What's New in TensorFlow 2.0

Get to grips with key structural changes in TensorFlow 2.0

Key Features

• Explore TF Keras APIs and strategies to run GPUs, TPUs, and compatible APIs across the TensorFlow ecosystem
• Learn and implement best practices for building data ingestion pipelines using TF 2.0 APIs
• Migrate your existing code from TensorFlow 1.x to TensorFlow 2.0 seamlessly

Book Description

TensorFlow is an end-to-end machine learning platform for experts as well as beginners, and its new version, TensorFlow 2.0 (TF 2.0), improves its simplicity and ease of use. This book will help you understand and utilize the latest TensorFlow features.

What's New in TensorFlow 2.0 starts by focusing on advanced concepts such as the new TensorFlow Keras APIs, eager execution, and efficient distribution strategies that help you to run your machine learning models on multiple GPUs and TPUs. The book then takes you through the process of building data ingestion and training pipelines, and it provides recommendations and best practices for feeding data to models created using the new tf.keras API. You'll explore the process of building an inference pipeline using TF Serving and other multi-platform deployments before moving on to explore the newly released AIY, which is essentially do-it-yourself AI. This book delves into the core APIs to help you build unified convolutional and recurrent layers and use TensorBoard to visualize deep learning models using what-if analysis.

By the end of the book, you'll have learned about compatibility between TF 2.0 and TF 1.x and be able to migrate to TF 2.0 smoothly.

What you will learn

• Implement tf.keras APIs in TF 2.0 to build, train, and deploy production-grade models
• Build models with Keras integration and eager execution
• Explore distribution strategies to run models on GPUs and TPUs
• Perform what-if analysis with TensorBoard across a variety of models
• Discover Vision Kit, Voice Kit, and the Edge TPU for model deployments
• Build complex input data pipelines for ingesting large training datasets

Who this book is for

If you re a data scientist, machine learning practitioner, deep learning researcher, or AI enthusiast who wants to migrate code to TensorFlow 2.0 and explore the latest features of TensorFlow 2.0, this book is for you. Prior experience with TensorFlow and Python programming is necessary to understand the concepts covered in the book.

Table of Contents

1. Getting Started with TensorFlow 2.0
2. Keras Default Integration and Eager Execution
3. Design and Construct Input Data Pipelines
4. Model Training and Use of Tensorboard
5. Model Inference Pipelines: Multi-platform Deployments
6. AIY Projects and TensorFlow Lite
7. Migrating from TensorFlow 1.x to 2.0

Ajay Baranwal works as a director at the Center for Deep Learning in Electronics Manufacturing, where he is responsible for researching and developing TensorFlow-based deep learning applications in the semiconductor and electronics manufacturing industry. Part of his role is to teach and train deep learning techniques to professionals.

He has a solid history of software engineering and management, where he got hooked on deep learning. He moved to natural language understanding (NLU) to pursue deep learning further at Abzooba and built an information retrieval system for the finance sector. He has also worked at Ansys Inc. as a senior manager (engineering) and a technical fellow (data science) and introduced several ML applications.

Alizishaan Khatri works as a machine learning engineer in Silicon Valley. He uses TensorFlow to build, design, and maintain production-grade systems that use deep learning for NLP applications. A major system he has built is a deep learning-based system for detecting offensive content in chats. Other works he has done includes text classification and named entity recognition (NER) systems for different use cases. He is passionate about sharing ideas with the community and frequently speaks at tech conferences across the globe.

He holds a master's degree in computer science from the SUNY Buffalo University. His thesis proposed a solution to the problem of overfitting in deep learning. Outside of his work, he enjoys skiing and mountaineering.

Tanish Baranwal is a sophomore in high school and lives in California with his family and has worked with his dad on deep learning projects using TensorFlow for the last 3 years. He has been coding for 9 years (since 1st grade) and is well versed in Python and JavaScript. He is now learning C++. He has certificates from various online courses and has won the Entrepreneurship Showcase Award at his school.

Some of his deep learning projects include anomaly detection systems for transaction fraud, a system to save energy by turning off domestic water heaters when not in use, and a fully functional style transfer program that can recreate any photograph in another style. He has also written blogs on deep learning on Medium with over 1,000 views.