Vertex AI V1 API - Class Google::Cloud::AIPlatform::V1::ExplanationMetadata (v0.9.1)

Reference documentation and code samples for the Vertex AI V1 API class Google::Cloud::AIPlatform::V1::ExplanationMetadata.

Metadata describing the Model's input and output for explanation.

Inherits

  • Object

Extended By

  • Google::Protobuf::MessageExts::ClassMethods

Includes

  • Google::Protobuf::MessageExts

Methods

#feature_attributions_schema_uri

def feature_attributions_schema_uri() -> ::String
Returns
  • (::String) — 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.

#feature_attributions_schema_uri=

def feature_attributions_schema_uri=(value) -> ::String
Parameter
  • value (::String) — 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.
Returns
  • (::String) — 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.

#inputs

def inputs() -> ::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata}
Returns
  • (::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata}) — 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.

#inputs=

def inputs=(value) -> ::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata}
Parameter
  • value (::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata}) — 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.

Returns
  • (::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::InputMetadata}) — 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.

#latent_space_source

def latent_space_source() -> ::String
Returns
  • (::String) — Name of the source to generate embeddings for example based explanations.

#latent_space_source=

def latent_space_source=(value) -> ::String
Parameter
  • value (::String) — Name of the source to generate embeddings for example based explanations.
Returns
  • (::String) — Name of the source to generate embeddings for example based explanations.

#outputs

def outputs() -> ::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::OutputMetadata}
Returns
  • (::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::OutputMetadata}) — 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.

#outputs=

def outputs=(value) -> ::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::OutputMetadata}
Parameter
  • value (::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::OutputMetadata}) — 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.

Returns
  • (::Google::Protobuf::Map{::String => ::Google::Cloud::AIPlatform::V1::ExplanationMetadata::OutputMetadata}) — 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.