Interface ExplanationMetadataOrBuilder (3.8.0) 

public interface ExplanationMetadataOrBuilder extends MessageOrBuilder

Implements

MessageOrBuilder

Methods

containsInputs(String key)

public abstract 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];

Parameter
NameDescription
keyString
Returns
TypeDescription
boolean

containsOutputs(String key)

public abstract 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];

Parameter
NameDescription
keyString
Returns
TypeDescription
boolean

getFeatureAttributionsSchemaUri()

public abstract 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;

Returns
TypeDescription
String

The featureAttributionsSchemaUri.

getFeatureAttributionsSchemaUriBytes()

public abstract 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;

Returns
TypeDescription
ByteString

The bytes for featureAttributionsSchemaUri.

getInputs()

public abstract Map<String,ExplanationMetadata.InputMetadata> getInputs()

Use #getInputsMap() instead.

Returns
TypeDescription
Map<String,InputMetadata>

getInputsCount()

public abstract 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];

Returns
TypeDescription
int

getInputsMap()

public abstract 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];

Returns
TypeDescription
Map<String,InputMetadata>

getInputsOrDefault(String key, ExplanationMetadata.InputMetadata defaultValue)

public abstract 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];

Parameters
NameDescription
keyString
defaultValueExplanationMetadata.InputMetadata
Returns
TypeDescription
ExplanationMetadata.InputMetadata

getInputsOrThrow(String key)

public abstract 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];

Parameter
NameDescription
keyString
Returns
TypeDescription
ExplanationMetadata.InputMetadata

getLatentSpaceSource()

public abstract String getLatentSpaceSource()

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

string latent_space_source = 5;

Returns
TypeDescription
String

The latentSpaceSource.

getLatentSpaceSourceBytes()

public abstract ByteString getLatentSpaceSourceBytes()

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

string latent_space_source = 5;

Returns
TypeDescription
ByteString

The bytes for latentSpaceSource.

getOutputs()

public abstract Map<String,ExplanationMetadata.OutputMetadata> getOutputs()

Use #getOutputsMap() instead.

Returns
TypeDescription
Map<String,OutputMetadata>

getOutputsCount()

public abstract 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];

Returns
TypeDescription
int

getOutputsMap()

public abstract 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];

Returns
TypeDescription
Map<String,OutputMetadata>

getOutputsOrDefault(String key, ExplanationMetadata.OutputMetadata defaultValue)

public abstract 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];

Parameters
NameDescription
keyString
defaultValueExplanationMetadata.OutputMetadata
Returns
TypeDescription
ExplanationMetadata.OutputMetadata

getOutputsOrThrow(String key)

public abstract 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];

Parameter
NameDescription
keyString
Returns
TypeDescription
ExplanationMetadata.OutputMetadata