadata.Builder