From the course: Hands-On Introduction to Transformers for Computer Vision
Join today to access over 24,800 courses taught by industry experts.
Training strategies for vision transformers - PyTorch Tutorial
From the course: Hands-On Introduction to Transformers for Computer Vision
Training strategies for vision transformers
- [Instructor] Welcome back to Chapter Five, video three, where we'll be talking all about training strategies for vision transformers. We mentioned how training is a deep well in the last video. There's so much to bite off when it comes to training, and there's so, so, so much research that goes into pre-training, unfreezing versus freezing, and there's a lot of different schools of thought here, so I'm going to do my best effort to gather the best tips of advice that I think that you should know. If you're interested in learning more, go dive deep. There's so many resources online for you to learn more about training regiments, training strategies. But quite frankly, for the majority of people, training strategies are not super significant past the best one for your use case. And if you're trying to iterate and be innovative, I love the effort, you should go for it, but don't feel like that is a requirement to have a good performing model in machine learning. Let's start basic…
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.