Class CfnInferenceExperiment
Creates an inference experiment using the configurations specified in the request.
Inherited Members
Namespace: Amazon.CDK.AWS.Sagemaker
Assembly: Amazon.CDK.Lib.dll
Syntax (csharp)
public class CfnInferenceExperiment : CfnResource, IInspectable, ITaggable
Syntax (vb)
Public Class CfnInferenceExperiment Inherits CfnResource Implements IInspectable, ITaggable
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
Examples
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
using Amazon.CDK.AWS.Sagemaker;
var cfnInferenceExperiment = new CfnInferenceExperiment(this, "MyCfnInferenceExperiment", new CfnInferenceExperimentProps {
EndpointName = "endpointName",
ModelVariants = new [] { new ModelVariantConfigProperty {
InfrastructureConfig = new ModelInfrastructureConfigProperty {
InfrastructureType = "infrastructureType",
RealTimeInferenceConfig = new RealTimeInferenceConfigProperty {
InstanceCount = 123,
InstanceType = "instanceType"
}
},
ModelName = "modelName",
VariantName = "variantName"
} },
Name = "name",
RoleArn = "roleArn",
Type = "type",
// the properties below are optional
DataStorageConfig = new DataStorageConfigProperty {
Destination = "destination",
// the properties below are optional
ContentType = new CaptureContentTypeHeaderProperty {
CsvContentTypes = new [] { "csvContentTypes" },
JsonContentTypes = new [] { "jsonContentTypes" }
},
KmsKey = "kmsKey"
},
Description = "description",
DesiredState = "desiredState",
KmsKey = "kmsKey",
Schedule = new InferenceExperimentScheduleProperty {
EndTime = "endTime",
StartTime = "startTime"
},
ShadowModeConfig = new ShadowModeConfigProperty {
ShadowModelVariants = new [] { new ShadowModelVariantConfigProperty {
SamplingPercentage = 123,
ShadowModelVariantName = "shadowModelVariantName"
} },
SourceModelVariantName = "sourceModelVariantName"
},
StatusReason = "statusReason",
Tags = new [] { new CfnTag {
Key = "key",
Value = "value"
} }
});
Synopsis
Constructors
CfnInferenceExperiment(Construct, string, ICfnInferenceExperimentProps) | Creates an inference experiment using the configurations specified in the request. |
Properties
AttrArn | The ARN for your inference experiment. |
AttrCreationTime | The timestamp at which the inference experiment was created. |
AttrEndpointMetadata | The metadata of the endpoint on which the inference experiment ran. |
AttrEndpointMetadataEndpointConfigName | Creates an inference experiment using the configurations specified in the request. |
AttrEndpointMetadataEndpointName | Creates an inference experiment using the configurations specified in the request. |
AttrEndpointMetadataEndpointStatus | Creates an inference experiment using the configurations specified in the request. |
AttrLastModifiedTime | The timestamp at which you last modified the inference experiment. |
AttrStatus | The status of the inference experiment. The following are the possible statuses for an inference experiment:. |
CFN_RESOURCE_TYPE_NAME | The CloudFormation resource type name for this resource class. |
CfnProperties | Creates an inference experiment using the configurations specified in the request. |
DataStorageConfig | The Amazon S3 location and configuration for storing inference request and response data. |
Description | The description of the inference experiment. |
DesiredState | The desired state of the experiment after stopping. |
EndpointName | The name of the endpoint. |
KmsKey | The AWS Key Management Service key that Amazon SageMaker uses to encrypt captured data at rest using Amazon S3 server-side encryption. |
ModelVariants | An array of |
Name | The name of the inference experiment. |
RoleArn | The ARN of the IAM role that Amazon SageMaker can assume to access model artifacts and container images, and manage Amazon SageMaker Inference endpoints for model deployment. |
Schedule | The duration for which the inference experiment ran or will run. |
ShadowModeConfig | The configuration of |
StatusReason | The error message for the inference experiment status result. |
Tags | Tag Manager which manages the tags for this resource. |
TagsRaw | An array of key-value pairs to apply to this resource. |
Type | The type of the inference experiment. |
Methods
Inspect(TreeInspector) | Examines the CloudFormation resource and discloses attributes. |
RenderProperties(IDictionary<string, object>) | Creates an inference experiment using the configurations specified in the request. |
Constructors
CfnInferenceExperiment(Construct, string, ICfnInferenceExperimentProps)
Creates an inference experiment using the configurations specified in the request.
public CfnInferenceExperiment(Construct scope, string id, ICfnInferenceExperimentProps props)
Parameters
- scope Construct
Scope in which this resource is defined.
- id string
Construct identifier for this resource (unique in its scope).
- props ICfnInferenceExperimentProps
Resource properties.
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
Properties
AttrArn
The ARN for your inference experiment.
public virtual string AttrArn { get; }
Property Value
Remarks
CloudformationAttribute: Arn
AttrCreationTime
The timestamp at which the inference experiment was created.
public virtual string AttrCreationTime { get; }
Property Value
Remarks
CloudformationAttribute: CreationTime
AttrEndpointMetadata
The metadata of the endpoint on which the inference experiment ran.
public virtual IResolvable AttrEndpointMetadata { get; }
Property Value
Remarks
CloudformationAttribute: EndpointMetadata
AttrEndpointMetadataEndpointConfigName
Creates an inference experiment using the configurations specified in the request.
public virtual string AttrEndpointMetadataEndpointConfigName { get; }
Property Value
Remarks
CloudformationAttribute: EndpointMetadata.EndpointConfigName
AttrEndpointMetadataEndpointName
Creates an inference experiment using the configurations specified in the request.
public virtual string AttrEndpointMetadataEndpointName { get; }
Property Value
Remarks
CloudformationAttribute: EndpointMetadata.EndpointName
AttrEndpointMetadataEndpointStatus
Creates an inference experiment using the configurations specified in the request.
public virtual string AttrEndpointMetadataEndpointStatus { get; }
Property Value
Remarks
CloudformationAttribute: EndpointMetadata.EndpointStatus
AttrLastModifiedTime
The timestamp at which you last modified the inference experiment.
public virtual string AttrLastModifiedTime { get; }
Property Value
Remarks
CloudformationAttribute: LastModifiedTime
AttrStatus
The status of the inference experiment. The following are the possible statuses for an inference experiment:.
public virtual string AttrStatus { get; }
Property Value
Remarks
CloudformationAttribute: Status
CFN_RESOURCE_TYPE_NAME
The CloudFormation resource type name for this resource class.
public static string CFN_RESOURCE_TYPE_NAME { get; }
Property Value
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
CfnProperties
Creates an inference experiment using the configurations specified in the request.
protected override IDictionary<string, object> CfnProperties { get; }
Property Value
Overrides
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
DataStorageConfig
The Amazon S3 location and configuration for storing inference request and response data.
public virtual object? DataStorageConfig { get; set; }
Property Value
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
Description
The description of the inference experiment.
public virtual string? Description { get; set; }
Property Value
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
DesiredState
The desired state of the experiment after stopping.
public virtual string? DesiredState { get; set; }
Property Value
Remarks
The possible states are the following:.
EndpointName
The name of the endpoint.
public virtual string EndpointName { get; set; }
Property Value
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
KmsKey
The AWS Key Management Service key that Amazon SageMaker uses to encrypt captured data at rest using Amazon S3 server-side encryption.
public virtual string? KmsKey { get; set; }
Property Value
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
ModelVariants
An array of ModelVariantConfigSummary
objects.
public virtual object ModelVariants { get; set; }
Property Value
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
Name
The name of the inference experiment.
public virtual string Name { get; set; }
Property Value
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
RoleArn
The ARN of the IAM role that Amazon SageMaker can assume to access model artifacts and container images, and manage Amazon SageMaker Inference endpoints for model deployment.
public virtual string RoleArn { get; set; }
Property Value
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
Schedule
The duration for which the inference experiment ran or will run.
public virtual object? Schedule { get; set; }
Property Value
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
ShadowModeConfig
The configuration of ShadowMode
inference experiment type, which shows the production variant that takes all the inference requests, and the shadow variant to which Amazon SageMaker replicates a percentage of the inference requests.
public virtual object? ShadowModeConfig { get; set; }
Property Value
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
StatusReason
The error message for the inference experiment status result.
public virtual string? StatusReason { get; set; }
Property Value
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
Tags
Tag Manager which manages the tags for this resource.
public virtual TagManager Tags { get; }
Property Value
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
TagsRaw
An array of key-value pairs to apply to this resource.
public virtual ICfnTag[]? TagsRaw { get; set; }
Property Value
ICfnTag[]
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
Type
The type of the inference experiment.
public virtual string Type { get; set; }
Property Value
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
Methods
Inspect(TreeInspector)
Examines the CloudFormation resource and discloses attributes.
public virtual void Inspect(TreeInspector inspector)
Parameters
- inspector TreeInspector
tree inspector to collect and process attributes.
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated
RenderProperties(IDictionary<string, object>)
Creates an inference experiment using the configurations specified in the request.
protected override IDictionary<string, object> RenderProperties(IDictionary<string, object> props)
Parameters
- props IDictionary<string, object>
Returns
Overrides
Remarks
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests .
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests .
CloudformationResource: AWS::SageMaker::InferenceExperiment
ExampleMetadata: fixture=_generated