From the course: Hands-On Introduction to Transformers for Computer Vision
Unlock this course with a free trial
Join today to access over 24,900 courses taught by industry experts.
Choosing the right ViT for the job - PyTorch Tutorial
From the course: Hands-On Introduction to Transformers for Computer Vision
Choosing the right ViT for the job
- [Instructor] Hey, everyone. Welcome to Chapter 6, Video 1. Choosing the Right Vision Transformer for the Job. We're going to get more hands-on and look at the real world in this video to help understand exactly how to choose the right Vision Transformer at the right task for the right problem. There are many popular visual AI tasks. A number of them from classification, detection, segmentation and much, much more. I'm going to break down each one of these tasks at a high level to just make sure that you understand what each one is. That way we can help understand which Vision Transformer to pick depending on what task we're trying to build. So, let's start from the top. The most basic, which is classification. Classification tasks a model to understand an image and label the entire image as a class. These models tend to be very small but also very powerful, and is one of the most basic computer vision tasks. If you can do well in a classification task, chances are that that method…