Reader small image

You're reading from  Modern Computer Vision with PyTorch

Product typeBook
Published inNov 2020
Reading LevelBeginner
PublisherPackt
ISBN-139781839213472
Edition1st Edition
Languages
Tools
Right arrow
Authors (2):
V Kishore Ayyadevara
V Kishore Ayyadevara
author image
V Kishore Ayyadevara

V Kishore Ayyadevara leads a team focused on using AI to solve problems in the healthcare space. He has 10 years' experience in data science, solving problems to improve customer experience in leading technology companies. In his current role, he is responsible for developing a variety of cutting edge analytical solutions that have an impact at scale while building strong technical teams. Prior to this, Kishore authored three books — Pro Machine Learning Algorithms, Hands-on Machine Learning with Google Cloud Platform, and SciPy Recipes. Kishore is an active learner with keen interest in identifying problems that can be solved using data, simplifying the complexity and in transferring techniques across domains to achieve quantifiable results.
Read more about V Kishore Ayyadevara

Yeshwanth Reddy
Yeshwanth Reddy
author image
Yeshwanth Reddy

Yeshwanth is a highly accomplished data scientist manager with 9+ years of experience in deep learning and document analysis. He has made significant contributions to the field, including building software for end-to-end document digitization, resulting in substantial cost savings. Yeshwanth's expertise extends to developing modules in OCR, word detection, and synthetic document generation. His groundbreaking work has been recognized through multiple patents. He also created a few Python libraries. With a passion for disrupting unsupervised and self-supervised learning, Yeshwanth is dedicated to reducing reliance on manual annotation and driving innovative solutions in the field of data science.
Read more about Yeshwanth Reddy

View More author details
Right arrow

Understanding IoU

Imagine a scenario where we came up with a prediction of a bounding box for an object. How do we measure the accuracy of our prediction? The concept of Intersection over Union (IoU) comes in handy in such a scenario.

Intersection within the term Intersection over Union measures how overlapping the predicted and actual bounding boxes are, while Union measures the overall space possible for overlap. IoU is the ratio of the overlapping region between the two bounding boxes over the combined region of both the bounding boxes.

This can be represented in a diagram as follows:

In the preceding diagram of two bounding boxes (rectangles), let's consider the left bounding box as the ground truth and the right bounding box as the predicted location of the object. IoU as a metric is the ratio of the overlapping region over the combined region between the two bounding boxes.

In the following diagram, you can observe the variation in the IoU metric as the overlap between bounding...

lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
Modern Computer Vision with PyTorch
Published in: Nov 2020Publisher: PacktISBN-13: 9781839213472

Authors (2)

author image
V Kishore Ayyadevara

V Kishore Ayyadevara leads a team focused on using AI to solve problems in the healthcare space. He has 10 years' experience in data science, solving problems to improve customer experience in leading technology companies. In his current role, he is responsible for developing a variety of cutting edge analytical solutions that have an impact at scale while building strong technical teams. Prior to this, Kishore authored three books — Pro Machine Learning Algorithms, Hands-on Machine Learning with Google Cloud Platform, and SciPy Recipes. Kishore is an active learner with keen interest in identifying problems that can be solved using data, simplifying the complexity and in transferring techniques across domains to achieve quantifiable results.
Read more about V Kishore Ayyadevara

author image
Yeshwanth Reddy

Yeshwanth is a highly accomplished data scientist manager with 9+ years of experience in deep learning and document analysis. He has made significant contributions to the field, including building software for end-to-end document digitization, resulting in substantial cost savings. Yeshwanth's expertise extends to developing modules in OCR, word detection, and synthetic document generation. His groundbreaking work has been recognized through multiple patents. He also created a few Python libraries. With a passion for disrupting unsupervised and self-supervised learning, Yeshwanth is dedicated to reducing reliance on manual annotation and driving innovative solutions in the field of data science.
Read more about Yeshwanth Reddy