YOLO(You Look Only Once) – PART III

Is YOLO a Popular one? Not but simple and easy to implement

It’s a State-of-the-Art Algorithm for Real-Time Object Detection System, found by Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi in 2016

Yes, it’s 5years old, but some may come to know about it now.

YOLO algorithm is an algorithm based on regression. Instead of selecting the eye-catching part of an Image, it predicts classes and bounding boxes for the whole image in one run of the Algorithm – If you want to understand the theory behind YOLO https://arxiv.org/pdf/1506.02640.pdf Read the official paper.

Different versions of YOLO’s

  1. You Only Look Once: Unified, Real-Time Object Detection
  2. YOLO9000: Better, Faster, Stronger
  3. YOLOv3: An Incremental Improvement
  4. YOLOv4
  5. YOLOv5

Why YOLO?

YOLO is incredibly faster but not the best version as v1. Each grid cell only predicts two boxes and can only have one class – class is an object or thing that you wanted to identify or detect in your detection algorithm ex: Dog, Cat, or Table, etc.

In our experimental learning. we will implement directly YOLOv3 – single class and YOLOv5 – Multiple class in the later parts.

Why YOLOv3?

YOLOv3 Implementation with your dataset – Next Part

Leave a Reply

Please log in using one of these methods to post your comment:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s