Supercharge your skills for developing powerful deep learning models and distributing them at scale efficiently using cloud services

Key Features

• Understand how to execute a deep learning project effectively using various tools available
• Learn how to develop PyTorch and TensorFlow models at scale using Amazon Web Services
• Explore effective solutions to various difficulties that arise from model deployment

Book Description

Machine learning engineers, deep learning specialists, and data engineers encounter various problems when moving deep learning models to a production environment. The main objective of this book is to close the gap between theory and applications by providing a thorough explanation of how to transform various models for deployment and efficiently distribute them with a full understanding of the alternatives.

First, you will learn how to construct complex deep learning models in PyTorch and TensorFlow. Next, you will acquire the knowledge you need to transform your models from one framework to the other and learn how to tailor them for specific requirements that deployment environments introduce. The book also provides concrete implementations and associated methodologies that will help you apply the knowledge you gain right away. You will get hands-on experience with commonly used deep learning frameworks and popular cloud services designed for data analytics at scale. Additionally, you will get to grips with the authors' collective knowledge of deploying hundreds of AI-based services at a large scale.

By the end of this book, you will have understood how to convert a model developed for proof of concept into a production-ready application optimized for a particular production setting.

What you will learn

• Understand how to develop a deep learning model using PyTorch and TensorFlow
• Convert a proof-of-concept model into a production-ready application
• Discover how to set up a deep learning pipeline in an efficient way using AWS
• Explore different ways to compress a model for various deployment requirements
• Develop Android and iOS applications that run deep learning on mobile devices
• Monitor a system with a deep learning model in production
• Choose the right system architecture for developing and deploying a model

Who this book is for

Machine learning engineers, deep learning specialists, and data scientists will find this book helpful in closing the gap between the theory and application with detailed examples. Beginner-level knowledge in machine learning or software engineering will help you grasp the concepts covered in this book easily.

Table of Contents

1. Effective Planning of Deep Learning-Driven Projects
2. Data Preparation for Deep Learning Projects
3. Developing a Powerful Deep Learning Model
4. Experiment Tracking, Model Management, and Dataset Versioning
5. Data Preparation in the Cloud
6. Efficient Model Training
7. Revealing the Secret of Deep Learning Models
8. Simplifying Deep Learning Model Deployment
9. Scaling a Deep Learning Pipeline
10. Improving Inference Efficiency
11. Deep Learning on Mobile Devices
12. Monitoring Deep Learning Endpoints in Production
13. Reviewing the Completed Deep Learning Project

About the Authors

Tomasz Palczewski is currently working as a staff software engineer at Samsung Research America. He has a Ph.D. in physics and an eMBA degree from Quantic. His zeal for getting insights out of large datasets using cutting-edge techniques led him to work across the globe at CERN (Switzerland), LBNL (Italy), J-PARC (Japan), University of Alabama (US), and University of California (US). In 2016, he was deployed to the South Pole to calibrate the world's largest neutrino telescope. Later, he decided to pivot his career and focus on applying his skills in industry. Currently, he works on modeling user behavior and creating value for advertising and marketing verticals by deploying machine learning (ML), deep learning, and statistical models at scale.

Jaejun (Brandon) Lee is currently working as an AI research lead at RoboEye.ai, integrating cutting-edge algorithms in computer vision and AI into industrial automation solutions. He has obtained his master’s degree from the University of Waterloo with research focused on natural language processing (NLP), specifically speech recognition. He has spent many years developing a fully productionized yet open source wake word detection toolkit with a web browser deployment target, Howl. Luckily, his effort has been picked up by Mozilla's Firefox Voice and it is actively providing a completely hands-free experience to many users all over the world.

Lenin Mookiah is a machine learning engineer who has worked with reputed tech companies – Samsung Research America, eBay Inc., and Adobe R&D. He has worked in the technology industry for over 11 years in various domains: banking, retail, eDiscovery, and media. He has played various roles in the end-to-end productization of large-scale machine learning systems. He mainly employs the big data ecosystem to build reliable feature pipelines that data scientists consume. Apart from his industrial experience, he researched anomaly detection in his Ph.D. at Tennessee Tech University (US) using a novel graph-based approach. He studied entity resolution on social networks during his master’s at Tsinghua University, China.