Book Image

Hands-On Deep Learning for Images with TensorFlow

By : Will Ballard
Book Image

Hands-On Deep Learning for Images with TensorFlow

By: Will Ballard

Overview of this book

TensorFlow is Google’s popular offering for machine learning and deep learning, quickly becoming a favorite tool for performing fast, efficient, and accurate deep learning tasks. Hands-On Deep Learning for Images with TensorFlow shows you the practical implementations of real-world projects, teaching you how to leverage TensorFlow’s capabilities to perform efficient image processing using the power of deep learning. With the help of this book, you will get to grips with the different paradigms of performing deep learning such as deep neural nets and convolutional neural networks, followed by understanding how they can be implemented using TensorFlow. By the end of this book, you will have mastered all the concepts of deep learning and their implementation with TensorFlow and Keras.

Related Content you might be interested in

Current Title:

Small book image
Hands-On Deep Learning for Images with TensorFlow
Will Ballard
Jul, 2018 | 96 pages
Small book image
Hands-On Deep Learning with TensorFlow
Dan Van Boxel
Jul, 2017 | 174 pages
Small book image
Keras Deep Learning Cookbook
Manpreet Singh Ghotra | Rajdeep Dua
Oct, 2018 | 252 pages
Small book image
TensorFlow 2.0 Quick Start Guide
Tony Holdroyd
Mar, 2019 | 196 pages
Table of Contents (7 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
Free Chapter
1
Machine Learning Toolkit
Machine Learning Toolkit
Installing Docker
The machine learning Docker file
Sharing data
Machine learning REST service
Summary
2
Image Data
Image Data
MNIST digits
Tensors – multidimensional arrays
Turning images into tensors
Turning categories into tensors
Summary
3
Classical Neural Network
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
4
A Convolutional Neural Network
A Convolutional Neural Network
Convolutions
Pooling
Building a convolutional neural network
Deep neural network
Summary
5
An Image Classification Server
An Image Classification Server
REST API definition
Trained models in Docker containers
Making predictions
Summary
6
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Hyperparameters

In this section, we'll explore hyperparameters, or parameters that can't quite be machine learned.

We'll also cover trainable parameters (these are the parameters that are learned by the solver), nontrainable parameters (additional parameters in the models that don't require training), and then finally, hyperparameters (parameters that aren't learned by a traditional solver).

In our Model summary output screenshot, pay attention to the number of trainable parameters in the highlighted section of code at the bottom of the screenshot. That is the number of individual floating-point numbers that are contained inside of our model that our adam optimizer, in conjunction with our categorical cross-entropy loss function, will be exploring in order to find the best parameter values possible. So, this trainable parameter number is the only set of...

Previous Section
End of Section 8
Next Section