Interface ExplainRequestOrBuilder (0.6.0)
Stay organized with collections
Save and categorize content based on your preferences.
publicinterface ExplainRequestOrBuilderextendsMessageOrBuilderImplements
MessageOrBuilderMethods
getDeployedModelId()
publicabstractStringgetDeployedModelId()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()
publicabstractByteStringgetDeployedModelIdBytes()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. |
getEndpoint()
publicabstractStringgetEndpoint() 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()
publicabstractByteStringgetEndpointBytes() 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()
publicabstractExplanationSpecOverridegetExplanationSpecOverride()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.vertexai.v1.ExplanationSpecOverride explanation_spec_override = 5;
| Returns | |
|---|---|
| Type | Description |
ExplanationSpecOverride |
The explanationSpecOverride. |
getExplanationSpecOverrideOrBuilder()
publicabstractExplanationSpecOverrideOrBuildergetExplanationSpecOverrideOrBuilder()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.vertexai.v1.ExplanationSpecOverride explanation_spec_override = 5;
| Returns | |
|---|---|
| Type | Description |
ExplanationSpecOverrideOrBuilder |
|
getInstances(int index)
publicabstractValuegetInstances(intindex)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 |
|
getInstancesCount()
publicabstractintgetInstancesCount()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()
publicabstractList<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)
publicabstractValueOrBuildergetInstancesOrBuilder(intindex)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()
publicabstractList<?extendsValueOrBuilder>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()
publicabstractValuegetParameters()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. |
getParametersOrBuilder()
publicabstractValueOrBuildergetParametersOrBuilder()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()
publicabstractbooleanhasExplanationSpecOverride()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.vertexai.v1.ExplanationSpecOverride explanation_spec_override = 5;
| Returns | |
|---|---|
| Type | Description |
boolean |
Whether the explanationSpecOverride field is set. |
hasParameters()
publicabstractbooleanhasParameters()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. |