Hands-On Deep Learning for Images with TensorFlow

Grid searches
47
Summary
51
Chapter 4: A Convolutional Neural Network
52
Convolutions
52
Pooling
55
Building a convolutional neural network
58
Deep neural network
61
Summary
66
Chapter 5: An Image Classification Server
67
REST API definition
67
Trained models in Docker containers
72
Making predictions
77
Summary
80

---

Table of Contents
[ ii ]
Other Books You May Enjoy
81
Index
84

---

Preface
TensorFlow is Google's popular offering for machine learning and deep learning. It has
quickly become a popular choice of tool for performing fast, efficient, and accurate deep
learning tasks.
This book shows you practical implementations of real-world projects, teaching you how to
leverage TensorFlow's capabilities to perform efficient deep learning. In this book, you will
be acquainted with the different paradigms of performing deep learning, such as deep
neural nets, convolutional neural networks, recurrent neural networks, and more, and how
they can be implemented using TensorFlow.
This will be demonstrated with the help of end-to-end implementations of three real-world
projects on popular topic areas such as natural language processing, image classification,
and fraud detection.
By the end of this book, you will have mastered all the concepts of deep learning and their
implementations with TensorFlow and Keras.
Who this book is for
This book is for application developers, data scientists, and machine learning practitioners
looking to integrate machine learning into application software and master deep learning
by implementing practical projects in TensorFlow. Knowledge of Python programming and
the basics of deep learning is required to get the most out of this book.