Class CfnModelPackage.ModelPackageContainerDefinitionProperty
Describes the Docker container for the model package.
Inheritance
Namespace: Amazon.CDK.AWS.Sagemaker
Assembly: Amazon.CDK.Lib.dll
Syntax (csharp)
public class ModelPackageContainerDefinitionProperty : Object, CfnModelPackage.IModelPackageContainerDefinitionProperty
Syntax (vb)
Public Class ModelPackageContainerDefinitionProperty
Inherits Object
Implements CfnModelPackage.IModelPackageContainerDefinitionProperty
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 modelInput;
var modelPackageContainerDefinitionProperty = new ModelPackageContainerDefinitionProperty {
Image = "image",
// the properties below are optional
ContainerHostname = "containerHostname",
Environment = new Dictionary<string, string> {
{ "environmentKey", "environment" }
},
Framework = "framework",
FrameworkVersion = "frameworkVersion",
ImageDigest = "imageDigest",
ModelDataUrl = "modelDataUrl",
ModelInput = modelInput,
NearestModelName = "nearestModelName"
};
Synopsis
Constructors
ModelPackageContainerDefinitionProperty() |
Properties
ContainerHostname | The DNS host name for the Docker container. |
Environment | The environment variables to set in the Docker container. |
Framework | The machine learning framework of the model package container image. |
FrameworkVersion | The framework version of the Model Package Container Image. |
Image | The Amazon EC2 Container Registry (Amazon ECR) path where inference code is stored. |
ImageDigest | An MD5 hash of the training algorithm that identifies the Docker image used for training. |
ModelDataUrl | The Amazon S3 path where the model artifacts, which result from model training, are stored. |
ModelInput | A structure with Model Input details. |
NearestModelName | The name of a pre-trained machine learning benchmarked by Amazon SageMaker Inference Recommender model that matches your model. |
Constructors
ModelPackageContainerDefinitionProperty()
public ModelPackageContainerDefinitionProperty()
Properties
ContainerHostname
The DNS host name for the Docker container.
public string ContainerHostname { get; set; }
Property Value
System.String
Remarks
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.
Framework
The machine learning framework of the model package container image.
public string Framework { get; set; }
Property Value
System.String
Remarks
FrameworkVersion
The framework version of the Model Package Container Image.
public string FrameworkVersion { get; set; }
Property Value
System.String
Remarks
Image
The Amazon EC2 Container Registry (Amazon ECR) path where inference code is stored.
public string Image { get; set; }
Property Value
System.String
Remarks
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 .
ImageDigest
An MD5 hash of the training algorithm that identifies the Docker image used for training.
public string ImageDigest { get; set; }
Property Value
System.String
Remarks
ModelDataUrl
The Amazon 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 model artifacts must be in an S3 bucket that is in the same region as the model package.
ModelInput
A structure with Model Input details.
public object ModelInput { get; set; }
Property Value
System.Object
Remarks
NearestModelName
The name of a pre-trained machine learning benchmarked by Amazon SageMaker Inference Recommender model that matches your model.
public string NearestModelName { get; set; }
Property Value
System.String
Remarks
You can find a list of benchmarked models by calling ListModelMetadata
.