Packt+ | Advance your knowledge in tech

0

Explore Products

Best Sellers

New Releases

Books

Videos

Audiobooks

Free Learning

Hands-On Convolutional Neural Networks with TensorFlow

You're reading from Hands-On Convolutional Neural Networks with TensorFlow Solve computer vision problems with modeling in TensorFlow and Python

Product type Paperback

Published in Aug 2018

Publisher Packt

ISBN-13 9781789130331

Length 272 pages

Edition 1st Edition

Languages

Python

Tools

TensorFlow

Concepts

Computer Vision

Authors (5):

Araujo

Zafar

Tzanidou

Burton

Patel

+1 more

View More author details

Table of Contents (12) Chapters

Preface

1. Setup and Introduction to TensorFlow FREE CHAPTER

2. Deep Learning and Convolutional Neural Networks

3. Image Classification in TensorFlow

4. Object Detection and Segmentation

5. VGG, Inception Modules, Residuals, and MobileNets

6. Autoencoders, Variational Autoencoders, and Generative Adversarial Networks

7. Transfer Learning

8. Machine Learning Best Practices and Troubleshooting

9. Training at Scale

10. References

11. Other Books You May Enjoy

Leave a review - let other readers know what you think

Bias and Variance

Variance and Bias is another way of saying overfitting and underfitting respectively, as discussed in Chapter 2, Deep Learning and Convolutional Neural Networks. We can diagnose the problem of "underfitting" and "overfitting" using the train set, dev set and test set errors.

Consider the following scenario where we have data coming from two different distributions named as Distribution 1 and Distribution 2. Distribution 2 represents the target application which we care about. The question is, how do we define train, dev and test sets on such distributions.

The best way to do so is to split it according to the preceding figure. Distribution 1 is split in to train set and part of it is used as the dev set. Here we are calling it the "Train-Dev set" ( because the dev set has same distribution as train set). Distribution 1 is used mainly for training as it is a large dataset. Distribution 2 is split into test set and dev set which are independent of either sets from Distribution...

The rest of the chapter is locked

Register for a free Packt account to unlock a world of extra content!

A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.

Unlock this book and the full library FREE for 7 days

Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of

Start free trial

Renews at $19.99/month. Cancel anytime

Authors (5)

Araujo

Araujo

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.

See other products by Araujo

Zafar

Zafar

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.

See other products by Zafar

Tzanidou

Tzanidou

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.

See other products by Tzanidou

Burton

Burton

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.

See other products by Burton

Patel

Patel

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.

See other products by Patel

Other recommended products

Related to this chapter

Generative Adversarial Networks Projects

Generative Adversarial Networks Projects

In this book, we will use different complexities of datasets in order to build end-to-end projects. With every chapter, the level of complexity and operations will become advanced. It consists of 8 full-fledged projects covering approaches such as 3D-GAN, Age-cGAN, DCGAN, SRGAN, StackGAN, and CycleGAN with real-world use cases.

Jan 2019 10h 32m

PyTorch Computer Vision Cookbook

PyTorch Computer Vision Cookbook

This book enables you to solve the trickiest of problems in computer vision using deep learning algorithms and techniques. You will learn to use several different algorithms for different CV problems such as classification, detection, segmentation, and more using Pytorch. Packed with best practices in training and deployment of CV applications.

Mar 2020 12h 8m

Hands-On Computer Vision with TensorFlow 2

Hands-On Computer Vision with TensorFlow 2

Computer vision is achieving a new frontier of capabilities in fields like health, automobile or robotics. This book explores TensorFlow 2, Google's open-source AI framework, and teaches how to leverage deep neural networks for visual tasks. It will help you acquire the insight and skills to be a part of the exciting advances in computer vision.

May 2019 12h 24m

Practical Convolutional Neural Networks

Practical Convolutional Neural Networks

This book helps you master CNN, from the basics to the most advanced concepts in CNN such as GANs, instance classification and attention mechanism for vision models and more. You will implement advanced CNN models using complex image and video datasets. By the end of the book you will learn CNN's best practices to implement smart ConvNet models and apply them to solve complex deep learning problems.

Feb 2018 7h 16m

Deep Learning with Keras

Deep Learning with Keras

Keras is a high-level neural network library written in Python that runs on top of either Theano or TensorFlow. With this book, you'll learn the basics of Keras in a highly practical way and understand how this minimal, highly modular framework runs on both CPU and GPU, allowing you to put your ideas into action in the shortest possible time.

Apr 2017 10h 36m

Advanced Deep Learning with TensorFlow 2 and Keras

Advanced Deep Learning with TensorFlow 2 and Keras

A second edition of the bestselling guide to exploring and mastering deep learning with Keras, updated to include TensorFlow 2.x with new chapters on object detection, semantic segmentation, and unsupervised learning using mutual information.

Feb 2020 17h 4m

Advanced Deep Learning with Python

Advanced Deep Learning with Python

This book is an expert-level guide to master the neural network variants using the Python ecosystem. You will gain the skills to build smarter, faster, and efficient deep learning systems with practical examples. By the end of this book, you will be up to date with the latest advances and current researches in the deep learning domain.

Dec 2019 15h 36m

Hands-On Deep Learning with TensorFlow

Hands-On Deep Learning with TensorFlow

With deep learning going mainstream, making sense of data and getting accurate results using deep networks is possible. Dan Van Boxel is your guide to exploring the possibilities with deep learning; he will enable you to understand data like never before. With the efficiency and simplicity of TensorFlow, you will be able to process your data and gain insights that will change how you look at data.

Jul 2017 5h 48m

Deep Learning for Computer Vision

Deep Learning for Computer Vision

Deep learning has shown its power in several application areas of Artificial Intelligence, especially in Computer Vision, the science of manipulating and processing images. In this book, you will learn different techniques in deep learning to accomplish tasks related to object classification, object detection, image segmentation, captioning, image generation, and more. You will also explore their application using the popular Python libraries such as TensorFlow and Keras. With practical examples, you will learn to develop Computer Vision applications by leveraging the power of deep learning.

Jan 2018 10h 20m

Modern Computer Vision with PyTorch

Modern Computer Vision with PyTorch

Starting from the basics of neural networks, this book covers over 50 applications of computer vision and helps you to gain a solid understanding of the theory of various architectures before implementing them. Each use case is accompanied by a notebook in GitHub with ready-to-execute code and self-assessment questions.

Nov 2020 27h 28m

Practical Computer Vision

Practical Computer Vision

Computer Vision is a broadly used term associated with acquiring, processing, and analyzing images. This book will show you how you can perform various Computer Vision techniques in the most practical way possible. Right from capturing images from various sources, you will learn how to perform image filtering/manipulation and detect features in your images. As you go through the chapters, you'll work with increasingly complex algorithms to develop complex Computer Vision applications

Feb 2018 7h 48m

Python Deep Learning Cookbook

Python Deep Learning Cookbook

Deep Learning is a rapidly evolving field of Machine Learning science which gives machines the ability to learn from information. This book contains detailed recipes to tackle with the common and not so common problems while dealing with deep learning algorithms and models in Python. You will benefit from this book by finding technical solutions to the issues presented, along with a detailed explanation of the solutions, and a discussion on corresponding pros and cons of implementing the proposed solution using Theano, Tensorflow, MXNet, and Keras. You'll come across recipes on data pre-processing, network models and topologies, supervised and unsupervised learning presented in a “solution to problem” fashion.

Oct 2017 11h 0m

Personalised recommendations for you

Based on your interests and search pattern

Modern Computer Vision with PyTorch

Modern Computer Vision with PyTorch

This book provides a hands-on approach to solving over 30 prominent real-world computer vision problems using PyTorch 2.x on actual datasets. Here you'll learn to build a neural network from scratch and optimize hyperparameters, perform image classification, multi-object detection, segmentation, and more. You'll also explore facial expression manipulation and combining CV with NLP and RL techniques, build generative AI applications, and take your model to production on AWS. By the end of this book, you'll master modern NN architectures and confidently solve real-world CV problems.

Jun 2024 24h 52m

Data Governance Handbook

Data Governance Handbook

This book provides a highly focused view of real business outcomes powered by data governance, that resonate with non-data executives such as CFOs and CEOs. You'll also find useful insights into how to implement data governance initiatives.

May 2024 13h 12m

Data Engineering with Databricks Cookbook

Data Engineering with Databricks Cookbook

This book shows you how to use Apache Spark, Delta Lake, and Databricks to build data pipelines, manage and transform data, optimize performance, and more. Additionally, you'll implement DataOps and DevOps practices, and orchestrate data workflows.

May 2024 14h 36m

Azure Data Engineer Associate Certification Guide

Azure Data Engineer Associate Certification Guide

Unlock the power of Azure data engineering with this certification guide, elevating your skills in data processing, storage, and security with the help of practical insights, hands-on exercises, and the latest advancements.

May 2024 18h 16m

Microsoft Power BI Cookbook

Microsoft Power BI Cookbook

Microsoft Power BI is the most sought-after platform for BI professionals' visualization needs. Explore the latest Power BI features, future AI enhancements, and integration with other Power Platform tools via new recipes in this updated edition.

Jul 2024 19h 56m

Python Data Cleaning Cookbook

Python Data Cleaning Cookbook

The book shows you how to clean, wrangle, and view data from multiple perspectives, including dataset and column attributes. You will cover common and not-so-common challenges that are faced while cleaning messy data for complex situations and learn to manipulate data to get it down to a form that can be useful for making the right decisions.

May 2024 16h 12m

Microsoft Azure AI Fundamentals AI-900 Exam Guide

Microsoft Azure AI Fundamentals AI-900 Exam Guide

This AI-900 study guide will help you prepare and practice for the certification exam. You'll delve into AI workloads, ML principles, computer vision, NLP, knowledge mining, and generative AI using Azure cloud services.

May 2024 9h 36m

Using Stable Diffusion with Python

Using Stable Diffusion with Python

This book shows you how to use Python to control Stable Diffusion and generate high-quality images. In addition to covering the basic usage of the diffusers package, the book provides solutions for extending the package for more advanced purposes.

Jun 2024 11h 44m

Getting Started with DuckDB

Getting Started with DuckDB

This hands-on book teaches you to analyze large datasets with blazing speed and ease. You will learn how to use DuckDB to quickly load, query, transform, analyze, and visualize data effectively through a series of practical examples.

Jun 2024 12h 44m

Databricks Certified Associate Developer for Apache Spark Using Python

Databricks Certified Associate Developer for Apache Spark Using Python

This guide gets you ready for certification with expert-backed content, key exam concepts, and topic reviews. Additionally, you'll be able to make the most of Apache Spark 3.0 to modernize workloads and more using specific tools and techniques.