Book Image

What's New in TensorFlow 2.0

By : Ajay Baranwal, Alizishaan Khatri, Tanish Baranwal
Book Image

What's New in TensorFlow 2.0

By: Ajay Baranwal, Alizishaan Khatri, Tanish Baranwal

Overview of this book

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.
Table of Contents (13 chapters)
Title Page

Inference in the browser

As you might recall, in an earlier section, we briefly discussed distributed systems. There, we discussed the scenario where the machine learning-based computation is primarily performed on host servers. Here, we will look at the scenario where these computations are performed on the user side, in the browser. Two significant advantages of doing this are as follows:

  • Compute gets pushed to the user side. Hosts do not have to worry about managing servers for performing computations.
  • Pushing models to the user side means that user data doesn't have to be sent to the host. This is a huge advantage for applications that work with sensitive or private user data. Inference in the browser hence becomes an excellent choice for privacy-critical machine learning applications:

The workflow described in the preceding diagram illustrates the end-to-end pipeline...