AWS Fundamentals Logo
AWS Fundamentals
L1 ConstructAWS::SageMaker::ModelPackage

CfnModelPackage

A container for your trained model that can be deployed for SageMaker inference. This can include inference code, artifacts, and metadata. The model package type can be one of the following. - Versioned model: A part of a model package group in Model Registry. - Unversioned model: Not part of a model package group and used in AWS Marketplace. For more information, see [`CreateModelPackage`](https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateModelPackage.html) .

Import

import { CfnModelPackage } from 'aws-cdk-lib/aws-sagemaker';

Or use the module namespace:

import * as sagemaker from 'aws-cdk-lib/aws-sagemaker';
// sagemaker.CfnModelPackage

Properties

Configuration passed to the constructor as CfnModelPackageProps.

additionalInferenceSpecificationsOptional
IResolvable | IResolvable | AdditionalInferenceSpecificationDefinitionProperty[]

An array of additional Inference Specification objects.

additionalInferenceSpecificationsToAddOptional
IResolvable | IResolvable | AdditionalInferenceSpecificationDefinitionProperty[]

An array of additional Inference Specification objects to be added to the existing array. The total number of additional Inference Specification objects cannot exceed 15. Each additional Inference Specification object specifies artifacts based on this model package that can be used on inference endpoints. Generally used with SageMaker Neo to store the compiled artifacts.

approvalDescriptionOptional
string

A description provided when the model approval is set.

certifyForMarketplaceOptional
boolean | IResolvable

Whether the model package is to be certified to be listed on AWS Marketplace. For information about listing model packages on AWS Marketplace, see [List Your Algorithm or Model Package on AWS Marketplace](https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-mkt-list.html) .

clientTokenOptional
string

A unique token that guarantees that the call to this API is idempotent.

customerMetadataPropertiesOptional
{ [key: string]: string } | IResolvable

The metadata properties for the model package.

domainOptional
string

The machine learning domain of your model package and its components. Common machine learning domains include computer vision and natural language processing.

driftCheckBaselinesOptional
IResolvable | DriftCheckBaselinesProperty

Represents the drift check baselines that can be used when the model monitor is set using the model package.

inferenceSpecificationOptional
IResolvable | InferenceSpecificationProperty

Defines how to perform inference generation after a training job is run.

lastModifiedTimeOptional
string

The last time the model package was modified.

metadataPropertiesOptional
IResolvable | MetadataPropertiesProperty

Metadata properties of the tracking entity, trial, or trial component.

modelApprovalStatusOptional
string

The approval status of the model. This can be one of the following values. - `APPROVED` - The model is approved - `REJECTED` - The model is rejected. - `PENDING_MANUAL_APPROVAL` - The model is waiting for manual approval.

modelCardOptional
IResolvable | ModelCardProperty

An Amazon SageMaker Model Card.

modelMetricsOptional
IResolvable | ModelMetricsProperty

Metrics for the model.

modelPackageDescriptionOptional
string

The description of the model package.

modelPackageGroupNameOptional
string

The model group to which the model belongs.

modelPackageNameOptional
string

The name of the model package. The name can be as follows:. - For a versioned model, the name is automatically generated by SageMaker Model Registry and follows the format ' `ModelPackageGroupName/ModelPackageVersion` '. - For an unversioned model, you must provide the name.

modelPackageStatusDetailsOptional
IResolvable | ModelPackageStatusDetailsProperty

Specifies the validation and image scan statuses of the model package.

modelPackageVersionOptional
number

The version number of a versioned model.

samplePayloadUrlOptional
string

The Amazon Simple Storage Service path where the sample payload are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).

securityConfigOptional
IResolvable | SecurityConfigProperty

An optional AWS Key Management Service key to encrypt, decrypt, and re-encrypt model package information for regulated workloads with highly sensitive data.

skipModelValidationOptional
string

Indicates if you want to skip model validation.

sourceAlgorithmSpecificationOptional
IResolvable | SourceAlgorithmSpecificationProperty

A list of algorithms that were used to create a model package.

sourceUriOptional
string

The URI of the source for the model package.

tagsOptional
CfnTag[]

A list of the tags associated with the model package. For more information, see [Tagging AWS resources](https://docs.aws.amazon.com/general/latest/gr/aws_tagging.html) in the *AWS General Reference Guide* .

taskOptional
string

The machine learning task your model package accomplishes. Common machine learning tasks include object detection and image classification.

validationSpecificationOptional
IResolvable | ValidationSpecificationProperty

Specifies batch transform jobs that SageMaker runs to validate your model package.

CloudFormation Resource

This L1 construct maps directly to the following CloudFormation resource type.

AWS::SageMaker::ModelPackageView in CloudFormation Explorer

Learn AWS the Practical Way

Our bi-weekly newsletter teaches hands-on AWS fundamentals. No certification fluff - just practical knowledge.

Subscribe to Newsletter

Quick Facts

LevelL1 (CloudFormation)
Moduleaws-sagemaker
CFN TypeAWS::SageMaker::ModelPackage
Properties27

Related Constructs

Explore This Service

External Links