publicstaticfinalclass ExplanationMetadata.OutputMetadataextendsGeneratedMessageV3implementsExplanationMetadata.OutputMetadataOrBuilder
Metadata of the prediction output to be explained.
Protobuf type google.cloud.vertexai.v1.ExplanationMetadata.OutputMetadata
Inherited Members
com.google.protobuf.GeneratedMessageV3.<ListT>makeMutableCopy(ListT)
com.google.protobuf.GeneratedMessageV3.<ListT>makeMutableCopy(ListT,int)
com.google.protobuf.GeneratedMessageV3.<T>emptyList(java.lang.Class<T>)
com.google.protobuf.GeneratedMessageV3.internalGetMapFieldReflection(int)
Static Fields
publicstaticfinalintDISPLAY_NAME_MAPPING_KEY_FIELD_NUMBER
| Field Value |
| Type |
Description |
int |
publicstaticfinalintINDEX_DISPLAY_NAME_MAPPING_FIELD_NUMBER
| Field Value |
| Type |
Description |
int |
publicstaticfinalintOUTPUT_TENSOR_NAME_FIELD_NUMBER
| Field Value |
| Type |
Description |
int |
Static Methods
publicstaticExplanationMetadata.OutputMetadatagetDefaultInstance()
publicstaticfinalDescriptors.DescriptorgetDescriptor()
publicstaticExplanationMetadata.OutputMetadata.BuildernewBuilder()
publicstaticExplanationMetadata.OutputMetadata.BuildernewBuilder(ExplanationMetadata.OutputMetadataprototype)
publicstaticExplanationMetadata.OutputMetadataparseDelimitedFrom(InputStreaminput)
publicstaticExplanationMetadata.OutputMetadataparseDelimitedFrom(InputStreaminput,ExtensionRegistryLiteextensionRegistry)
publicstaticExplanationMetadata.OutputMetadataparseFrom(byte[]data)
| Parameter |
| Name |
Description |
data |
byte[]
|
publicstaticExplanationMetadata.OutputMetadataparseFrom(byte[]data,ExtensionRegistryLiteextensionRegistry)
publicstaticExplanationMetadata.OutputMetadataparseFrom(ByteStringdata)
publicstaticExplanationMetadata.OutputMetadataparseFrom(ByteStringdata,ExtensionRegistryLiteextensionRegistry)
publicstaticExplanationMetadata.OutputMetadataparseFrom(CodedInputStreaminput)
publicstaticExplanationMetadata.OutputMetadataparseFrom(CodedInputStreaminput,ExtensionRegistryLiteextensionRegistry)
publicstaticExplanationMetadata.OutputMetadataparseFrom(InputStreaminput)
publicstaticExplanationMetadata.OutputMetadataparseFrom(InputStreaminput,ExtensionRegistryLiteextensionRegistry)
publicstaticExplanationMetadata.OutputMetadataparseFrom(ByteBufferdata)
publicstaticExplanationMetadata.OutputMetadataparseFrom(ByteBufferdata,ExtensionRegistryLiteextensionRegistry)
publicstaticParser<ExplanationMetadata.OutputMetadata>parser()
Methods
publicbooleanequals(Objectobj)
| Parameter |
| Name |
Description |
obj |
Object
|
Overrides
publicExplanationMetadata.OutputMetadatagetDefaultInstanceForType()
publicExplanationMetadata.OutputMetadata.DisplayNameMappingCasegetDisplayNameMappingCase()
publicStringgetDisplayNameMappingKey()
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.
|
publicByteStringgetDisplayNameMappingKeyBytes()
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.
|
publicValuegetIndexDisplayNameMapping()
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.
|
publicValueOrBuildergetIndexDisplayNameMappingOrBuilder()
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;
publicStringgetOutputTensorName()
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.
|
publicByteStringgetOutputTensorNameBytes()
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.
|
publicParser<ExplanationMetadata.OutputMetadata>getParserForType()
Overrides
publicintgetSerializedSize()
| Returns |
| Type |
Description |
int |
Overrides
publicbooleanhasDisplayNameMappingKey()
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.
|
publicbooleanhasIndexDisplayNameMapping()
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.
|
| Returns |
| Type |
Description |
int |
Overrides
protectedGeneratedMessageV3.FieldAccessorTableinternalGetFieldAccessorTable()
Overrides
publicfinalbooleanisInitialized()
Overrides
publicExplanationMetadata.OutputMetadata.BuildernewBuilderForType()
protectedExplanationMetadata.OutputMetadata.BuildernewBuilderForType(GeneratedMessageV3.BuilderParentparent)
Overrides
protectedObjectnewInstance(GeneratedMessageV3.UnusedPrivateParameterunused)
| Returns |
| Type |
Description |
Object |
Overrides
publicExplanationMetadata.OutputMetadata.BuildertoBuilder()
publicvoidwriteTo(CodedOutputStreamoutput)
Overrides