Elements of Deep Learning for Computer Vision
- Length: 208 pages
- Edition: 1
- Language: English
- Publisher: BPB Publications
- Publication Date: 2021-06-25
- ISBN-10: 9390684684
- ISBN-13: 9789390684687
- Sales Rank: #0 (See Top 100 Books)
Conceptualizing deep learning in computer vision applications using PyTorch and Python libraries.
Key Features
- Covers a variety of computer vision projects, including face recognition and object recognition such as Yolo, Faster R-CNN.
- Includes graphical representations and illustrations of neural networks and teaches how to program them.
- Includes deep learning techniques and architectures introduced by Microsoft, Google, and the University of Oxford.
Description
Elements of Deep Learning for Computer Vision gives a thorough understanding of deep learning and provides highly accurate computer vision solutions while using libraries like PyTorch.
This book introduces you to Deep Learning and explains all the concepts required to understand the basic working, development, and tuning of a neural network using Pytorch. The book then addresses the field of computer vision using two libraries, including the Python wrapper/version of OpenCV and PIL. After establishing and understanding both the primary concepts, the book addresses them together by explaining Convolutional Neural Networks(CNNs). CNNs are further elaborated using top industry standards and research to explain how they provide complicated Object Detection in images and videos, while also explaining their evaluation. Towards the end, the book explains how to develop a fully functional object detection model, including its deployment over APIs.
By the end of this book, you are well-equipped with the role of deep learning in the field of computer vision along with a guided process to design deep learning solutions.
What you will learn
- Get to know the mechanism of deep learning and how neural networks operate.
- Learn to develop a highly accurate neural network model.
- Access to rich Python libraries to address computer vision challenges.
- Build deep learning models using PyTorch and learn how to deploy using the API.
- Learn to develop Object Detection and Face Recognition models along with their deployment.
Who this book is for
This book is for the readers who aspire to gain a strong fundamental understanding of how to infuse deep learning into computer vision and image processing applications. Readers are expected to have intermediate Python skills. No previous knowledge of PyTorch and Computer Vision is required.
About the Authors
Bharat Sikka is a data scientist based in Mumbai, India. Over the years, he has worked on implementing algorithms like YOLOv3/v4, Faster-RCNN, Mask-RCNN, among others. He is currently working as a data scientist at the State Bank of India.
He holds an MS degree in Data Science and Analytics from Royal Holloway, University of London, and a BTech degree in Information Technology from Symbiosis International University and has earned multiple certifications, including MOOCs in varied fields, including machine learning.
He is a science fiction fanatic, loves to travel, and is a great cook.
Blog links: https://github.com/bharatsikka
LinkedIn Profile: www.linkedin.com/in/bharat-sikka
Cover Page Title Page Copyright Page Dedication Page About the Author About the Reviewer Acknowledgement Preface Errata Table of Contents Section 1: Introductory Concepts 1. An Introduction to Deep Learning Objectives 1.1 Artificial intelligence 1.2 Machine learning 1.3 Deep learning 1.4 Future of deep learning 2. Supervised Learning Objectives 2.1 Data and Supervised learning 2.2 Tasks in supervised learning 2.3 Neurons and layers 2.4 Regression and classification output neurons 2.5 Neural networks using PyTorch PyTorch requirements PyTorch installation 2.6 Classification of Iris species using Iris dataset and PyTorch 3. Gradient Descent Objectives 3.1 Gradient descent 3.2 Overfitting and underfitting 3.3 Regularizations and learning rate 3.4 Stochastic Gradient Descent 3.5 Loss Functions and optimizers Conclusion Section 2: Computer Vision 4. OpenCV with Python Objectives 4.1 Computer vision 4.2 OpenCV Further operations on images Image properties and resizing Pixel manipulation Region of image and padding Face recognition Conclusion 5. Python Imaging Library and Pillow Objectives 5.1 Python Imaging Library Basic image operations Reading an image Displaying an image Writing/saving an image Image properties and resizing Pixel manipulation Region of image and padding Image enhancing A viral image Conclusion Section 3: Convolutional Neural Networks for Vision 6. Introduction to Convolutional Neural Networks Objectives 6.1 Convolutional Neural Networks (CNNs) Weights and parameters Pooling Padding Transfer learning CNN classifier implementation using CIFAR 10 and PyTorch Conclusion 7. GoogLeNet, VGGNet, and ResNet Objectives 7.1 GoogLeNet 7.2 VGGNet 7.3 ResNet 7.4 Torchvision Datasets IO Models Ops, Transforms, and Utils Conclusion Section 4: Object Detection 8. Understanding Object Detection Objectives 8.1 Introduction to object detection 8.2 Classification 8.3 Localization 8.4 Detection 8.5 mean Average Precision (mAP) Conclusion 9. Popular Algorithms for Object Detection Objectives 9.1 OverFeat Working and implementation 9.2 Region-based CNN Selective search Working and implementation 9.3 Fast R-CNN Region of interest pooling Working and implementation 9.4 Faster R-CNN Working and implementation Anchors 9.5 You Only Look Once (YOLO) Working and implementation Conclusion 10. Faster R-CNN with PyTorch and YOLOv4 with Darknet Objectives 10.1 Torchvision libraries continued Transforms Transforms on PIL image Transforms on torch Utils 10.2 Object Detection using PyTorch 10.3 Object detection using YOLO Conclusion 11. Comparing Algorithms and API Deployment with Flask Objectives 11.1 Comparing mean Average Precision (mAP) of Faster R-CNN and YOLO Faster R-CNN performance in mAP YOLO performance 11.2 Model deployment using Flask Installation Initialization and Hello World! Conclusion Section 5: Further Usage and Applications in Real Life 12. Applications in Real World Objectives 12.1 Introduction to Detecto Installation Dataset Labelling/annotating a dataset Training a model using Detecto Conclusion References Index
Donate to keep this site alive
1. Disable the AdBlock plugin. Otherwise, you may not get any links.
2. Solve the CAPTCHA.
3. Click download link.
4. Lead to download server to download.