Hands-on convolutional neural networks with tensorflow : solve computer vision problems with modeling in tensorflow and python / Iffat Zafar [and four others].

Format:

Book

Author/Creator:

Zafar, Iffat, author.

Tzanidou, Giounona, author.

Burton, Richard, author.

Nimo (Rapper), author.

Araújo, Leonardo, author.

Language:

English

Subjects (All):

Neural networks (Computer science)--Computer simulation.

Neural networks (Computer science).

Physical Description:

1 online resource (264 pages)

Edition:

1st edition

Place of Publication:

Birmingham : Packt Publishing Ltd, [2018]

System Details:

text file

Biography/History:

Zafar Iffat: Iffat Zafar was born in Pakistan. She received her Ph. D. from the Loughborough University in Computer Vision and Machine Learning in 2008. After her Ph. D. in 2008, she worked as research associate at the Department of Computer Science, Loughborough University, for about 4 years. She currently works in the industry as an AI engineer, researching and developing algorithms using Machine Learning and Deep Learning for object detection and general Deep Learning tasks for edge and cloud-based applications. Tzanidou Giounona: Giounona Tzanidou is a PhD in computer vision from Loughborough University, UK, where she developed algorithms for runtime surveillance video analytics. Then, she worked as a research fellow at Kingston University, London, on a project aiming at prediction detection and understanding of terrorist interest through intelligent video surveillance. She was also engaged in teaching computer vision and embedded systems modules at Loughborough University. Now an engineer, she investigates the application of deep learning techniques for object detection and recognition in videos. Burton Richard: Richard Burton graduated from the University of Leicester with a master's degree in mathematics. After graduating, he worked as a research engineer at the University of Leicester for a number of years, where he developed deep learning object detection models for their industrial partners. Now, he is working as a software engineer in the industry, where he continues to research the applications of deep learning in computer vision. Patel Nimesh: Nimesh Patel graduated from the University of Leicester with an MSc in applied computation and numerical modeling. During this time, a project collaboration with one of University of Leicesters partners was undertaken, dealing with Machine Learning for Hand Gesture recognition. Since then, he has worked in the industry, researching Machine Learning for Computer Vision related tasks, such as Depth Estimation. Araujo Leonardo: Leonardo Araujo is just the regular, Brazilian, curious engineer, who has worked in the industry for the past 19 years (yes, in Brazil, people work before graduation), doing HW/SW development and research on the topics of control engineering and computer vision. For the past 6 years, he has focused more on Machine Learning methods. His passions are too many to put on the book.

Summary:

Learn how to apply TensorFlow to a wide range of deep learning and Machine Learning problems with this practical guide on training CNNs for image classification, image recognition, object detection and many computer vision challenges. Key Features Learn the fundamentals of Convolutional Neural Networks Harness Python and Tensorflow to train CNNs Build scalable deep learning models that can process millions of items Book Description Convolutional Neural Networks (CNN) are one of the most popular architectures used in computer vision apps. This book is an introduction to CNNs through solving real-world problems in deep learning while teaching you their implementation in popular Python library - TensorFlow. By the end of the book, you will be training CNNs in no time! We start with an overview of popular machine learning and deep learning models, and then get you set up with a TensorFlow development environment. This environment is the basis for implementing and training deep learning models in later chapters. Then, you will use Convolutional Neural Networks to work on problems such as image classification, object detection, and semantic segmentation. After that, you will use transfer learning to see how these models can solve other deep learning problems. You will also get a taste of implementing generative models such as autoencoders and generative adversarial networks. Later on, you will see useful tips on machine learning best practices and troubleshooting. Finally, you will learn how to apply your models on large datasets of millions of images. What you will learn Train machine learning models with TensorFlow Create systems that can evolve and scale during their life cycle Use CNNs in image recognition and classification Use TensorFlow for building deep learning models Train popular deep learning models Fine-tune a neural network to improve the quality of results with transfer learning Build TensorFlow models that can scale to large datasets and systems Who this book is for This book is for Software Engineers, Data Scientists, or Machine Learning practitioners who want to use CNNs for solving real-world problems. Knowledge of basic machine learning concepts, linear algebra and Python will help.

Contents:

Cover

Title Page

Copyright and Credits

Packt Upsell

Contributors

Table of Contents

Preface

Chapter 1: Setup and Introduction to TensorFlow

The TensorFlow way of thinking

Setting up and installing TensorFlow

Conda environments

Checking whether your installation works

TensorFlow API levels

Eager execution

Building your first TensorFlow model

One-hot vectors

Splitting into training and test sets

Creating TensorFlow graphs

Variables

Operations

Feeding data with placeholders

Initializing variables

Training our model

Loss functions

Optimization

Evaluating a trained model

The session

Summary

Chapter 2: Deep Learning and Convolutional Neural Networks

AI and ML

Types of ML

Old versus new ML

Artificial neural networks

Activation functions

The XOR problem

Training neural networks

Backpropagation and the chain rule

Batches

The optimizer and its hyperparameters

Underfitting versus overfitting

Feature scaling

Fully connected layers

A TensorFlow example for the XOR problem

Convolutional neural networks

Convolution

Input padding

Calculating the number of parameters (weights)

Calculating the number of operations

Converting convolution layers into fully connected layers

The pooling layer

1x1 Convolution

Calculating the receptive field

Building a CNN model in TensorFlow

TensorBoard

Other types of convolutions

Chapter 3: Image Classification in TensorFlow

CNN model architecture

Cross-entropy loss (log loss)

Multi-class cross entropy loss

The train/test dataset split

Datasets

ImageNet

CIFAR

Loading CIFAR

Image classification with TensorFlow

Building the CNN graph

Learning rate scheduling

Introduction to the tf.data API.

The main training loop

Model Initialization

Do not initialize all weights with zeros

Initializing with a mean zero distribution

Xavier-Bengio and the Initializer

Improving generalization by regularizing

L2 and L1 regularization

Dropout

The batch norm layer

Chapter 4: Object Detection and Segmentation

Image classification with localization

Localization as regression

TensorFlow implementation

Other applications of localization

Object detection as classification - Sliding window

Using heuristics to guide us (R-CNN)

Problems

Fast R-CNN

Faster R-CNN

Region Proposal Network

RoI Pooling layer

Conversion from traditional CNN to Fully Convnets

Single Shot Detectors - You Only Look Once

Creating training set for Yolo object detection

Evaluating detection (Intersection Over Union)

Filtering output

Anchor Box

Testing/Predicting in Yolo

Detector Loss function (YOLO loss)

Loss Part 1

Loss Part 2

Loss Part 3

Semantic segmentation

Max Unpooling

Deconvolution layer (Transposed convolution)

The loss function

Labels

Improving results

Instance segmentation

Mask R-CNN

Chapter 5: VGG, Inception Modules, Residuals, and MobileNets

Substituting big convolutions

Substituting the 3x3 convolution

VGGNet

Architecture

Parameters and memory calculation

Code

More about VGG

GoogLeNet

Inception module

More about GoogLeNet

Residual Networks

MobileNets

Depthwise separable convolution

Control parameters

More about MobileNets

Chapter 6: Autoencoders, Variational Autoencoders, and Generative Adversarial Networks

Why generative models

Autoencoders

Convolutional autoencoder example

Uses and limitations of autoencoders

Variational autoencoders.

Parameters to define a normal distribution

VAE loss function

Kullback-Leibler divergence

Training the VAE

The reparameterization trick

Convolutional Variational Autoencoder code

Generating new data

Generative adversarial networks

The discriminator

The generator

GAN loss function

Generator loss

Discriminator loss

Putting the losses together

Training the GAN

Deep convolutional GAN

WGAN

BEGAN

Conditional GANs

Problems with GANs

Loss interpretability

Mode collapse

Techniques to improve GANs' trainability

Minibatch discriminator

Chapter 7: Transfer Learning

When?

How? An overview

How? Code example

TensorFlow useful elements

An autoencoder without the decoder

Selecting layers

Training only some layers

Complete source

Chapter 8: Machine Learning Best Practices and Troubleshooting

Building Machine Learning Systems

Data Preparation

Split of Train/Development/Test set

Mismatch of the Dev and Test set

When to Change Dev/Test Set

Bias and Variance

Data Imbalance

Collecting more data

Look at your performance metric

Data synthesis/Augmentation

Resample Data

Loss function Weighting

Evaluation Metrics

Code Structure best Practice

Singleton Pattern

Recipe for CNN creation

Chapter 9: Training at Scale

Storing data in TFRecords

Making a TFRecord

Storing encoded images

Sharding

Making efficient pipelines

Parallel calls for map transformations

Getting a batch

Prefetching

Tracing your graph

Distributed computing in TensorFlow

Model/data parallelism

Synchronous/asynchronous SGD

When data does not fit on one computer

The advantages of NoSQL systems

Installing Cassandra (Ubuntu 16.04)

The CQLSH tool

Creating databases, tables, and indexes.

Doing queries in Python

Populating tables in Python

Doing backups

Scaling computation in the cloud

EC2

AMI

Storage (S3)

SageMaker

References

Chapter 1

Chapter 2

Chapter 3

Chapter 4

Chapter 5

Chapter 7

Chapter 9

Other Books You May Enjoy

Index.

Notes:

Description based on print version record.

ISBN:

9781789132823

1789132827

OCLC:

1056157565