You're reading from Amazon SageMaker Best Practices Proven tips and tricks to build successful machine learning solutions on Amazon SageMaker

Product type Paperback

Published in Sep 2021

Publisher Packt

ISBN-13 9781801070522

Length 348 pages

Edition 1st Edition

Languages

Python

Tools

Amazon SimpleDB

Concepts

Machine Learning

Authors (3):

Randy DeFauw

Shelbee Eigenbrode

Sireesha Muppala

View More author details

Table of Contents (20) Chapters

Preface

1. Section 1: Processing Data at Scale

2. Chapter 1: Amazon SageMaker Overview FREE CHAPTER

3. Chapter 2: Data Science Environments

4. Chapter 3: Data Labeling with Amazon SageMaker Ground Truth

5. Chapter 4: Data Preparation at Scale Using Amazon SageMaker Data Wrangler and Processing

6. Chapter 5: Centralized Feature Repository with Amazon SageMaker Feature Store

7. Section 2: Model Training Challenges

8. Chapter 6: Training and Tuning at Scale

9. Chapter 7: Profile Training Jobs with Amazon SageMaker Debugger

10. Section 3: Manage and Monitor Models

11. Chapter 8: Managing Models at Scale Using a Model Registry

12. Chapter 9: Updating Production Models Using Amazon SageMaker Endpoint Production Variants

13. Chapter 10: Optimizing Model Hosting and Inference Costs

14. Chapter 11: Monitoring Production Models with Amazon SageMaker Model Monitor and Clarify

15. Section 4: Automate and Operationalize Machine Learning

16. Chapter 12: Machine Learning Automated Workflows

17. Chapter 13:Well-Architected Machine Learning with Amazon SageMaker

18. Chapter 14: Managing SageMaker Features across Accounts

19. Other Books You May Enjoy

Using Elastic Inference for deep learning models

If you examine the overall cost of ML, you may be surprised to see that the bulk of your monthly cost comes from real-time inference endpoints. Training jobs, while potentially resource-intensive, run for some time and then terminate. Managed notebook instances can be shut down during off hours. But inference endpoints run 24 hours a day, 7 days a week. If you are using a deep learning model, inference endpoint costs become more pronounced, as instances with dedicated GPU capacity are more expensive than other comparable instances.

When you obtain inferences from a deep learning model, you do not need as much GPU capacity as you need during training. Elastic Inference lets you attach fractional GPU capacity to regular EC2 instances or Elastic Container Service (ECS) containers. As a result, you can get deep learning inferences quickly at a reduced cost.

The Elastic Inference section in the notebook shows how to attach an Elastic...