Interface ExplanationMetadata.OutputMetadataOrBuilder (3.41.0)

public static interface ExplanationMetadata.OutputMetadataOrBuilder extends MessageOrBuilder

Implements

MessageOrBuilder

Methods

getDisplayNameMappingCase()

public abstract ExplanationMetadata.OutputMetadata.DisplayNameMappingCase getDisplayNameMappingCase()
Returns
TypeDescription
ExplanationMetadata.OutputMetadata.DisplayNameMappingCase

getDisplayNameMappingKey()

public abstract String getDisplayNameMappingKey()

Specify a field name in the prediction to look for the display name.

Use this if the prediction contains the display names for the outputs.

The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.

string display_name_mapping_key = 2;

Returns
TypeDescription
String

The displayNameMappingKey.

getDisplayNameMappingKeyBytes()

public abstract ByteString getDisplayNameMappingKeyBytes()

Specify a field name in the prediction to look for the display name.

Use this if the prediction contains the display names for the outputs.

The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.

string display_name_mapping_key = 2;

Returns
TypeDescription
ByteString

The bytes for displayNameMappingKey.

getIndexDisplayNameMapping()

public abstract Value getIndexDisplayNameMapping()

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.

.google.protobuf.Value index_display_name_mapping = 1;

Returns
TypeDescription
Value

The indexDisplayNameMapping.

getIndexDisplayNameMappingOrBuilder()

public abstract ValueOrBuilder getIndexDisplayNameMappingOrBuilder()

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.

.google.protobuf.Value index_display_name_mapping = 1;

Returns
TypeDescription
ValueOrBuilder

getOutputTensorName()

public abstract String getOutputTensorName()

Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.

string output_tensor_name = 3;

Returns
TypeDescription
String

The outputTensorName.

getOutputTensorNameBytes()

public abstract ByteString getOutputTensorNameBytes()

Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.

string output_tensor_name = 3;

Returns
TypeDescription
ByteString

The bytes for outputTensorName.

hasDisplayNameMappingKey()

public abstract boolean hasDisplayNameMappingKey()

Specify a field name in the prediction to look for the display name.

Use this if the prediction contains the display names for the outputs.

The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.

string display_name_mapping_key = 2;

Returns
TypeDescription
boolean

Whether the displayNameMappingKey field is set.

hasIndexDisplayNameMapping()

public abstract boolean hasIndexDisplayNameMapping()

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.

.google.protobuf.Value index_display_name_mapping = 1;

Returns
TypeDescription
boolean

Whether the indexDisplayNameMapping field is set.