AWS::SageMaker::ModelPackage ModelPackageContainerDefinition
Describes the Docker container for the model package.
Syntax
To declare this entity in your Amazon CloudFormation template, use the following syntax:
JSON
{ "ContainerHostname" :
String
, "Environment" :{
, "Framework" :Key
:Value
, ...}String
, "FrameworkVersion" :String
, "Image" :String
, "ImageDigest" :String
, "ModelDataSource" :ModelDataSource
, "ModelDataUrl" :String
, "ModelInput" :ModelInput
, "NearestModelName" :String
}
YAML
ContainerHostname:
String
Environment:Framework:
Key
:Value
String
FrameworkVersion:String
Image:String
ImageDigest:String
ModelDataSource:ModelDataSource
ModelDataUrl:String
ModelInput:ModelInput
NearestModelName:String
Properties
ContainerHostname
-
The DNS host name for the Docker container.
Required: No
Type: String
Pattern:
^[a-zA-Z0-9](-*[a-zA-Z0-9]){0,62}
Maximum:
63
Update requires: No interruption
Environment
-
The environment variables to set in the Docker container. 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.Required: No
Type: Object of String
Pattern:
[a-zA-Z_][a-zA-Z0-9_]*
Maximum:
1024
Update requires: No interruption
Framework
-
The machine learning framework of the model package container image.
Required: No
Type: String
Update requires: No interruption
FrameworkVersion
-
The framework version of the Model Package Container Image.
Required: No
Type: String
Pattern:
[0-9]\.[A-Za-z0-9.]+
Minimum:
3
Maximum:
10
Update requires: No interruption
Image
-
The Amazon EC2 Container Registry (Amazon ECR) path where inference code is stored.
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.Required: Yes
Type: String
Pattern:
[\S]{1,255}
Minimum:
1
Maximum:
255
Update requires: No interruption
ImageDigest
-
An MD5 hash of the training algorithm that identifies the Docker image used for training.
Required: No
Type: String
Pattern:
^[Ss][Hh][Aa]256:[0-9a-fA-F]{64}$
Maximum:
72
Update requires: No interruption
ModelDataSource
-
Specifies the location of ML model data to deploy during endpoint creation.
Required: No
Type: ModelDataSource
Update requires: No interruption
ModelDataUrl
-
The Amazon 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).Note
The model artifacts must be in an S3 bucket that is in the same region as the model package.
Required: No
Type: String
Pattern:
^(https|s3)://([^/]+)/?(.*)$
Maximum:
1024
Update requires: No interruption
ModelInput
-
A structure with Model Input details.
Required: No
Type: ModelInput
Update requires: No interruption
NearestModelName
-
The name of a pre-trained machine learning benchmarked by Amazon SageMaker Inference Recommender model that matches your model. You can find a list of benchmarked models by calling
ListModelMetadata
.Required: No
Type: String
Update requires: No interruption