Use your own inference code

You can use Amazon SageMaker to interact with Docker containers and run your own inference code in one of two ways:

• To use your own inference code with a persistent endpoint to get one prediction at a time, use SageMaker hosting services.

• To use your own inference code to get predictions for an entire dataset, use SageMaker batch transform.

Topics

• Use Your Own Inference Code with Hosting Services
• Use Your Own Inference Code with Batch Transform