Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
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
Advanced Deep Learning with TensorFlow 2 and Keras

You're reading from   Advanced Deep Learning with TensorFlow 2 and Keras Apply DL, GANs, VAEs, deep RL, unsupervised learning, object detection and segmentation, and more

Arrow left icon
Product type Paperback
Published in Feb 2020
Publisher Packt
ISBN-13 9781838821654
Length 512 pages
Edition 2nd Edition
Languages
Tools
Arrow right icon
Author (1):
Arrow left icon
Rowel Atienza Rowel Atienza
Author Profile Icon Rowel Atienza
Rowel Atienza
Arrow right icon
View More author details
Toc

Table of Contents (16) Chapters Close

Preface 1. Introducing Advanced Deep Learning with Keras 2. Deep Neural Networks FREE CHAPTER 3. Autoencoders 4. Generative Adversarial Networks (GANs) 5. Improved GANs 6. Disentangled Representation GANs 7. Cross-Domain GANs 8. Variational Autoencoders (VAEs) 9. Deep Reinforcement Learning 10. Policy Gradient Methods 11. Object Detection 12. Semantic Segmentation 13. Unsupervised Learning Using Mutual Information 14. Other Books You May Enjoy
15. Index

3. Ground truth anchor boxes

From Figure 11.2.3, it appears that given an object bounding box, there are many ground truth anchor boxes that can be assigned to an object. In fact, just for the illustration in Figure 11.2.3, there are already 3 anchor boxes. If all anchor boxes per region are considered, there are 6 x 6 = 36 ground truth boxes just for . Using all 9,648 anchor boxes is obviously excessive. Only one of all anchor boxes should be associated with the ground truth bounding box. All other anchor boxes are background anchor boxes. What is the criterion for choosing which one should be considered the ground truth anchor box for an object in the image?

The basis for choosing the anchor box is called Intersection over Union (IoU). IoU is also known as Jaccard index. IoU is illustrated in Figure 11.3.1. Given 2 regions, an object bounding box, B0 and an anchor box, A1, IoU is equal to the area of overlap divided by the area of the combined regions:

(Equation 11.3.1...
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 $19.99/month. Cancel anytime
Banner background image