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

Scaling inference endpoints to meet inference traffic demands

When we need a real-time inference endpoint, the processing power requirements may vary based on incoming traffic. For example, if we are providing air quality inferences for a mobile application, usage will likely fluctuate based on time of day. If we provision the inference endpoint for peak load, we will pay too much during off-peak times. If we provision the inference endpoint for a smaller load, we may hit performance bottlenecks during peak times. We can use inference endpoint auto-scaling to adjust capacity to demand.

There are two types of scaling, vertical and horizontal. Vertical scaling means that we adjust the size of an individual endpoint instance. Horizontal scaling means that we adjust the number of endpoint instances. We prefer horizontal scaling as it results in less disruption for end users; a load balancer can redistribute traffic without having an impact on end users.

There are four steps to configure...