Book Image

Practical Convolutional Neural Networks

By : Mohit Sewak, Md. Rezaul Karim, Pradeep Pujari
Book Image

Practical Convolutional Neural Networks

By: Mohit Sewak, Md. Rezaul Karim, Pradeep Pujari

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.

Related Content you might be interested in

Current Title:

Small book image
Practical Convolutional Neural Networks
Mohit Sewak | Md. Rezaul Karim | Pradeep Pujari
Feb, 2018 | 218 pages
Small book image
Predictive Analytics with TensorFlow
Md Rezaul Karim
Nov, 2017 | 522 pages
Small book image
Neural Network Programming with Tensorflow
Manpreet Singh Ghotra | Rajdeep Dua
Nov, 2017 | 274 pages
Small book image
Deep Learning By Example
Ahmed Menshawy
Feb, 2018 | 450 pages
Table of Contents (11 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
Deep Neural Networks – Overview
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
2
Introduction to Convolutional Neural Networks
Introduction to Convolutional Neural Networks
History of CNNs
Convolutional neural networks
Practical example – image classification
Summary
3
Build Your First CNN and Performance Optimization
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
4
Popular CNN Model Architectures
Popular CNN Model Architectures
Introduction to ImageNet
LeNet
AlexNet architecture
VGGNet architecture
GoogLeNet architecture
ResNet architecture
Summary
5
Transfer Learning
Transfer Learning
Feature extraction approach
Transfer learning example
Multi-task learning
Summary
6
Autoencoders for CNN
Autoencoders for CNN
Introducing to autoencoders
Convolutional autoencoder
Applications
Summary
7
Object Detection and Instance Segmentation with CNN
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
8
GAN: Generating New Images with CNN
GAN: Generating New Images with CNN
Pix2pix - Image-to-Image translation GAN
GAN – code example
Feature matching
Summary
9
Attention Mechanism for CNN and Visual Models
Attention Mechanism for CNN and Visual Models
Attention mechanism for image captioning
Types of Attention
Using attention to improve visual models
References
Summary
10
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Introducing to autoencoders

An autoencoder is a regular neural network, an unsupervised learning model that takes an input and produces the same input in the output layer. So, there is no associated label in the training data. Generally, an autoencoder consists of two parts:

  • Encoder network
  • Decoder network

It learns all the required features from unlabeled training data, which is known as lower dimensional feature representation. In the following figure, the input data (x) is passed through an encoder that produces a compressed representation of the input data. Mathematically, in the equation, z = h(x), z is a feature vector, and is usually a smaller dimension than x.

Then, we take these produced features from the input data and pass them through a decoder network to reconstruct the original data. 

An encoder can be a fully connected neural network or a convolutional neural network (CNN). A decoder also uses the same kind of network as an encoder. Here, we've explained and implemented the encoder...

Previous Section
End of Chapter 6
Next Chapter