Interface ExplanationMetadataOrBuilder (1.40.0)

publicinterface ExplanationMetadataOrBuilderextendsMessageOrBuilder

Implements

MessageOrBuilder

Methods

containsInputs(String key)

publicabstractbooleancontainsInputs(Stringkey)

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.vertexai.v1.ExplanationMetadata.InputMetadata> inputs = 1 [(.google.api.field_behavior) = REQUIRED];

Parameter
Name Description
key String
Returns
Type Description
boolean

containsOutputs(String key)

publicabstractbooleancontainsOutputs(Stringkey)

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.vertexai.v1.ExplanationMetadata.OutputMetadata> outputs = 2 [(.google.api.field_behavior) = REQUIRED];

Parameter
Name Description
key String
Returns
Type Description
boolean

getFeatureAttributionsSchemaUri()

publicabstractStringgetFeatureAttributionsSchemaUri()

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;

Returns
Type Description
String

The featureAttributionsSchemaUri.

getFeatureAttributionsSchemaUriBytes()

publicabstractByteStringgetFeatureAttributionsSchemaUriBytes()

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;

Returns
Type Description
ByteString

The bytes for featureAttributionsSchemaUri.

getInputs() (deprecated)

publicabstractMap<String,ExplanationMetadata.InputMetadata>getInputs()

Use #getInputsMap() instead.

Returns
Type Description
Map<String,InputMetadata>

getInputsCount()

publicabstractintgetInputsCount()

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.vertexai.v1.ExplanationMetadata.InputMetadata> inputs = 1 [(.google.api.field_behavior) = REQUIRED];

Returns
Type Description
int

getInputsMap()

publicabstractMap<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.vertexai.v1.ExplanationMetadata.InputMetadata> inputs = 1 [(.google.api.field_behavior) = REQUIRED];

Returns
Type Description
Map<String,InputMetadata>

getInputsOrDefault(String key, ExplanationMetadata.InputMetadata defaultValue)

publicabstractExplanationMetadata.InputMetadatagetInputsOrDefault(Stringkey,ExplanationMetadata.InputMetadatadefaultValue)

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.vertexai.v1.ExplanationMetadata.InputMetadata> inputs = 1 [(.google.api.field_behavior) = REQUIRED];

Parameters
Name Description
key String
defaultValue ExplanationMetadata.InputMetadata
Returns
Type Description
ExplanationMetadata.InputMetadata

getInputsOrThrow(String key)

publicabstractExplanationMetadata.InputMetadatagetInputsOrThrow(Stringkey)

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.vertexai.v1.ExplanationMetadata.InputMetadata> inputs = 1 [(.google.api.field_behavior) = REQUIRED];

Parameter
Name Description
key String
Returns
Type Description
ExplanationMetadata.InputMetadata

getLatentSpaceSource()

publicabstractStringgetLatentSpaceSource()

Name of the source to generate embeddings for example based explanations.

string latent_space_source = 5;

Returns
Type Description
String

The latentSpaceSource.

getLatentSpaceSourceBytes()

publicabstractByteStringgetLatentSpaceSourceBytes()

Name of the source to generate embeddings for example based explanations.

string latent_space_source = 5;

Returns
Type Description
ByteString

The bytes for latentSpaceSource.

getOutputs() (deprecated)

publicabstractMap<String,ExplanationMetadata.OutputMetadata>getOutputs()

Use #getOutputsMap() instead.

Returns
Type Description
Map<String,OutputMetadata>

getOutputsCount()

publicabstractintgetOutputsCount()

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.vertexai.v1.ExplanationMetadata.OutputMetadata> outputs = 2 [(.google.api.field_behavior) = REQUIRED];

Returns
Type Description
int

getOutputsMap()

publicabstractMap<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.vertexai.v1.ExplanationMetadata.OutputMetadata> outputs = 2 [(.google.api.field_behavior) = REQUIRED];

Returns
Type Description
Map<String,OutputMetadata>

getOutputsOrDefault(String key, ExplanationMetadata.OutputMetadata defaultValue)

publicabstractExplanationMetadata.OutputMetadatagetOutputsOrDefault(Stringkey,ExplanationMetadata.OutputMetadatadefaultValue)

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.vertexai.v1.ExplanationMetadata.OutputMetadata> outputs = 2 [(.google.api.field_behavior) = REQUIRED];

Parameters
Name Description
key String
defaultValue ExplanationMetadata.OutputMetadata
Returns
Type Description
ExplanationMetadata.OutputMetadata

getOutputsOrThrow(String key)

publicabstractExplanationMetadata.OutputMetadatagetOutputsOrThrow(Stringkey)

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.vertexai.v1.ExplanationMetadata.OutputMetadata> outputs = 2 [(.google.api.field_behavior) = REQUIRED];

Parameter
Name Description
key String
Returns
Type Description
ExplanationMetadata.OutputMetadata

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025年11月19日 UTC.