SageMaker Model

An AWS SageMaker Model is a containerized machine learning model that defines how inference should be run in SageMaker. It specifies the location of model artifacts in Amazon S3, the Docker image containing inference code, and optional environment variables. Once created, the model can be deployed to an endpoint for real-time predictions or used in batch transform jobs for offline inference.

aws.sagemaker_model

Fields

TitleIDTypeData TypeDescription
_keycorestring
account_idcorestring
containerscorejsonThe containers in the inference pipeline.
creation_timecoretimestampA timestamp that shows when the model was created.
deployment_recommendationcorejsonA set of recommended deployment configurations for the model.
enable_network_isolationcoreboolIf True, no inbound or outbound network calls can be made to or from the model container.
execution_role_arncorestringThe Amazon Resource Name (ARN) of the IAM role that you specified for the model.
inference_execution_configcorejsonSpecifies details of how containers in a multi-container endpoint are called.
model_arncorestringThe Amazon Resource Name (ARN) of the model.
model_namecorestringName of the SageMaker model.
primary_containercorejsonThe location of the primary inference code, associated artifacts, and custom environment map that the inference code uses when it is deployed in production.
tagscorehstore
vpc_configcorejsonA VpcConfig object that specifies the VPC that this model has access to. For more information, see Protect Endpoints by Using an Amazon Virtual Private Cloud