What do you get with eBook?

Instant access to your Digital eBook purchase

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

AI Assistant (beta) to help accelerate your learning

Key benefits

Learn best practices about bringing your models to production

Explore the tools available for serving ML models and the differences between them

Understand state-of-the-art monitoring approaches for model serving implementations

Description

Serving patterns enable data science and ML teams to bring their models to production. Most ML models are not deployed for consumers, so ML engineers need to know the critical steps for how to serve an ML model. This book will cover the whole process, from the basic concepts like stateful and stateless serving to the advantages and challenges of each. Batch, real-time, and continuous model serving techniques will also be covered in detail. Later chapters will give detailed examples of keyed prediction techniques and ensemble patterns. Valuable associated technologies like TensorFlow severing, BentoML, and RayServe will also be discussed, making sure that you have a good understanding of the most important methods and techniques in model serving. Later, you’ll cover topics such as monitoring and performance optimization, as well as strategies for managing model drift and handling updates and versioning. The book will provide practical guidance and best practices for ensuring that your model serving pipeline is robust, scalable, and reliable. Additionally, this book will explore the use of cloud-based platforms and services for model serving using AWS SageMaker with the help of detailed examples. By the end of this book, you'll be able to save and serve your model using state-of-the-art techniques.

Who is this book for?

This book is for machine learning engineers and data scientists who want to bring their models into production. Those who are familiar with machine learning and have experience of using machine learning techniques but are looking for options and strategies to bring their models to production will find great value in this book. Working knowledge of Python programming is a must to get started.

What you will learn

Explore specific patterns in model serving that are crucial for every data science professional

Understand how to serve machine learning models using different techniques

Discover the various approaches to stateless serving

Implement advanced techniques for batch and streaming model serving

Get to grips with the fundamental concepts in continued model evaluation

Serve machine learning models using a fully managed AWS Sagemaker cloud solution

What do you get with eBook?

Instant access to your Digital eBook purchase

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

AI Assistant (beta) to help accelerate your learning

Frequently bought together

$46.99

Machine Learning Model Serving Patterns and Best Practices

$41.99

Applied Machine Learning and High-Performance Computing on AWS

$46.99

Total $ 135.97

HB Feb 12, 2023

This book is ideal for ML engineers and data scientists who want to bring their models into production and have a working knowledge of Python programming.The Github repository provided by the publisher is a great resource, with organized code and helpful examples.Overall, a highly recommended resource for anyone looking to learn more about ML model serving.

Amazon Verified review

Shesh Narayan May 13, 2023

This book is a comprehensive guide to the process of serving machine learning models in production. It covers a wide range of topics, from the basics of model serving to more advanced concepts such as ensemble modeling and cloud-based solutions. The book is well-written and easy to follow, and it includes numerous examples and illustrations.One of the strengths of this book is its focus on patterns. The author identifies a number of common patterns that are used in model serving, and he provides detailed explanations of each pattern. This makes it easier for readers to understand the different approaches to model serving and to choose the right approach for their specific needs.Another strength of this book is its coverage of cloud-based solutions. The author provides detailed instructions on how to use a number of popular cloud-based platforms for model serving, such as Amazon SageMaker and Google Cloud Platform. This makes it easy for readers to get started with cloud-based model serving, even if they have no prior experience with cloud computing.Overall, this is an excellent book for anyone who wants to learn more about model serving. It is well-written, comprehensive, and informative. I highly recommend it to anyone who is involved in the development or deployment of machine learning models.Here are some additional thoughts about the book:1.The book is well-organized and easy to follow. The chapters are well-structured and the information is presented in a clear and concise manner.2.The book is comprehensive and covers a wide range of topics related to model serving. The author does a good job of explaining the different concepts and providing examples to illustrate his points.3.The book is up-to-date and includes information on the latest trends in model serving. The author does a good job of discussing the challenges and opportunities associated with model serving in the cloud.4.The book is well-written and easy to read. The author has a good writing style and he does a good job of explaining complex concepts in a way that is easy to understand.Overall, I highly recommend this book to anyone who is interested in learning more about model serving. It is a comprehensive and well-written resource that will provide you with the knowledge and skills you need to successfully deploy machine learning models in production.

Amazon Verified review

Steven Fernandes Apr 01, 2023

In this comprehensive guide to model serving, the author expertly navigates the essential concepts and techniques required for deploying ML models in production. The book begins by introducing stateful and stateless serving, highlighting the pros and cons of each. It then delves into various serving techniques such as batch, real-time, and continuous, providing valuable insights on keyed prediction and ensemble patterns.The author discusses vital technologies like TensorFlow Serving, BentoML, and RayServe, equipping readers with a solid understanding of the most important methods in the field. The book also addresses monitoring, performance optimization, model drift management, and versioning, sharing practical guidance and best practices for robust, scalable, and reliable pipelines. The exploration of cloud-based platforms, specifically AWS SageMaker, enhances the text with detailed examples, making it an invaluable resource for ML engineers and data science teams.

Amazon Verified review

Giang Nguyen Mar 10, 2023

"Machine Learning Model Serving Patterns and Best Practices" is an excellent resource for anyone looking to deploy and manage machine learning models in production environments. The authors have done an excellent job of covering all the essential aspects of model serving, from understanding the challenges of model deployment to implementing best practices for monitoring and accessibility.The book is well-organized and comprehensive, with each chapter covering a specific topic related to model serving. The authors provide clear explanations of technical concepts and offer practical advice and real-world examples that are valuable for both beginners and experienced practitioners. I believe that the book is a valuable resource for anyone involved in deploying and managing machine learning models in production environments. Highly recommended!

Amazon Verified review

Dror May 24, 2023

Software is eating the world, and in this post-ChatGPT era, it seems that more than ever before, artificial intelligence (AI) is eating software. While there are many excellent guides to AI model training, the complementary skill of model serving - the deployment of models in production - remains much harder to learn and master, despite its importance.This book does a wonderful job in bridging this gap, and serves as a practical and comprehensive guide to AI model serving. It provides a broad and deep hands-on overview on model deployment in production, and covers the most common and important serving use cases and patterns. It begins with an introduction to model serving, followed by a detailed coverage of serving patterns and best practices. These include stateless model serving, continuous model evaluation, batch and online model serving, and the pipeline and ensemble model serving patterns.A variety of useful tools for AI model serving are also described in detail, including TensorFlow Serving, Ray Serve and BentoML. The last chapter of the book provides helpful coverage of model serving in a fully-managed cloud environment on the most popular cloud platform - AWS SageMaker.This practical guide will benefit any machine learning engineer, data scientist, MLOps or software engineer whose work involves serving models in production. Note that the book does not delve into model training (to which many excellent guides already exist), and assumes some familiarity with the Python programming language. The provided code examples in the accompanying GitHub repo are very helpful as well.Highly recommended!

Amazon Verified review

Machine Learning Model Serving Patterns and Best Practices: A definitive guide to deploying, monitoring, and providing accessibility to ML models in production

What do you get with eBook?

Key benefits

Description

Who is this book for?

What you will learn

Product Details

What do you get with eBook?

Product Details

Frequently bought together

Recommendations for you

Customer reviews

Filter reviews by

People who bought this also bought

About the author

FAQs

Machine Learning Model Serving Patterns and Best Practices: A definitive guide to deploying, monitoring, and providing accessibility to ML models in production

What do you get with eBook?

Contact Details

Billing Address

Key benefits

Description

Who is this book for?

What you will learn

Product Details

What do you get with eBook?

Contact Details

Billing Address

Product Details

Packt Subscriptions

Frequently bought together

Recommendations for you

Customer reviews

Filter reviews by

People who bought this also bought

About the author

FAQs