Hi,

This week's lesson is about the Introduction to the YOLO Family.

Image

Deep learning (DL) has grown to be one of the pillars supporting the world's technology. Most prominent businesses employ deep learning in some capacity or another. While there are many subdomains of deep learning, the most prominent field will always be computer vision. 

Teaching machines to assess visual input solves a chunk of the world's problems. Nowadays, we have everything from number plate recognition systems to automatic security card readers powered by deep learning. We cannot emphasize enough that deep learning is indeed taking us to a more comfortable era of living standards. 

Currently, the company at the top of the automobile industry by market capitalization is none other than Tesla. The company is famous for making self-driving cars, which involves solving one of the most important computer vision tasks in today's world, object detection. Teaching a computer to identify a picture's label is one thing, but teaching a computer to estimate the exact ROI of the object required is a different ball game. 

That brings us to the purpose of this series and this tutorial: to tell you everything you need to know about the game changer in Object Detection, the YOLO family. 

The big picture: YOLO (also known as You Only Look Once) is an ingenious single-stage object detector introduced in 2015. It employed various efficient and groundbreaking techniques to sweep the object detection scene at that time. Since then, various successors with ever-improving approaches have been developed to keep the YOLO family at the top of the object detection world. 

How it works: This blog is an elaborate overview of the evolution of YOLO. This tutorial covers everything from YOLO's conception, to its highlights, to the changes brought in by the subsequent YOLO versions. 

Our thoughts: This blog hosts an overview of everything related to the YOLO family. One can treat this as an all-in-one database to have a basic understanding (and appreciation) of YOLO. 

Yes, but: We have not covered the detailed explanations of the concepts used in different versions of YOLO. These will be covered in the subsequent tutorials.

Stay smart: Stay tuned for the subsequent posts in this series to know more about the beautiful intricacies of YOLO. 

Click here to read the full tutorial

PyImageSearch University

This lesson is part of PyImageSearch University, our flagship program to help you master computer vision, deep learning, and OpenCV. PyImageSearch University is updated each week with new lessons.

Don't spend your time trying to piece together code when you could get pristine code right now. Want the full, working code of nearly every blog post plus a Colab Notebook and video walkthrough of the code?

I want the code

Having problems with your local development environment or IDE? Fortunately, our pre-configured Colab Notebooks allow you to run code the moment you join PyImageSearch University. Of course, you don't want to be a sys-admin, so don't waste time messing with your development environment. 

Want to Master Computer Vision and Deep Learning?

Do you think mastering computer vision and deep learning has to be time-consuming, overwhelming, and complicated? Or has to involve complex mathematics and equations? Or requires a degree in computer science?

That's not the case. All you need to master computer vision and deep learning is for someone to explain things to you in simple, intuitive terms. And that's exactly what we do. Our mission is to change education and how complex Artificial Intelligence topics are taught.

Inside PyImageSearch University, you'll find:

  • Code that works for almost any OpenCV or TensorFlow CV problem
  • 35+ courses on the hottest computer vision, deep learning, and OpenCV topics
  • 35+ Certificates of Completion (one for each course)
  • 39+ hours of on-demand video
  • Pre-configured Jupyter Notebooks running in Google Colab
  • Run all code examples in your web browser — works on Windows, macOS, and Linux (no dev environment configuration required!)
  • Access to centralized code repos for nearly all 500+ tutorials on the PyImageSearch blog
  • Easy one-click downloads for code, datasets, pre-trained models, etc.
  • Access on mobile, laptop, desktop, etc.
  • New courses released regularly and new tutorials weekly, ensuring you can keep up with state-of-the-art techniques

Click here to join PyImageSearch University


The PyImageSearch Team

P.S. You may have missed these, but last Wednesday and Thursday, we published the new posts Ideating the Solution and Planning Experiments and Text Detection and OCR with Google Cloud Vision API, respectively.