Book Image

Amazon SageMaker Best Practices

By : Sireesha Muppala, Randy DeFauw, Shelbee Eigenbrode
Book Image

Amazon SageMaker Best Practices

By: Sireesha Muppala, Randy DeFauw, Shelbee Eigenbrode

Overview of this book

Amazon SageMaker is a fully managed AWS service that provides the ability to build, train, deploy, and monitor machine learning models. The book begins with a high-level overview of Amazon SageMaker capabilities that map to the various phases of the machine learning process to help set the right foundation. You'll learn efficient tactics to address data science challenges such as processing data at scale, data preparation, connecting to big data pipelines, identifying data bias, running A/B tests, and model explainability using Amazon SageMaker. As you advance, you'll understand how you can tackle the challenge of training at scale, including how to use large data sets while saving costs, monitoring training resources to identify bottlenecks, speeding up long training jobs, and tracking multiple models trained for a common goal. Moving ahead, you'll find out how you can integrate Amazon SageMaker with other AWS to build reliable, cost-optimized, and automated machine learning applications. In addition to this, you'll build ML pipelines integrated with MLOps principles and apply best practices to build secure and performant solutions. By the end of the book, you'll confidently be able to apply Amazon SageMaker's wide range of capabilities to the full spectrum of machine learning workflows.
Table of Contents (20 chapters)
Section 1: Processing Data at Scale
Section 2: Model Training Challenges
Section 3: Manage and Monitor Models
Section 4: Automate and Operationalize Machine Learning

Basic concepts of Amazon SageMaker Endpoint Production Variants

In this section, you will review the basics of deploying and updating ML models using SageMaker Endpoint Production Variants. There are two ways you can deploy a machine learning model using SageMaker: by using a real-time endpoint for low latency live predictions or a batch transform for making asynchronous predictions on large numbers of inference requests. Production Variants can be applied to real-time endpoints.

Deploying a real-time endpoint involves two steps:

  1. Creating an Endpoint Configuration

    An endpoint configuration identifies one or more Production Variants. Each production variant indicates a model and infrastructure to deploy the model on.

  2. Creating an Endpoint Pointing to the Endpoint Configuration

    Endpoint creation results in an HTTPS endpoint that the model consumers can use to invoke the model.

The following diagram shows two different endpoint configurations with Production Variants...