public final class ExplanationMetadata extends GeneratedMessageV3 implements ExplanationMetadataOrBuilder
Metadata describing the Model's input and output for explanation.
Protobuf type google.cloud.aiplatform.v1.ExplanationMetadata
Static Fields
public static final int FEATURE_ATTRIBUTIONS_SCHEMA_URI_FIELD_NUMBER
Field Value
public static final int INPUTS_FIELD_NUMBER
Field Value
public static final int LATENT_SPACE_SOURCE_FIELD_NUMBER
Field Value
public static final int OUTPUTS_FIELD_NUMBER
Field Value
Static Methods
public static ExplanationMetadata getDefaultInstance()
Returns
public static final Descriptors.Descriptor getDescriptor()
Returns
public static ExplanationMetadata.Builder newBuilder()
Returns
public static ExplanationMetadata.Builder newBuilder(ExplanationMetadata prototype)
Parameter
Returns
public static ExplanationMetadata parseDelimitedFrom(InputStream input)
Parameter
Returns
Exceptions
public static ExplanationMetadata parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationMetadata parseFrom(byte[] data)
Parameter
| Name | Description |
data | byte[]
|
Returns
Exceptions
public static ExplanationMetadata parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationMetadata parseFrom(ByteString data)
Parameter
Returns
Exceptions
public static ExplanationMetadata parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationMetadata parseFrom(CodedInputStream input)
Parameter
Returns
Exceptions
public static ExplanationMetadata parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationMetadata parseFrom(InputStream input)
Parameter
Returns
Exceptions
public static ExplanationMetadata parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationMetadata parseFrom(ByteBuffer data)
Parameter
Returns
Exceptions
public static ExplanationMetadata parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static Parser<ExplanationMetadata> parser()
Returns
Methods
public boolean containsInputs(String key)
Required. Map from feature names to feature input metadata. Keys are the
name of the features. Values are the specification of the feature.
An empty InputMetadata is valid. It describes a text feature which has the
name specified as the key in
ExplanationMetadata.inputs.
The baseline of the empty feature is chosen by Vertex AI.
For Vertex AI-provided Tensorflow images, the key can be any friendly
name of the feature. Once specified,
featureAttributions
are keyed by this key (if not grouped with another feature).
For custom images, the key must match with the key in
instance.
map<string, .google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata> inputs = 1 [(.google.api.field_behavior) = REQUIRED];
public boolean containsOutputs(String key)
Required. Map from output names to output metadata.
For Vertex AI-provided Tensorflow images, keys can be any user defined
string that consists of any UTF-8 characters.
For custom images, keys are the name of the output field in the prediction
to be explained.
Currently only one key is allowed.
map<string, .google.cloud.aiplatform.v1.ExplanationMetadata.OutputMetadata> outputs = 2 [(.google.api.field_behavior) = REQUIRED];
public boolean equals(Object obj)
Parameter
Returns
Overrides
public ExplanationMetadata getDefaultInstanceForType()
Returns
public String getFeatureAttributionsSchemaUri()
Points to a YAML file stored on Google Cloud Storage describing the format
of the feature
attributions.
The schema is defined as an OpenAPI 3.0.2 Schema
Object.
AutoML tabular Models always have this field populated by Vertex AI.
Note: The URI given on output may be different, including the URI scheme,
than the one given on input. The output URI will point to a location where
the user only has a read access.
string feature_attributions_schema_uri = 3;
| Type | Description |
String | The featureAttributionsSchemaUri.
|
public ByteString getFeatureAttributionsSchemaUriBytes()
Points to a YAML file stored on Google Cloud Storage describing the format
of the feature
attributions.
The schema is defined as an OpenAPI 3.0.2 Schema
Object.
AutoML tabular Models always have this field populated by Vertex AI.
Note: The URI given on output may be different, including the URI scheme,
than the one given on input. The output URI will point to a location where
the user only has a read access.
string feature_attributions_schema_uri = 3;
| Type | Description |
ByteString | The bytes for featureAttributionsSchemaUri.
|
public Map<String,ExplanationMetadata.InputMetadata> getInputs()
Returns
public int getInputsCount()
Required. Map from feature names to feature input metadata. Keys are the
name of the features. Values are the specification of the feature.
An empty InputMetadata is valid. It describes a text feature which has the
name specified as the key in
ExplanationMetadata.inputs.
The baseline of the empty feature is chosen by Vertex AI.
For Vertex AI-provided Tensorflow images, the key can be any friendly
name of the feature. Once specified,
featureAttributions
are keyed by this key (if not grouped with another feature).
For custom images, the key must match with the key in
instance.
map<string, .google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata> inputs = 1 [(.google.api.field_behavior) = REQUIRED];
public Map<String,ExplanationMetadata.InputMetadata> getInputsMap()
Required. Map from feature names to feature input metadata. Keys are the
name of the features. Values are the specification of the feature.
An empty InputMetadata is valid. It describes a text feature which has the
name specified as the key in
ExplanationMetadata.inputs.
The baseline of the empty feature is chosen by Vertex AI.
For Vertex AI-provided Tensorflow images, the key can be any friendly
name of the feature. Once specified,
featureAttributions
are keyed by this key (if not grouped with another feature).
For custom images, the key must match with the key in
instance.
map<string, .google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata> inputs = 1 [(.google.api.field_behavior) = REQUIRED];
public ExplanationMetadata.InputMetadata getInputsOrDefault(String key, ExplanationMetadata.InputMetadata defaultValue)
Required. Map from feature names to feature input metadata. Keys are the
name of the features. Values are the specification of the feature.
An empty InputMetadata is valid. It describes a text feature which has the
name specified as the key in
ExplanationMetadata.inputs.
The baseline of the empty feature is chosen by Vertex AI.
For Vertex AI-provided Tensorflow images, the key can be any friendly
name of the feature. Once specified,
featureAttributions
are keyed by this key (if not grouped with another feature).
For custom images, the key must match with the key in
instance.
map<string, .google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata> inputs = 1 [(.google.api.field_behavior) = REQUIRED];
public ExplanationMetadata.InputMetadata getInputsOrThrow(String key)
Required. Map from feature names to feature input metadata. Keys are the
name of the features. Values are the specification of the feature.
An empty InputMetadata is valid. It describes a text feature which has the
name specified as the key in
ExplanationMetadata.inputs.
The baseline of the empty feature is chosen by Vertex AI.
For Vertex AI-provided Tensorflow images, the key can be any friendly
name of the feature. Once specified,
featureAttributions
are keyed by this key (if not grouped with another feature).
For custom images, the key must match with the key in
instance.
map<string, .google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata> inputs = 1 [(.google.api.field_behavior) = REQUIRED];
public String getLatentSpaceSource()
Name of the source to generate embeddings for example based explanations.
string latent_space_source = 5;
| Type | Description |
String | The latentSpaceSource.
|
public ByteString getLatentSpaceSourceBytes()
Name of the source to generate embeddings for example based explanations.
string latent_space_source = 5;
| Type | Description |
ByteString | The bytes for latentSpaceSource.
|
public Map<String,ExplanationMetadata.OutputMetadata> getOutputs()
Returns
public int getOutputsCount()
Required. Map from output names to output metadata.
For Vertex AI-provided Tensorflow images, keys can be any user defined
string that consists of any UTF-8 characters.
For custom images, keys are the name of the output field in the prediction
to be explained.
Currently only one key is allowed.
map<string, .google.cloud.aiplatform.v1.ExplanationMetadata.OutputMetadata> outputs = 2 [(.google.api.field_behavior) = REQUIRED];
public Map<String,ExplanationMetadata.OutputMetadata> getOutputsMap()
Required. Map from output names to output metadata.
For Vertex AI-provided Tensorflow images, keys can be any user defined
string that consists of any UTF-8 characters.
For custom images, keys are the name of the output field in the prediction
to be explained.
Currently only one key is allowed.
map<string, .google.cloud.aiplatform.v1.ExplanationMetadata.OutputMetadata> outputs = 2 [(.google.api.field_behavior) = REQUIRED];
public ExplanationMetadata.OutputMetadata getOutputsOrDefault(String key, ExplanationMetadata.OutputMetadata defaultValue)
Required. Map from output names to output metadata.
For Vertex AI-provided Tensorflow images, keys can be any user defined
string that consists of any UTF-8 characters.
For custom images, keys are the name of the output field in the prediction
to be explained.
Currently only one key is allowed.
map<string, .google.cloud.aiplatform.v1.ExplanationMetadata.OutputMetadata> outputs = 2 [(.google.api.field_behavior) = REQUIRED];
public ExplanationMetadata.OutputMetadata getOutputsOrThrow(String key)
Required. Map from output names to output metadata.
For Vertex AI-provided Tensorflow images, keys can be any user defined
string that consists of any UTF-8 characters.
For custom images, keys are the name of the output field in the prediction
to be explained.
Currently only one key is allowed.
map<string, .google.cloud.aiplatform.v1.ExplanationMetadata.OutputMetadata> outputs = 2 [(.google.api.field_behavior) = REQUIRED];
public Parser<ExplanationMetadata> getParserForType()
Returns
Overrides
public int getSerializedSize()
Returns
Overrides
public final UnknownFieldSet getUnknownFields()
Returns
Overrides
Returns
Overrides
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Overrides
protected MapField internalGetMapField(int number)
Parameter
Returns
Overrides
public final boolean isInitialized()
Returns
Overrides
public ExplanationMetadata.Builder newBuilderForType()
Returns
protected ExplanationMetadata.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Parameter
Returns
Overrides
protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Parameter
Returns
Overrides
public ExplanationMetadata.Builder toBuilder()
Returns
public void writeTo(CodedOutputStream output)
Parameter
Overrides
Exceptions
