Interface ExplanationMetadata.OutputMetadataOrBuilder (0.4.0)
Stay organized with collections
Save and categorize content based on your preferences.
publicstaticinterface ExplanationMetadata.OutputMetadataOrBuilderextendsMessageOrBuilderImplements
MessageOrBuilderMethods
getDisplayNameMappingCase()
publicabstractExplanationMetadata.OutputMetadata.DisplayNameMappingCasegetDisplayNameMappingCase()| Returns | |
|---|---|
| Type | Description |
ExplanationMetadata.OutputMetadata.DisplayNameMappingCase |
|
getDisplayNameMappingKey()
publicabstractStringgetDisplayNameMappingKey()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 | |
|---|---|
| Type | Description |
String |
The displayNameMappingKey. |
getDisplayNameMappingKeyBytes()
publicabstractByteStringgetDisplayNameMappingKeyBytes()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 | |
|---|---|
| Type | Description |
ByteString |
The bytes for displayNameMappingKey. |
getIndexDisplayNameMapping()
publicabstractValuegetIndexDisplayNameMapping()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 | |
|---|---|
| Type | Description |
Value |
The indexDisplayNameMapping. |
getIndexDisplayNameMappingOrBuilder()
publicabstractValueOrBuildergetIndexDisplayNameMappingOrBuilder()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 | |
|---|---|
| Type | Description |
ValueOrBuilder |
|
getOutputTensorName()
publicabstractStringgetOutputTensorName()Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.
string output_tensor_name = 3;
| Returns | |
|---|---|
| Type | Description |
String |
The outputTensorName. |
getOutputTensorNameBytes()
publicabstractByteStringgetOutputTensorNameBytes()Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.
string output_tensor_name = 3;
| Returns | |
|---|---|
| Type | Description |
ByteString |
The bytes for outputTensorName. |
hasDisplayNameMappingKey()
publicabstractbooleanhasDisplayNameMappingKey()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 | |
|---|---|
| Type | Description |
boolean |
Whether the displayNameMappingKey field is set. |
hasIndexDisplayNameMapping()
publicabstractbooleanhasIndexDisplayNameMapping()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 | |
|---|---|
| Type | Description |
boolean |
Whether the indexDisplayNameMapping field is set. |