Book Image

Learn Amazon SageMaker

By : Julien Simon
Book Image

Learn Amazon SageMaker

By: Julien Simon

Overview of this book

Amazon SageMaker enables you to quickly build, train, and deploy machine learning (ML) models at scale, without managing any infrastructure. It helps you focus on the ML problem at hand and deploy high-quality models by removing the heavy lifting typically involved in each step of the ML process. This book is a comprehensive guide for data scientists and ML developers who want to learn the ins and outs of Amazon SageMaker. You’ll understand how to use various modules of SageMaker as a single toolset to solve the challenges faced in ML. As you progress, you’ll cover features such as AutoML, built-in algorithms and frameworks, and the option for writing your own code and algorithms to build ML models. Later, the book will show you how to integrate Amazon SageMaker with popular deep learning libraries such as TensorFlow and PyTorch to increase the capabilities of existing models. You’ll also learn to get the models to production faster with minimum effort and at a lower cost. Finally, you’ll explore how to use Amazon SageMaker Debugger to analyze, detect, and highlight problems to understand the current model state and improve model accuracy. By the end of this Amazon book, you’ll be able to use Amazon SageMaker on the full spectrum of ML workflows, from experimentation, training, and monitoring to scaling, deployment, and automation.
Table of Contents (19 chapters)
Section 1: Introduction to Amazon SageMaker
Section 2: Building and Training Models
Section 3: Diving Deeper on Training
Section 4: Managing Models in Production

Deploying a multi-model endpoint

Multi-model endpoints are useful when you're dealing with a large number of models that it wouldn't make sense to deploy to individual endpoints. For example, imagine an SaaS company building a regression model for each one of their 10,000 customers. Surely they wouldn't want to manage (and pay for) 10,000 endpoints!

Understanding multi-model endpoints

A multi-model endpoint can serve CPU-based predictions from an arbitrary number of models stored in S3 (GPUs are not supported at the time of writing). The path of the model artifact to use is passed in each prediction request. Models are loaded and unloaded dynamically, according to usage and to the amount of memory available on the endpoint. Models can also be added to, or removed, from the endpoint by simply copying or deleting artifacts in S3.

In order to serve multiple models, your inference container must implement a specific set of APIs that the endpoint will invoke: LOAD...