Book Overview & Buying
Table Of Contents
Feedback & Rating

Practical Convolutional Neural Networks

By : Mohit Sewak, Karim, Pradeep Pujari

1.5 (6)

Buy this Book

Practical Convolutional Neural Networks

1.5 (6)

By: Mohit Sewak, Karim, Pradeep Pujari

Buy this Book

Overview of this book

Convolutional Neural Network (CNN) is revolutionizing several application domains such as visual recognition systems, self-driving cars, medical discoveries, innovative eCommerce and more.You will learn to create innovative solutions around image and video analytics to solve complex machine learning and computer vision related problems and implement real-life CNN models. This book starts with an overview of deep neural networkswith the example of image classification and walks you through building your first CNN for human face detector. We will learn to use concepts like transfer learning with CNN, and Auto-Encoders to build very powerful models, even when not much of supervised training data of labeled images is available. Later we build upon the learning achieved to build advanced vision related algorithms for object detection, instance segmentation, generative adversarial networks, image captioning, attention mechanisms for vision, and recurrent models for vision. By the end of this book, you should be ready to implement advanced, effective and efficient CNN models at your professional project or personal initiatives by working on complex image and video datasets.

Preface

Who this book is for

What this book covers

To get the most out of this book

Get in touch

Free Chapter

Deep Neural Networks – Overview

Building blocks of a neural network

Introduction to TensorFlow

Introduction to the MNIST dataset

Keras deep learning library overview

Handwritten number recognition with Keras and MNIST

Understanding backpropagation

Summary

Introduction to Convolutional Neural Networks

History of CNNs

Convolutional neural networks

Practical example – image classification

Summary

Build Your First CNN and Performance Optimization

CNN architectures and drawbacks of DNNs

Convolution and pooling operations in TensorFlow

Training a CNN

Building, training, and evaluating our first CNN

Model performance optimization

Summary

Popular CNN Model Architectures

Introduction to ImageNet

LeNet

AlexNet architecture

VGGNet architecture

GoogLeNet architecture

ResNet architecture

Summary

Transfer Learning

Feature extraction approach

Transfer learning example

Multi-task learning

Summary

Autoencoders for CNN

Introducing to autoencoders

Convolutional autoencoder

Applications

Summary

Object Detection and Instance Segmentation with CNN

The differences between object detection and image classification

Traditional, nonCNN approaches to object detection

R-CNN – Regions with CNN features

Fast R-CNN – fast region-based CNN

Faster R-CNN – faster region proposal network-based CNN

Mask R-CNN – Instance segmentation with CNN

Instance segmentation in code

References

Summary

GAN: Generating New Images with CNN

Pix2pix - Image-to-Image translation GAN

GAN – code example

Feature matching

Summary

Attention Mechanism for CNN and Visual Models

Attention mechanism for image captioning

Types of Attention

Using attention to improve visual models

References

Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

1.5 (6)

5 star

4 star

16.7%

3 star

2 star

1 star

83.3%

AlexNet architecture

The first breakthrough in the architecture of CNN came in the year 2012. This award-winning CNN architecture is called AlexNet. It was developed at the University of Toronto by Alex Krizhevsky and his professor, Jeffry Hinton.

In the first run, a ReLU activation function and a dropout of 0.5 were used in this network to fight overfitting. As we can see in the following image, there is a normalization layer used in the architecture, but this is not used in practice anymore as it used heavy data augmentation. AlexNet is still used today even though there are more accurate networks available, because of its relative simple structure and small depth. It is widely used in computer vision:

AlexNet is trained on the ImageNet database using two separate GPUs, possibly due to processing limitations with inter-GPU connections at the time, as shown in the...