Book Image

Hands-On Neural Networks with TensorFlow 2.0

By : Paolo Galeone

Book Image

Hands-On Neural Networks with TensorFlow 2.0

By: Paolo Galeone

Overview of this book

TensorFlow, the most popular and widely used machine learning framework, has made it possible for almost anyone to develop machine learning solutions with ease. With TensorFlow (TF) 2.0, you'll explore a revamped framework structure, offering a wide variety of new features aimed at improving productivity and ease of use for developers. This book covers machine learning with a focus on developing neural network-based solutions. You'll start by getting familiar with the concepts and techniques required to build solutions to deep learning problems. As you advance, you’ll learn how to create classifiers, build object detection and semantic segmentation networks, train generative models, and speed up the development process using TF 2.0 tools such as TensorFlow Datasets and TensorFlow Hub. By the end of this TensorFlow book, you'll be ready to solve any machine learning problem by developing solutions using TF 2.0 and putting them into production.

Preface

Who this book is for

What this book covers

To get the most out of this book

Free Chapter

Section 1: Neural Network Fundamentals

Section 1: Neural Network Fundamentals

What is Machine Learning?

What is Machine Learning?

The importance of the dataset

Supervised learning

Unsupervised learning

Semi-supervised learning

Neural Networks and Deep Learning

Neural Networks and Deep Learning

Neural networks

Convolutional neural networks

Section 2: TensorFlow Fundamentals

Section 2: TensorFlow Fundamentals

TensorFlow Graph Architecture

TensorFlow Graph Architecture

Environment setup

Dataflow graphs

Model definition and training

Interacting with the graph using Python

TensorFlow 2.0 Architecture

TensorFlow 2.0 Architecture

Relearning the framework

The Keras framework and its models

Eager execution and new features

Codebase migration

Efficient Data Input Pipelines and Estimator API

Efficient Data Input Pipelines and Estimator API

Efficient data input pipelines

Section 3: The Application of Neural Networks

Section 3: The Application of Neural Networks

Image Classification Using TensorFlow Hub

Image Classification Using TensorFlow Hub

Getting the data

Transfer learning

Introduction to Object Detection

Introduction to Object Detection

Getting the data

Object localization

Classification and localization

Semantic Segmentation and Custom Dataset Builder

Semantic Segmentation and Custom Dataset Builder

Semantic segmentation

Create a TensorFlow DatasetBuilder

Model training and evaluation

Generative Adversarial Networks

Generative Adversarial Networks

Understanding GANs and their applications

Unconditional GANs

Conditional GANs

Bringing a Model to Production

Bringing a Model to Production

The SavedModel serialization format

Python deployment

Supported deployment platforms

Other Books You May Enjoy

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

5 star

0

4 star

0

3 star

0

2 star

0

1 star

0

Efficient Data Input Pipelines and Estimator API

In this chapter, we will look at two of the most common modules of the TensorFlow API: tf.data and tf.estimator.

The TensorFlow 1.x design was so good that almost nothing changed in TensorFlow 2.0; in fact, tf.data and tf.estimator were the first two high-level modules introduced during the life cycle of TensorFlow 1.x.

The tf.data module is a high-level API that allows you to define high-efficiency input pipelines without worrying about threads, queues, synchronization, and distributed filesystems. The API was designed with simplicity in mind to overcome the usability issues of the previous low-level API.

The tf.estimator API was designed to simplify and standardize machine learning programming, allowing to train, evaluate, run inference, and export for serving a parametric model, letting the user focus on the model and input definition...