@Generated(value="com.amazonaws:aws-java-sdk-code-generator") public class ProductionVariant extends Object implements Serializable, Cloneable, StructuredPojo
Identifies a model that you want to host and the resources to deploy for hosting it. If you are deploying multiple models, tell Amazon SageMaker how to distribute traffic among the models by specifying variant weights.
Constructor and Description |
---|
ProductionVariant() |
Modifier and Type | Method and Description |
---|---|
ProductionVariant |
clone() |
boolean |
equals(Object obj) |
String |
getAcceleratorType()
The size of the Elastic Inference (EI) instance to use for the production variant.
|
Integer |
getInitialInstanceCount()
Number of instances to launch initially.
|
Float |
getInitialVariantWeight()
Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
|
String |
getInstanceType()
The ML compute instance type.
|
String |
getModelName()
The name of the model that you want to host.
|
String |
getVariantName()
The name of the production variant.
|
int |
hashCode() |
void |
marshall(ProtocolMarshaller protocolMarshaller)
Marshalls this structured data using the given
ProtocolMarshaller . |
void |
setAcceleratorType(String acceleratorType)
The size of the Elastic Inference (EI) instance to use for the production variant.
|
void |
setInitialInstanceCount(Integer initialInstanceCount)
Number of instances to launch initially.
|
void |
setInitialVariantWeight(Float initialVariantWeight)
Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
|
void |
setInstanceType(String instanceType)
The ML compute instance type.
|
void |
setModelName(String modelName)
The name of the model that you want to host.
|
void |
setVariantName(String variantName)
The name of the production variant.
|
String |
toString()
Returns a string representation of this object.
|
ProductionVariant |
withAcceleratorType(ProductionVariantAcceleratorType acceleratorType)
The size of the Elastic Inference (EI) instance to use for the production variant.
|
ProductionVariant |
withAcceleratorType(String acceleratorType)
The size of the Elastic Inference (EI) instance to use for the production variant.
|
ProductionVariant |
withInitialInstanceCount(Integer initialInstanceCount)
Number of instances to launch initially.
|
ProductionVariant |
withInitialVariantWeight(Float initialVariantWeight)
Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
|
ProductionVariant |
withInstanceType(ProductionVariantInstanceType instanceType)
The ML compute instance type.
|
ProductionVariant |
withInstanceType(String instanceType)
The ML compute instance type.
|
ProductionVariant |
withModelName(String modelName)
The name of the model that you want to host.
|
ProductionVariant |
withVariantName(String variantName)
The name of the production variant.
|
public void setVariantName(String variantName)
The name of the production variant.
variantName
- The name of the production variant.public String getVariantName()
The name of the production variant.
public ProductionVariant withVariantName(String variantName)
The name of the production variant.
variantName
- The name of the production variant.public void setModelName(String modelName)
The name of the model that you want to host. This is the name that you specified when creating the model.
modelName
- The name of the model that you want to host. This is the name that you specified when creating the model.public String getModelName()
The name of the model that you want to host. This is the name that you specified when creating the model.
public ProductionVariant withModelName(String modelName)
The name of the model that you want to host. This is the name that you specified when creating the model.
modelName
- The name of the model that you want to host. This is the name that you specified when creating the model.public void setInitialInstanceCount(Integer initialInstanceCount)
Number of instances to launch initially.
initialInstanceCount
- Number of instances to launch initially.public Integer getInitialInstanceCount()
Number of instances to launch initially.
public ProductionVariant withInitialInstanceCount(Integer initialInstanceCount)
Number of instances to launch initially.
initialInstanceCount
- Number of instances to launch initially.public void setInstanceType(String instanceType)
The ML compute instance type.
instanceType
- The ML compute instance type.ProductionVariantInstanceType
public String getInstanceType()
The ML compute instance type.
ProductionVariantInstanceType
public ProductionVariant withInstanceType(String instanceType)
The ML compute instance type.
instanceType
- The ML compute instance type.ProductionVariantInstanceType
public ProductionVariant withInstanceType(ProductionVariantInstanceType instanceType)
The ML compute instance type.
instanceType
- The ML compute instance type.ProductionVariantInstanceType
public void setInitialVariantWeight(Float initialVariantWeight)
Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
The traffic to a production variant is determined by the ratio of the VariantWeight
to the sum of
all VariantWeight
values across all ProductionVariants. If unspecified, it defaults to 1.0.
initialVariantWeight
- Determines initial traffic distribution among all of the models that you specify in the endpoint
configuration. The traffic to a production variant is determined by the ratio of the
VariantWeight
to the sum of all VariantWeight
values across all
ProductionVariants. If unspecified, it defaults to 1.0.public Float getInitialVariantWeight()
Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
The traffic to a production variant is determined by the ratio of the VariantWeight
to the sum of
all VariantWeight
values across all ProductionVariants. If unspecified, it defaults to 1.0.
VariantWeight
to the sum of all VariantWeight
values across all
ProductionVariants. If unspecified, it defaults to 1.0.public ProductionVariant withInitialVariantWeight(Float initialVariantWeight)
Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
The traffic to a production variant is determined by the ratio of the VariantWeight
to the sum of
all VariantWeight
values across all ProductionVariants. If unspecified, it defaults to 1.0.
initialVariantWeight
- Determines initial traffic distribution among all of the models that you specify in the endpoint
configuration. The traffic to a production variant is determined by the ratio of the
VariantWeight
to the sum of all VariantWeight
values across all
ProductionVariants. If unspecified, it defaults to 1.0.public void setAcceleratorType(String acceleratorType)
The size of the Elastic Inference (EI) instance to use for the production variant. EI instances provide on-demand GPU computing for inference. For more information, see Using Elastic Inference in Amazon SageMaker.
acceleratorType
- The size of the Elastic Inference (EI) instance to use for the production variant. EI instances provide
on-demand GPU computing for inference. For more information, see Using Elastic Inference in Amazon
SageMaker.ProductionVariantAcceleratorType
public String getAcceleratorType()
The size of the Elastic Inference (EI) instance to use for the production variant. EI instances provide on-demand GPU computing for inference. For more information, see Using Elastic Inference in Amazon SageMaker.
ProductionVariantAcceleratorType
public ProductionVariant withAcceleratorType(String acceleratorType)
The size of the Elastic Inference (EI) instance to use for the production variant. EI instances provide on-demand GPU computing for inference. For more information, see Using Elastic Inference in Amazon SageMaker.
acceleratorType
- The size of the Elastic Inference (EI) instance to use for the production variant. EI instances provide
on-demand GPU computing for inference. For more information, see Using Elastic Inference in Amazon
SageMaker.ProductionVariantAcceleratorType
public ProductionVariant withAcceleratorType(ProductionVariantAcceleratorType acceleratorType)
The size of the Elastic Inference (EI) instance to use for the production variant. EI instances provide on-demand GPU computing for inference. For more information, see Using Elastic Inference in Amazon SageMaker.
acceleratorType
- The size of the Elastic Inference (EI) instance to use for the production variant. EI instances provide
on-demand GPU computing for inference. For more information, see Using Elastic Inference in Amazon
SageMaker.ProductionVariantAcceleratorType
public String toString()
toString
in class Object
Object.toString()
public ProductionVariant clone()
public void marshall(ProtocolMarshaller protocolMarshaller)
StructuredPojo
ProtocolMarshaller
.marshall
in interface StructuredPojo
protocolMarshaller
- Implementation of ProtocolMarshaller
used to marshall this object's data.