public static final class ExplanationMetadata.OutputMetadata extends GeneratedMessageV3 implements ExplanationMetadata.OutputMetadataOrBuilder
Metadata of the prediction output to be explained.
Protobuf type google.cloud.aiplatform.v1.ExplanationMetadata.OutputMetadata
Static Fields
public static final int DISPLAY_NAME_MAPPING_KEY_FIELD_NUMBER
Field Value
public static final int INDEX_DISPLAY_NAME_MAPPING_FIELD_NUMBER
Field Value
public static final int OUTPUT_TENSOR_NAME_FIELD_NUMBER
Field Value
Static Methods
public static ExplanationMetadata.OutputMetadata getDefaultInstance()
Returns
public static final Descriptors.Descriptor getDescriptor()
Returns
public static ExplanationMetadata.OutputMetadata.Builder newBuilder()
Returns
public static ExplanationMetadata.OutputMetadata.Builder newBuilder(ExplanationMetadata.OutputMetadata prototype)
Parameter
Returns
public static ExplanationMetadata.OutputMetadata parseDelimitedFrom(InputStream input)
Parameter
Returns
Exceptions
public static ExplanationMetadata.OutputMetadata parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationMetadata.OutputMetadata parseFrom(byte[] data)
Parameter
| Name | Description |
data | byte[]
|
Returns
Exceptions
public static ExplanationMetadata.OutputMetadata parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationMetadata.OutputMetadata parseFrom(ByteString data)
Parameter
Returns
Exceptions
public static ExplanationMetadata.OutputMetadata parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationMetadata.OutputMetadata parseFrom(CodedInputStream input)
Parameter
Returns
Exceptions
public static ExplanationMetadata.OutputMetadata parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationMetadata.OutputMetadata parseFrom(InputStream input)
Parameter
Returns
Exceptions
public static ExplanationMetadata.OutputMetadata parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static ExplanationMetadata.OutputMetadata parseFrom(ByteBuffer data)
Parameter
Returns
Exceptions
public static ExplanationMetadata.OutputMetadata parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static Parser<ExplanationMetadata.OutputMetadata> parser()
Returns
Methods
public boolean equals(Object obj)
Parameter
Returns
Overrides
public ExplanationMetadata.OutputMetadata getDefaultInstanceForType()
Returns
public ExplanationMetadata.OutputMetadata.DisplayNameMappingCase getDisplayNameMappingCase()
Returns
public 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;
| Type | Description |
String | The displayNameMappingKey.
|
public 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;
| Type | Description |
ByteString | The bytes for displayNameMappingKey.
|
public 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;
| Type | Description |
Value | The indexDisplayNameMapping.
|
public 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;
public String getOutputTensorName()
Name of the output tensor. Required and is only applicable to Vertex
AI provided images for Tensorflow.
string output_tensor_name = 3;
| Type | Description |
String | The outputTensorName.
|
public ByteString getOutputTensorNameBytes()
Name of the output tensor. Required and is only applicable to Vertex
AI provided images for Tensorflow.
string output_tensor_name = 3;
| Type | Description |
ByteString | The bytes for outputTensorName.
|
public Parser<ExplanationMetadata.OutputMetadata> getParserForType()
Returns
Overrides
public int getSerializedSize()
Returns
Overrides
public final UnknownFieldSet getUnknownFields()
Returns
Overrides
public 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;
| Type | Description |
boolean | Whether the displayNameMappingKey field is set.
|
public 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;
| Type | Description |
boolean | Whether the indexDisplayNameMapping field is set.
|
Returns
Overrides
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Overrides
public final boolean isInitialized()
Returns
Overrides
public ExplanationMetadata.OutputMetadata.Builder newBuilderForType()
Returns
protected ExplanationMetadata.OutputMetadata.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Parameter
Returns
Overrides
protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Parameter
Returns
Overrides
public ExplanationMetadata.OutputMetadata.Builder toBuilder()
Returns
public void writeTo(CodedOutputStream output)
Parameter
Overrides
Exceptions
