Search icon CANCEL
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Mastering Computer Vision with TensorFlow 2.x

You're reading from   Mastering Computer Vision with TensorFlow 2.x Build advanced computer vision applications using machine learning and deep learning techniques

Arrow left icon
Product type Paperback
Published in May 2020
Publisher Packt
ISBN-13 9781838827069
Length 430 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Author (1):
Arrow left icon
Krishnendu Kar Krishnendu Kar
Author Profile Icon Krishnendu Kar
Krishnendu Kar
Arrow right icon
View More author details
Toc

Table of Contents (18) Chapters Close

Preface 1. Section 1: Introduction to Computer Vision and Neural Networks
2. Computer Vision and TensorFlow Fundamentals FREE CHAPTER 3. Content Recognition Using Local Binary Patterns 4. Facial Detection Using OpenCV and CNN 5. Deep Learning on Images 6. Section 2: Advanced Concepts of Computer Vision with TensorFlow
7. Neural Network Architecture and Models 8. Visual Search Using Transfer Learning 9. Object Detection Using YOLO 10. Semantic Segmentation and Neural Style Transfer 11. Section 3: Advanced Implementation of Computer Vision with TensorFlow
12. Action Recognition Using Multitask Deep Learning 13. Object Detection Using R-CNN, SSD, and R-FCN 14. Section 4: TensorFlow Implementation at the Edge and on the Cloud
15. Deep Learning on Edge Devices with CPU/GPU Optimization 16. Cloud Computing Platform for Computer Vision 17. Other Books You May Enjoy

Section 3: Advanced Implementation of Computer Vision with TensorFlow

In this section, you will build on your understanding acquired from the previous sections and develop newer concepts and learn new techniques for action recognition and object detection. Throughout this section, you will learn different TensorFlow tools, such as TensorFlow Hub, TFRecord, and TensorBoard. You will also learn how to use TensorFlow to develop machine learning models for action recognition.

By the end of this section, you will be able to do the following:

  • Understand the theory and develop an intuition behind various action recognition methods such as OpenPose, Stacked HourGlass, and PoseNet (chapter 9)
  • Analyze the OpenPose and Stacked HourGlass code to develop an understanding of how to build a very complex neural network and connect its different blocks. Hopefully, you can use this learning to...
lock icon 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
Renews at €18.99/month. Cancel anytime