Hands-On Java Deep Learning for Computer Vision电子书

Title Page

Copyright and Credits

Hands-On Java Deep Learning for Computer Vision

About Packt

Why subscribe?

Packt.com

Contributor

About the author

Packt is searching for authors like you

Preface

Who this book is for

What this book covers

To get the most out of this book

Download the example code files

Download the color images

Conventions used

Get in touch

Reviews

Introduction to Computer Vision and Training Neural Networks

The computer vision state

The importance of data in deep learning algorithms

Exploring neural networks

Building a single neuron

Building a single neuron with multiple outputs

Building a neural network

How does a neural network learn?

Learning neural network weights

Updating the neural network weights

Advantages of deep learning

Organizing data and applications

Organizing your data

Bias and variance

Computational model efficiency

Effective training techniques

Initializing the weights

Activation functions

Optimizing algorithms

Configuring the training parameters of the neural network

Representing images and outputs

Multiclass classification

Building a handwritten digit recognizer

Testing the performance of the neural network

Summary

Convolutional Neural Network Architectures

Understanding edge detection

What is edge detection?

Vertical edge detection

Horizontal edge detection

Edge detection intuition

Building a Java edge detection application

Types of filters

Basic coding

Convolution on RGB images

Working with convolutional layers' parameters

Padding

Stride

Pooling layers

Max pooling

Average pooling

Pooling on RGB images

Pooling characteristics

Building and training a Convolution Neural Network

Why convolution?

Improving the handwritten digit recognition application

Summary

Transfer Learning and Deep CNN Architectures

Working with classical networks

LeNet-5

AlexNet

VGG-16

Using residual networks for image recognition

Deep network performance

ResNet-50

The power of 1 x 1 convolutions and the inception network

Applying transfer learning

Neural networks

Building an animal image classification – using transfer learning and VGG-16 architecture

Summary

Real-Time Object Detection

Resolving object localization

Labeling and defining data for localization

Object localization prediction layer

Landmark detection

Object detection with the sliding window solution

Disadvantages of sliding windows

Convolutional sliding window

Detecting objects with the YOLO algorithm

Max suppression and anchor boxes

Max suppression

Anchor boxes

Building a real-time video, car, and pedestrian detection application

Architecture of the application

YOLO V2-optimized architecture

Coding the application

Summary

Creating Art with Neural Style Transfer

What are convolution network layers learning?

Neural style transfer

Minimizing the cost function

Applying content cost function

Applying style cost function

How to capture the style

Style cost function

Building a neural network that produces art

Summary

Face Recognition

Problems in face detection

Face verification versus face recognition

Face verification

Face recognition

One-shot learning problem

Similarity function

Differentiating inputs with Siamese networks

Learning with Siamese networks

Exploring triplet loss

Choosing the triplets

Binary classification

Binary classification cost function

Building a face recognition Java application

Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think