public static interface CfnModelPackage.ModelPackageContainerDefinitionProperty
Example:
// The code below shows an example of how to instantiate this type. // The values are placeholders you should change. import software.amazon.awscdk.services.sagemaker.*; Object modelInput; ModelPackageContainerDefinitionProperty modelPackageContainerDefinitionProperty = ModelPackageContainerDefinitionProperty.builder() .image("image") // the properties below are optional .containerHostname("containerHostname") .environment(Map.of( "environmentKey", "environment")) .framework("framework") .frameworkVersion("frameworkVersion") .imageDigest("imageDigest") .modelDataUrl("modelDataUrl") .modelInput(modelInput) .nearestModelName("nearestModelName") .productId("productId") .build();
Modifier and Type | Interface and Description |
---|---|
static class |
CfnModelPackage.ModelPackageContainerDefinitionProperty.Builder
A builder for
CfnModelPackage.ModelPackageContainerDefinitionProperty |
static class |
CfnModelPackage.ModelPackageContainerDefinitionProperty.Jsii$Proxy
An implementation for
CfnModelPackage.ModelPackageContainerDefinitionProperty |
Modifier and Type | Method and Description |
---|---|
static CfnModelPackage.ModelPackageContainerDefinitionProperty.Builder |
builder() |
default java.lang.String |
getContainerHostname()
The DNS host name for the Docker container.
|
default java.lang.Object |
getEnvironment()
The environment variables to set in the Docker container.
|
default java.lang.String |
getFramework()
The machine learning framework of the model package container image.
|
default java.lang.String |
getFrameworkVersion()
The framework version of the Model Package Container Image.
|
java.lang.String |
getImage()
The Amazon EC2 Container Registry (Amazon ECR) path where inference code is stored.
|
default java.lang.String |
getImageDigest()
An MD5 hash of the training algorithm that identifies the Docker image used for training.
|
default java.lang.String |
getModelDataUrl()
The Amazon S3 path where the model artifacts, which result from model training, are stored.
|
default java.lang.Object |
getModelInput()
A structure with Model Input details.
|
default java.lang.String |
getNearestModelName()
The name of a pre-trained machine learning benchmarked by Amazon SageMaker Inference Recommender model that matches your model.
|
default java.lang.String |
getProductId()
The AWS Marketplace product ID of the model package.
|
java.lang.String getImage()
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 .
default java.lang.String getContainerHostname()
default java.lang.Object getEnvironment()
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.
default java.lang.String getFramework()
default java.lang.String getFrameworkVersion()
default java.lang.String getImageDigest()
default java.lang.String getModelDataUrl()
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.
default java.lang.Object getModelInput()
default java.lang.String getNearestModelName()
You can find a list of benchmarked models by calling ListModelMetadata
.
default java.lang.String getProductId()