From the course: Hands-On Introduction to Transformers for Computer Vision
Join today to access over 24,900 courses taught by industry experts.
Transformers in the wild: How to find the right one for you - PyTorch Tutorial
From the course: Hands-On Introduction to Transformers for Computer Vision
Transformers in the wild: How to find the right one for you
- [Instructor] Hey, everyone. Welcome to chapter five, video one, "Transformers in the Wild: How to Find the Right One for You." We're going to be talking all about how we can take everything that we've learned so far and really apply it to more real-life use cases here. The first and most important thing to understand is something that we kind of touched upon, which is transfer learning. So what is transfer learning? Transfer learning allows you to skip a step here by leveraging a strong pre-trained model. If a vision transformer is good on a huge dataset, chances are it's not just good at solving that problem, it's probably good at solving most problems. Transfer learning, in the long run, helps you save a ton of time on compute and cost by allowing you to train less parameters for less amount of times. So a quick example on what transfer learning could look like. Let's say I have a dataset of 10 million cat images, and the task here is to properly identify the species of cat or…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.