Class ExplanationMetadata (1.2.0)

ExplanationMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)

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

Attributes

NameDescription
inputs Sequence[google.cloud.aiplatform_v1beta1.types.ExplanationMetadata.InputsEntry]
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.
outputs Sequence[google.cloud.aiplatform_v1beta1.types.ExplanationMetadata.OutputsEntry]
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.
feature_attributions_schema_uri str
Points to a YAML file stored on Google Cloud Storage describing the format of the [feature attributions][google.cloud.aiplatform.v1beta1.Attribution.feature_attributions]. The schema is defined as an OpenAPI 3.0.2 `Schema Object

Inheritance

builtins.object > proto.message.Message > ExplanationMetadata

Classes

InputMetadata

InputMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)

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.

InputsEntry

InputsEntry(mapping=None, *, ignore_unknown_fields=False, **kwargs)

The abstract base class for a message.

Parameters
NameDescription
kwargs dict

Keys and values corresponding to the fields of the message.

mapping Union[dict, `.Message`]

A dictionary or message to be used to determine the values for this message.

ignore_unknown_fields Optional(bool)

If True, do not raise errors for unknown fields. Only applied if mapping is a mapping type or there are keyword parameters.

OutputMetadata

OutputMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Metadata of the prediction output to be explained. .. attribute:: index_display_name_mapping

Static mapping between the index and display name.

Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values.

The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The Attribution.output_display_name is populated by locating in the mapping with Attribution.output_index.

:type: google.protobuf.struct_pb2.Value

OutputsEntry

OutputsEntry(mapping=None, *, ignore_unknown_fields=False, **kwargs)

The abstract base class for a message.

Parameters
NameDescription
kwargs dict

Keys and values corresponding to the fields of the message.

mapping Union[dict, `.Message`]

A dictionary or message to be used to determine the values for this message.

ignore_unknown_fields Optional(bool)

If True, do not raise errors for unknown fields. Only applied if mapping is a mapping type or there are keyword parameters.