public static final class ExplanationMetadata.InputMetadata extends GeneratedMessageV3 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.v1beta1.ExplanationMetadata.InputMetadata
Static Fields
public static final int DENSE_SHAPE_TENSOR_NAME_FIELD_NUMBER
Field Value
public static final int ENCODED_BASELINES_FIELD_NUMBER
Field Value
public static final int ENCODED_TENSOR_NAME_FIELD_NUMBER
Field Value
public static final int ENCODING_FIELD_NUMBER
Field Value
FEATURE_VALUE_DOMAIN_FIELD_NUMBER
public static final int FEATURE_VALUE_DOMAIN_FIELD_NUMBER
Field Value
public static final int GROUP_NAME_FIELD_NUMBER
Field Value
public static final int INDEX_FEATURE_MAPPING_FIELD_NUMBER
Field Value
public static final int INDICES_TENSOR_NAME_FIELD_NUMBER
Field Value
public static final int INPUT_BASELINES_FIELD_NUMBER
Field Value
public static final int INPUT_TENSOR_NAME_FIELD_NUMBER
Field Value
public static final int MODALITY_FIELD_NUMBER
Field Value
public static final int VISUALIZATION_FIELD_NUMBER
Field Value
Static Methods
public static ExplanationMetadata.InputMetadata getDefaultInstance()
Returns
public static final Descriptors.Descriptor getDescriptor()
Returns
public static ExplanationMetadata.InputMetadata.Builder newBuilder()
Returns
public static ExplanationMetadata.InputMetadata.Builder newBuilder(ExplanationMetadata.InputMetadata prototype)
Parameter
Returns
public static ExplanationMetadata.InputMetadata parseDelimitedFrom(InputStream input)
Parameter
Returns
Exceptions
public static ExplanationMetadata.InputMetadata parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationMetadata.InputMetadata parseFrom(byte[] data)
Parameter
| Name | Description |
data | byte[]
|
Returns
Exceptions
public static ExplanationMetadata.InputMetadata parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationMetadata.InputMetadata parseFrom(ByteString data)
Parameter
Returns
Exceptions
public static ExplanationMetadata.InputMetadata parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationMetadata.InputMetadata parseFrom(CodedInputStream input)
Parameter
Returns
Exceptions
public static ExplanationMetadata.InputMetadata parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationMetadata.InputMetadata parseFrom(InputStream input)
Parameter
Returns
Exceptions
public static ExplanationMetadata.InputMetadata parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationMetadata.InputMetadata parseFrom(ByteBuffer data)
Parameter
Returns
Exceptions
public static ExplanationMetadata.InputMetadata parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static Parser<ExplanationMetadata.InputMetadata> parser()
Returns
Methods
public boolean equals(Object obj)
Parameter
Returns
Overrides
public ExplanationMetadata.InputMetadata getDefaultInstanceForType()
Returns
public String getDenseShapeTensorName()
Returns
| Type | Description |
String | The denseShapeTensorName.
|
public ByteString getDenseShapeTensorNameBytes()
Returns
| Type | Description |
ByteString | The bytes for denseShapeTensorName.
|
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;
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;
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;
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;
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;
| Type | Description |
List<? extends com.google.protobuf.ValueOrBuilder> | |
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;
| Type | Description |
String | The encodedTensorName.
|
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;
| Type | Description |
ByteString | The bytes for encodedTensorName.
|
public ExplanationMetadata.InputMetadata.Encoding getEncoding()
Defines how the feature is encoded into the input tensor. Defaults to
IDENTITY.
.google.cloud.aiplatform.v1beta1.ExplanationMetadata.InputMetadata.Encoding encoding = 3;
public int getEncodingValue()
Defines how the feature is encoded into the input tensor. Defaults to
IDENTITY.
.google.cloud.aiplatform.v1beta1.ExplanationMetadata.InputMetadata.Encoding encoding = 3;
| Type | Description |
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.v1beta1.ExplanationMetadata.InputMetadata.FeatureValueDomain feature_value_domain = 5;
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.v1beta1.ExplanationMetadata.InputMetadata.FeatureValueDomain feature_value_domain = 5;
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;
| Type | Description |
String | The groupName.
|
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;
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;
| Name | Description |
index | int
The index of the element to return.
|
Returns
| Type | Description |
String | The indexFeatureMapping at the given 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;
| Name | Description |
index | int
The index of the value to return.
|
Returns
| Type | Description |
ByteString | The bytes of the indexFeatureMapping at the given index.
|
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;
| Type | Description |
int | The count of indexFeatureMapping.
|
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;
public String getIndicesTensorName()
Returns
| Type | Description |
String | The indicesTensorName.
|
public ByteString getIndicesTensorNameBytes()
Returns
| Type | Description |
ByteString | The bytes for indicesTensorName.
|
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;
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;
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;
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;
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;
| Type | Description |
List<? extends com.google.protobuf.ValueOrBuilder> | |
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;
| Type | Description |
String | The inputTensorName.
|
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;
| Type | Description |
ByteString | The bytes for inputTensorName.
|
public String getModality()
Modality of the feature. Valid values are: numeric, image. Defaults to
numeric.
string modality = 4;
| Type | Description |
String | The modality.
|
public ByteString getModalityBytes()
Modality of the feature. Valid values are: numeric, image. Defaults to
numeric.
string modality = 4;
public Parser<ExplanationMetadata.InputMetadata> getParserForType()
Returns
Overrides
public int getSerializedSize()
Returns
Overrides
public final UnknownFieldSet getUnknownFields()
Returns
Overrides
public ExplanationMetadata.InputMetadata.Visualization getVisualization()
Visualization configurations for image explanation.
.google.cloud.aiplatform.v1beta1.ExplanationMetadata.InputMetadata.Visualization visualization = 11;
public ExplanationMetadata.InputMetadata.VisualizationOrBuilder getVisualizationOrBuilder()
Visualization configurations for image explanation.
.google.cloud.aiplatform.v1beta1.ExplanationMetadata.InputMetadata.Visualization visualization = 11;
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.v1beta1.ExplanationMetadata.InputMetadata.FeatureValueDomain feature_value_domain = 5;
| Type | Description |
boolean | Whether the featureValueDomain field is set.
|
public boolean hasVisualization()
Visualization configurations for image explanation.
.google.cloud.aiplatform.v1beta1.ExplanationMetadata.InputMetadata.Visualization visualization = 11;
| Type | Description |
boolean | Whether the visualization field is set.
|
Returns
Overrides
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Overrides
public final boolean isInitialized()
Returns
Overrides
public ExplanationMetadata.InputMetadata.Builder newBuilderForType()
Returns
protected ExplanationMetadata.InputMetadata.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Parameter
Returns
Overrides
protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Parameter
Returns
Overrides
public ExplanationMetadata.InputMetadata.Builder toBuilder()
Returns
public void writeTo(CodedOutputStream output)
Parameter
Overrides
Exceptions
