AWS::SageMaker::Model ContainerDefinition
Describes the container, as part of model definition.
Syntax
To declare this entity in your Amazon CloudFormation template, use the following syntax:
JSON
{ "ContainerHostname" :
String
, "Environment" :Json
, "Image" :String
, "ImageConfig" :ImageConfig
, "InferenceSpecificationName" :String
, "Mode" :String
, "ModelDataSource" :ModelDataSource
, "ModelDataUrl" :String
, "ModelPackageName" :String
, "MultiModelConfig" :MultiModelConfig
}
YAML
ContainerHostname:
String
Environment:Json
Image:String
ImageConfig:ImageConfig
InferenceSpecificationName:String
Mode:String
ModelDataSource:ModelDataSource
ModelDataUrl:String
ModelPackageName:String
MultiModelConfig:MultiModelConfig
Properties
ContainerHostname
-
This parameter is ignored for models that contain only a
PrimaryContainer
.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 aContainerDefinition
that is part of an inference pipeline, a unique name is automatically assigned based on the position of theContainerDefinition
in the pipeline. If you specify a value for theContainerHostName
for anyContainerDefinition
that is part of an inference pipeline, you must specify a value for theContainerHostName
parameter of everyContainerDefinition
in that pipeline.Required: No
Type: String
Pattern:
^[a-zA-Z0-9](-*[a-zA-Z0-9]){0,62}
Maximum:
63
Update requires: Replacement
Environment
-
The environment variables to set in the Docker container. Don't include any sensitive data in your environment variables.
The maximum length of each key and value in the
Environment
map is 1024 bytes. The maximum length of all keys and values in the map, combined, is 32 KB. If you pass multiple containers to aCreateModel
request, then the maximum length of all of their maps, combined, is also 32 KB.Required: No
Type: Json
Update requires: Replacement
Image
-
The path where inference code is stored. 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]
andregistry/repository[@digest]
image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker.Note
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.
Required: No
Type: String
Pattern:
[\S]+
Maximum:
255
Update requires: Replacement
ImageConfig
-
Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC). For information about storing containers in a private Docker registry, see Use a Private Docker Registry for Real-Time Inference Containers.
Note
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.
Required: No
Type: ImageConfig
Update requires: Replacement
InferenceSpecificationName
-
The inference specification name in the model package version.
Required: No
Type: String
Update requires: Replacement
Mode
-
Whether the container hosts a single model or multiple models.
Required: No
Type: String
Allowed values:
SingleModel | MultiModel
Update requires: Replacement
ModelDataSource
-
Specifies the location of ML model data to deploy.
Note
Currently you cannot use
ModelDataSource
in conjunction with SageMaker batch transform, SageMaker serverless endpoints, SageMaker multi-model endpoints, and SageMaker Marketplace.Required: No
Type: ModelDataSource
Update requires: Replacement
ModelDataUrl
-
The S3 path where the model artifacts, which result from model training, are stored. 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.
Note
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 Amazon Security Token Service to download model artifacts from the S3 path you provide. Amazon STS is activated in your Amazon account by default. If you previously deactivated Amazon STS for a region, you need to reactivate Amazon STS for that region. For more information, see Activating and Deactivating Amazon STS in an Amazon Region in the Amazon Identity and Access Management User Guide.
Important
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
.Required: No
Type: String
Pattern:
^(https|s3)://([^/]+)/?(.*)$
Maximum:
1024
Update requires: Replacement
ModelPackageName
-
The name or Amazon Resource Name (ARN) of the model package to use to create the model.
Required: No
Type: String
Pattern:
(arn:aws[a-z\-]*:sagemaker:[a-z0-9\-]*:[0-9]{12}:[a-z\-]*\/)?([a-zA-Z0-9]([a-zA-Z0-9-]){0,62})(?<!-)(\/[0-9]{1,9})?$
Minimum:
1
Maximum:
176
Update requires: Replacement
MultiModelConfig
-
Specifies additional configuration for multi-model endpoints.
Required: No
Type: MultiModelConfig
Update requires: Replacement