- 3.54.0 (latest)
- 3.53.0
- 3.52.0
- 3.50.0
- 3.49.0
- 3.48.0
- 3.47.0
- 3.46.0
- 3.45.0
- 3.44.0
- 3.43.0
- 3.42.0
- 3.41.0
- 3.40.0
- 3.38.0
- 3.37.0
- 3.36.0
- 3.35.0
- 3.34.0
- 3.33.0
- 3.32.0
- 3.31.0
- 3.30.0
- 3.29.0
- 3.28.0
- 3.25.0
- 3.24.0
- 3.23.0
- 3.22.0
- 3.21.0
- 3.20.0
- 3.19.0
- 3.18.0
- 3.17.0
- 3.16.0
- 3.15.0
- 3.14.0
- 3.13.0
- 3.12.0
- 3.11.0
- 3.10.0
- 3.9.0
- 3.8.0
- 3.7.0
- 3.6.0
- 3.5.0
- 3.4.2
- 3.3.0
- 3.2.0
- 3.0.0
- 2.9.8
- 2.8.9
- 2.7.4
- 2.5.3
- 2.4.0
public static final class ExplainRequest.Builder extends GeneratedMessageV3.Builder<ExplainRequest.Builder> implements ExplainRequestOrBuilder
Request message for PredictionService.Explain.
Protobuf type google.cloud.aiplatform.v1.ExplainRequest
Inheritance
Object > AbstractMessageLite.Builder<MessageType,BuilderType> > AbstractMessage.Builder<BuilderType> > GeneratedMessageV3.Builder > ExplainRequest.BuilderImplements
ExplainRequestOrBuilderStatic Methods
getDescriptor()
public static final Descriptors.Descriptor getDescriptor()
Returns | |
---|---|
Type | Description |
Descriptor |
Methods
addAllInstances(Iterable<? extends Value> values)
public ExplainRequest.Builder addAllInstances(Iterable<? extends Value> values)
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Parameter | |
---|---|
Name | Description |
values | Iterable<? extends com.google.protobuf.Value> |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
addInstances(Value value)
public ExplainRequest.Builder addInstances(Value value)
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Parameter | |
---|---|
Name | Description |
value | Value |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
addInstances(Value.Builder builderForValue)
public ExplainRequest.Builder addInstances(Value.Builder builderForValue)
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Parameter | |
---|---|
Name | Description |
builderForValue | Builder |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
addInstances(int index, Value value)
public ExplainRequest.Builder addInstances(int index, Value value)
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Parameters | |
---|---|
Name | Description |
index | int |
value | Value |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
addInstances(int index, Value.Builder builderForValue)
public ExplainRequest.Builder addInstances(int index, Value.Builder builderForValue)
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Parameters | |
---|---|
Name | Description |
index | int |
builderForValue | Builder |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
addInstancesBuilder()
public Value.Builder addInstancesBuilder()
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Returns | |
---|---|
Type | Description |
Builder |
addInstancesBuilder(int index)
public Value.Builder addInstancesBuilder(int index)
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Parameter | |
---|---|
Name | Description |
index | int |
Returns | |
---|---|
Type | Description |
Builder |
addRepeatedField(Descriptors.FieldDescriptor field, Object value)
public ExplainRequest.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Parameters | |
---|---|
Name | Description |
field | FieldDescriptor |
value | Object |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
build()
public ExplainRequest build()
Returns | |
---|---|
Type | Description |
ExplainRequest |
buildPartial()
public ExplainRequest buildPartial()
Returns | |
---|---|
Type | Description |
ExplainRequest |
clear()
public ExplainRequest.Builder clear()
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
clearDeployedModelId()
public ExplainRequest.Builder clearDeployedModelId()
If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding Endpoint.traffic_split.
string deployed_model_id = 3;
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder | This builder for chaining. |
clearEndpoint()
public ExplainRequest.Builder clearEndpoint()
Required. The name of the Endpoint requested to serve the explanation.
Format:
projects/{project}/locations/{location}/endpoints/{endpoint}
string endpoint = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.resource_reference) = { ... }
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder | This builder for chaining. |
clearExplanationSpecOverride()
public ExplainRequest.Builder clearExplanationSpecOverride()
If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as:
- Explaining top-5 predictions results as opposed to top-1;
- Increasing path count or step count of the attribution methods to reduce approximate errors;
- Using different baselines for explaining the prediction results.
.google.cloud.aiplatform.v1.ExplanationSpecOverride explanation_spec_override = 5;
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
clearField(Descriptors.FieldDescriptor field)
public ExplainRequest.Builder clearField(Descriptors.FieldDescriptor field)
Parameter | |
---|---|
Name | Description |
field | FieldDescriptor |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
clearInstances()
public ExplainRequest.Builder clearInstances()
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
clearOneof(Descriptors.OneofDescriptor oneof)
public ExplainRequest.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Parameter | |
---|---|
Name | Description |
oneof | OneofDescriptor |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
clearParameters()
public ExplainRequest.Builder clearParameters()
The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.
.google.protobuf.Value parameters = 4;
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
clone()
public ExplainRequest.Builder clone()
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
getDefaultInstanceForType()
public ExplainRequest getDefaultInstanceForType()
Returns | |
---|---|
Type | Description |
ExplainRequest |
getDeployedModelId()
public String getDeployedModelId()
If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding Endpoint.traffic_split.
string deployed_model_id = 3;
Returns | |
---|---|
Type | Description |
String | The deployedModelId. |
getDeployedModelIdBytes()
public ByteString getDeployedModelIdBytes()
If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding Endpoint.traffic_split.
string deployed_model_id = 3;
Returns | |
---|---|
Type | Description |
ByteString | The bytes for deployedModelId. |
getDescriptorForType()
public Descriptors.Descriptor getDescriptorForType()
Returns | |
---|---|
Type | Description |
Descriptor |
getEndpoint()
public String getEndpoint()
Required. The name of the Endpoint requested to serve the explanation.
Format:
projects/{project}/locations/{location}/endpoints/{endpoint}
string endpoint = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.resource_reference) = { ... }
Returns | |
---|---|
Type | Description |
String | The endpoint. |
getEndpointBytes()
public ByteString getEndpointBytes()
Required. The name of the Endpoint requested to serve the explanation.
Format:
projects/{project}/locations/{location}/endpoints/{endpoint}
string endpoint = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.resource_reference) = { ... }
Returns | |
---|---|
Type | Description |
ByteString | The bytes for endpoint. |
getExplanationSpecOverride()
public ExplanationSpecOverride getExplanationSpecOverride()
If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as:
- Explaining top-5 predictions results as opposed to top-1;
- Increasing path count or step count of the attribution methods to reduce approximate errors;
- Using different baselines for explaining the prediction results.
.google.cloud.aiplatform.v1.ExplanationSpecOverride explanation_spec_override = 5;
Returns | |
---|---|
Type | Description |
ExplanationSpecOverride | The explanationSpecOverride. |
getExplanationSpecOverrideBuilder()
public ExplanationSpecOverride.Builder getExplanationSpecOverrideBuilder()
If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as:
- Explaining top-5 predictions results as opposed to top-1;
- Increasing path count or step count of the attribution methods to reduce approximate errors;
- Using different baselines for explaining the prediction results.
.google.cloud.aiplatform.v1.ExplanationSpecOverride explanation_spec_override = 5;
Returns | |
---|---|
Type | Description |
ExplanationSpecOverride.Builder |
getExplanationSpecOverrideOrBuilder()
public ExplanationSpecOverrideOrBuilder getExplanationSpecOverrideOrBuilder()
If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as:
- Explaining top-5 predictions results as opposed to top-1;
- Increasing path count or step count of the attribution methods to reduce approximate errors;
- Using different baselines for explaining the prediction results.
.google.cloud.aiplatform.v1.ExplanationSpecOverride explanation_spec_override = 5;
Returns | |
---|---|
Type | Description |
ExplanationSpecOverrideOrBuilder |
getInstances(int index)
public Value getInstances(int index)
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Parameter | |
---|---|
Name | Description |
index | int |
Returns | |
---|---|
Type | Description |
Value |
getInstancesBuilder(int index)
public Value.Builder getInstancesBuilder(int index)
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Parameter | |
---|---|
Name | Description |
index | int |
Returns | |
---|---|
Type | Description |
Builder |
getInstancesBuilderList()
public List<Value.Builder> getInstancesBuilderList()
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Returns | |
---|---|
Type | Description |
List<Builder> |
getInstancesCount()
public int getInstancesCount()
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Returns | |
---|---|
Type | Description |
int |
getInstancesList()
public List<Value> getInstancesList()
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Returns | |
---|---|
Type | Description |
List<Value> |
getInstancesOrBuilder(int index)
public ValueOrBuilder getInstancesOrBuilder(int index)
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Parameter | |
---|---|
Name | Description |
index | int |
Returns | |
---|---|
Type | Description |
ValueOrBuilder |
getInstancesOrBuilderList()
public List<? extends ValueOrBuilder> getInstancesOrBuilderList()
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Returns | |
---|---|
Type | Description |
List<? extends com.google.protobuf.ValueOrBuilder> |
getParameters()
public Value getParameters()
The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.
.google.protobuf.Value parameters = 4;
Returns | |
---|---|
Type | Description |
Value | The parameters. |
getParametersBuilder()
public Value.Builder getParametersBuilder()
The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.
.google.protobuf.Value parameters = 4;
Returns | |
---|---|
Type | Description |
Builder |
getParametersOrBuilder()
public ValueOrBuilder getParametersOrBuilder()
The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.
.google.protobuf.Value parameters = 4;
Returns | |
---|---|
Type | Description |
ValueOrBuilder |
hasExplanationSpecOverride()
public boolean hasExplanationSpecOverride()
If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as:
- Explaining top-5 predictions results as opposed to top-1;
- Increasing path count or step count of the attribution methods to reduce approximate errors;
- Using different baselines for explaining the prediction results.
.google.cloud.aiplatform.v1.ExplanationSpecOverride explanation_spec_override = 5;
Returns | |
---|---|
Type | Description |
boolean | Whether the explanationSpecOverride field is set. |
hasParameters()
public boolean hasParameters()
The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.
.google.protobuf.Value parameters = 4;
Returns | |
---|---|
Type | Description |
boolean | Whether the parameters field is set. |
internalGetFieldAccessorTable()
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns | |
---|---|
Type | Description |
FieldAccessorTable |
isInitialized()
public final boolean isInitialized()
Returns | |
---|---|
Type | Description |
boolean |
mergeExplanationSpecOverride(ExplanationSpecOverride value)
public ExplainRequest.Builder mergeExplanationSpecOverride(ExplanationSpecOverride value)
If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as:
- Explaining top-5 predictions results as opposed to top-1;
- Increasing path count or step count of the attribution methods to reduce approximate errors;
- Using different baselines for explaining the prediction results.
.google.cloud.aiplatform.v1.ExplanationSpecOverride explanation_spec_override = 5;
Parameter | |
---|---|
Name | Description |
value | ExplanationSpecOverride |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
mergeFrom(ExplainRequest other)
public ExplainRequest.Builder mergeFrom(ExplainRequest other)
Parameter | |
---|---|
Name | Description |
other | ExplainRequest |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
public ExplainRequest.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters | |
---|---|
Name | Description |
input | CodedInputStream |
extensionRegistry | ExtensionRegistryLite |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
Exceptions | |
---|---|
Type | Description |
IOException |
mergeFrom(Message other)
public ExplainRequest.Builder mergeFrom(Message other)
Parameter | |
---|---|
Name | Description |
other | Message |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
mergeParameters(Value value)
public ExplainRequest.Builder mergeParameters(Value value)
The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.
.google.protobuf.Value parameters = 4;
Parameter | |
---|---|
Name | Description |
value | Value |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
mergeUnknownFields(UnknownFieldSet unknownFields)
public final ExplainRequest.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Parameter | |
---|---|
Name | Description |
unknownFields | UnknownFieldSet |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
removeInstances(int index)
public ExplainRequest.Builder removeInstances(int index)
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Parameter | |
---|---|
Name | Description |
index | int |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
setDeployedModelId(String value)
public ExplainRequest.Builder setDeployedModelId(String value)
If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding Endpoint.traffic_split.
string deployed_model_id = 3;
Parameter | |
---|---|
Name | Description |
value | String The deployedModelId to set. |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder | This builder for chaining. |
setDeployedModelIdBytes(ByteString value)
public ExplainRequest.Builder setDeployedModelIdBytes(ByteString value)
If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding Endpoint.traffic_split.
string deployed_model_id = 3;
Parameter | |
---|---|
Name | Description |
value | ByteString The bytes for deployedModelId to set. |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder | This builder for chaining. |
setEndpoint(String value)
public ExplainRequest.Builder setEndpoint(String value)
Required. The name of the Endpoint requested to serve the explanation.
Format:
projects/{project}/locations/{location}/endpoints/{endpoint}
string endpoint = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.resource_reference) = { ... }
Parameter | |
---|---|
Name | Description |
value | String The endpoint to set. |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder | This builder for chaining. |
setEndpointBytes(ByteString value)
public ExplainRequest.Builder setEndpointBytes(ByteString value)
Required. The name of the Endpoint requested to serve the explanation.
Format:
projects/{project}/locations/{location}/endpoints/{endpoint}
string endpoint = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.resource_reference) = { ... }
Parameter | |
---|---|
Name | Description |
value | ByteString The bytes for endpoint to set. |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder | This builder for chaining. |
setExplanationSpecOverride(ExplanationSpecOverride value)
public ExplainRequest.Builder setExplanationSpecOverride(ExplanationSpecOverride value)
If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as:
- Explaining top-5 predictions results as opposed to top-1;
- Increasing path count or step count of the attribution methods to reduce approximate errors;
- Using different baselines for explaining the prediction results.
.google.cloud.aiplatform.v1.ExplanationSpecOverride explanation_spec_override = 5;
Parameter | |
---|---|
Name | Description |
value | ExplanationSpecOverride |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
setExplanationSpecOverride(ExplanationSpecOverride.Builder builderForValue)
public ExplainRequest.Builder setExplanationSpecOverride(ExplanationSpecOverride.Builder builderForValue)
If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as:
- Explaining top-5 predictions results as opposed to top-1;
- Increasing path count or step count of the attribution methods to reduce approximate errors;
- Using different baselines for explaining the prediction results.
.google.cloud.aiplatform.v1.ExplanationSpecOverride explanation_spec_override = 5;
Parameter | |
---|---|
Name | Description |
builderForValue | ExplanationSpecOverride.Builder |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
setField(Descriptors.FieldDescriptor field, Object value)
public ExplainRequest.Builder setField(Descriptors.FieldDescriptor field, Object value)
Parameters | |
---|---|
Name | Description |
field | FieldDescriptor |
value | Object |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
setInstances(int index, Value value)
public ExplainRequest.Builder setInstances(int index, Value value)
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Parameters | |
---|---|
Name | Description |
index | int |
value | Value |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
setInstances(int index, Value.Builder builderForValue)
public ExplainRequest.Builder setInstances(int index, Value.Builder builderForValue)
Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];
Parameters | |
---|---|
Name | Description |
index | int |
builderForValue | Builder |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
setParameters(Value value)
public ExplainRequest.Builder setParameters(Value value)
The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.
.google.protobuf.Value parameters = 4;
Parameter | |
---|---|
Name | Description |
value | Value |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
setParameters(Value.Builder builderForValue)
public ExplainRequest.Builder setParameters(Value.Builder builderForValue)
The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.
.google.protobuf.Value parameters = 4;
Parameter | |
---|---|
Name | Description |
builderForValue | Builder |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
public ExplainRequest.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Parameters | |
---|---|
Name | Description |
field | FieldDescriptor |
index | int |
value | Object |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |
setUnknownFields(UnknownFieldSet unknownFields)
public final ExplainRequest.Builder setUnknownFields(UnknownFieldSet unknownFields)
Parameter | |
---|---|
Name | Description |
unknownFields | UnknownFieldSet |
Returns | |
---|---|
Type | Description |
ExplainRequest.Builder |