Hands-On Deep Learning for Images with TensorFlow

A
activation
C
categories
classical neural network
convolutional neural network
convolutions
D
data
, 
testing
deep neural network
, 
dense neural network
versus classical neural network
Docker container
, 
used, for executing REST server
, 
Docker
, 
, 
URL, for installation
F
G
grid searches
, 
H
I
images
turning, into tensors
, 
Intel Math Kernal Libraries
M
, 
, 
, 
, 
, 
N
, 
O
Optical Character Recognition (OCR)
overfitting
P
pooling
R
REST API
defining
S
solvers
T
tensors
, 

---

categories, turning into
30
, 
31
images, turning into
28

---

Document Outline

• Cover
• Title Page
• Copyright and Credits
• Packt Upsell
• Contributors
• Table of Contents
• Preface
• Chapter 1: Machine Learning Toolkit
  • Installing Docker
  • The machine learning Docker file
  • Sharing data
  • Machine learning REST service
  • Summary
• Chapter 2: Image Data
  • MNIST digits
  • Tensors – multidimensional arrays
  • Turning images into tensors
  • Turning categories into tensors
  • Summary
• Chapter 3: Classical Neural Network
  • Comparison between classical dense neural networks
  • Activation and nonlinearity
  • Softmax
  • Training and testing data
  • Dropout and Flatten
  • Solvers
  • Hyperparameters
  • Grid searches
  • Summary
• Chapter 4: A Convolutional Neural Network
  • Convolutions
  • Pooling
  • Building a convolutional neural network
  • Deep neural network
  • Summary
• Chapter 5: An Image Classification Server
  • REST API definition
  • Trained models in Docker containers
  • Making predictions
  • Summary
• Other Books You May Enjoy
• Index