The following diagram shows how you train and deploy a model with Amazon SageMaker. Your training code accesses your training data and outputs model artifacts from an S3 bucket. Then you can make requests to a model endpoint to run inference. You can store both the training and inference container images in an Amazon Elastic Container Registry (ECR).

Learn more about how to get inferences from your Amazon SageMaker models and deploy your models for serving inference.

Configure Amazon EC2 to meet your security and compliance objectives, and learn how to use other AWS services that help you to secure your Amazon EC2 resources.

Find an Amazon EC2 instance to match the features that you need.

Attach a network interface to your instance to specify its private IP addresses, Elastic IP addresses, and security groups.

Your AWS account automatically has a default security group for the default VPC in each Region. If you don't specify a security group when you launch an instance, the instance is automatically associated with the default security group for the VPC. If you don't want your instances to use the default security group, you can create your own custom security groups and specify them when you launch your instances.

Learn how the AWS shared responsibility model applies to data protection in Amazon Elastic Compute Cloud.

Add rules to your security group for specific kinds of access.

View your current quotas (also referred to as limits) for Amazon EC2 and request increases in these quotes as needed.

Use these instances for baseline performance and the ability to burst to higher performance as required by your workload.