Accelerated Computer Vision 3.7 - You Only Look Once (YOLO) model

[ARCHIVED CONTENT] This video has been archived and may contain outdated or inaccurate content. For the most up-to-date resources, we encourage you to explore and bookmark relevant playlists on Machine Learning University’s YouTube page. Please note that content may be updated, replaced, or removed over time.
----------
PREVIOUS DESCRIPTION: In this video, we cover another object detection model: You Only Look Once (YOLO). We see that this model introduces a grid-like structure and uses an object detection network that can be easily trained end-to-end. We also go over the output shape of the network that depends on how many bounding boxes produced and the number of classes.

0:00 YOLO
1:00 Architecture and Details
5:28 Pros and Cons

This content is based on Machine Learning University (MLU) Accelerated Computer Vision class. Our mission is to make Machine Learning accessible to everyone. We believe machine learning will be a tool for success for many people in their careers. We teach machine learning courses in different topics. This class is designed to help you get started with Computer Vision, learn widely used techniques and apply them on real-world problems.