Class CfnModel.ContainerDefinitionProperty
Describes the container, as part of model definition.
Inheritance
Implements
Namespace: Amazon.CDK.AWS.Sagemaker
Assembly: Amazon.CDK.AWS.Sagemaker.dll
Syntax (csharp)
public class ContainerDefinitionProperty : Object, CfnModel.IContainerDefinitionProperty
Syntax (vb)
Public Class ContainerDefinitionProperty
Inherits Object
Implements CfnModel.IContainerDefinitionProperty
Remarks
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 environment;
var containerDefinitionProperty = new ContainerDefinitionProperty {
ContainerHostname = "containerHostname",
Environment = environment,
Image = "image",
ImageConfig = new ImageConfigProperty {
RepositoryAccessMode = "repositoryAccessMode",
// the properties below are optional
RepositoryAuthConfig = new RepositoryAuthConfigProperty {
RepositoryCredentialsProviderArn = "repositoryCredentialsProviderArn"
}
},
InferenceSpecificationName = "inferenceSpecificationName",
Mode = "mode",
ModelDataUrl = "modelDataUrl",
ModelPackageName = "modelPackageName",
MultiModelConfig = new MultiModelConfigProperty {
ModelCacheSetting = "modelCacheSetting"
}
};
Synopsis
Constructors
ContainerDefinitionProperty() |
Properties
ContainerHostname | This parameter is ignored for models that contain only a |
Environment | The environment variables to set in the Docker container. |
Image | The path where inference code is stored. |
ImageConfig | Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC). |
InferenceSpecificationName | The inference specification name in the model package version. |
Mode | Whether the container hosts a single model or multiple models. |
ModelDataUrl | The S3 path where the model artifacts, which result from model training, are stored. |
ModelPackageName | The name or Amazon Resource Name (ARN) of the model package to use to create the model. |
MultiModelConfig | Specifies additional configuration for multi-model endpoints. |
Constructors
ContainerDefinitionProperty()
public ContainerDefinitionProperty()
Properties
ContainerHostname
This parameter is ignored for models that contain only a PrimaryContainer
.
public string ContainerHostname { get; set; }
Property Value
System.String
Remarks
When a ContainerDefinition
is part of an inference pipeline, the value of the parameter uniquely identifies the container for the purposes of logging and metrics. For information, see Use Logs and Metrics to Monitor an Inference Pipeline . If you don't specify a value for this parameter for a ContainerDefinition
that is part of an inference pipeline, a unique name is automatically assigned based on the position of the ContainerDefinition
in the pipeline. If you specify a value for the ContainerHostName
for any ContainerDefinition
that is part of an inference pipeline, you must specify a value for the ContainerHostName
parameter of every ContainerDefinition
in that pipeline.
Environment
The environment variables to set in the Docker container.
public object Environment { get; set; }
Property Value
System.Object
Remarks
Each key and value in the Environment
string to string map can have length of up to 1024. We support up to 16 entries in the map.
Image
The path where inference code is stored.
public string Image { get; set; }
Property Value
System.String
Remarks
This can be either in Amazon EC2 Container Registry or in a Docker registry that is accessible from the same VPC that you configure for your endpoint. If you are using your own custom algorithm instead of an algorithm provided by SageMaker, the inference code must meet SageMaker requirements. SageMaker supports both registry/repository[:tag]
and registry/repository[@digest]
image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker .
The model artifacts in an Amazon S3 bucket and the Docker image for inference container in Amazon EC2 Container Registry must be in the same region as the model or endpoint you are creating.
ImageConfig
Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC).
public object ImageConfig { get; set; }
Property Value
System.Object
Remarks
For information about storing containers in a private Docker registry, see Use a Private Docker Registry for Real-Time Inference Containers .
The model artifacts in an Amazon S3 bucket and the Docker image for inference container in Amazon EC2 Container Registry must be in the same region as the model or endpoint you are creating.
InferenceSpecificationName
The inference specification name in the model package version.
public string InferenceSpecificationName { get; set; }
Property Value
System.String
Remarks
Mode
Whether the container hosts a single model or multiple models.
public string Mode { get; set; }
Property Value
System.String
Remarks
ModelDataUrl
The S3 path where the model artifacts, which result from model training, are stored.
public string ModelDataUrl { get; set; }
Property Value
System.String
Remarks
This path must point to a single gzip compressed tar archive (.tar.gz suffix). The S3 path is required for SageMaker built-in algorithms, but not if you use your own algorithms. For more information on built-in algorithms, see Common Parameters .
The model artifacts must be in an S3 bucket that is in the same region as the model or endpoint you are creating.
If you provide a value for this parameter, SageMaker uses AWS Security Token Service to download model artifacts from the S3 path you provide. AWS STS is activated in your AWS account by default. If you previously deactivated AWS STS for a region, you need to reactivate AWS STS for that region. For more information, see Activating and Deactivating AWS STS in an AWS Region in the AWS Identity and Access Management User Guide .
If you use a built-in algorithm to create a model, SageMaker requires that you provide a S3 path to the model artifacts in ModelDataUrl
.
ModelPackageName
The name or Amazon Resource Name (ARN) of the model package to use to create the model.
public string ModelPackageName { get; set; }
Property Value
System.String
Remarks
MultiModelConfig
Specifies additional configuration for multi-model endpoints.
public object MultiModelConfig { get; set; }
Property Value
System.Object