Hands-On Deep Learning for Images with TensorFlow

About the author
Will Ballard is the chief technology officer at GLG, responsible for engineering and IT. He
was also responsible for the design and operation of large data centers that helped run site
services for customers including Gannett, Hearst Magazines, NFL.com, NPR, The
Washington Post, and Whole Foods. He has also held leadership roles in software
development at NetSolve (now Cisco), NetSpend, and Works.com (now Bank of America).
Packt is searching for authors like you
If you're interested in becoming an author for Packt, please visit 
authors.packtpub.com
and apply today. We have worked with thousands of developers and tech professionals,
just like you, to help them share their insight with the global tech community. You can
make a general application, apply for a specific hot topic that we are recruiting an author
for, or submit your own idea.

---

Table of Contents
Preface
1
Chapter 1: Machine Learning Toolkit
5
Installing Docker
5
The machine learning Docker file
9
Sharing data
13
Machine learning REST service
17
Summary
22
Chapter 2: Image Data
23
MNIST digits
23
Tensors – multidimensional arrays
26
Turning images into tensors
28
Turning categories into tensors
30
Summary
32
Chapter 3: Classical Neural Network
33
Comparison between classical dense neural networks
33
Activation and nonlinearity
35
Softmax
38
Training and testing data
40
Dropout and Flatten
41
Solvers
44
Hyperparameters
46