From the course: Hands-On Introduction to Transformers for Computer Vision
Join today to access over 24,900 courses taught by industry experts.
Evaluating ViTs - PyTorch Tutorial
From the course: Hands-On Introduction to Transformers for Computer Vision
Evaluating ViTs
- [Instructor] Hey, everyone, and welcome back to chapter six, video two. We are going to be evaluating our ViTs. Now, we've been talking this throughout the course about how to evaluate our ViTs. We're going to do a little bit more of a deep dive this time making sure you understand what you need to be looking for, how to understand evaluation metrics, both for detection as well as for classification. I will be using FiftyOne throughout to help visualize and do the evaluation for us, as well as pointing out a couple other helpful things throughout that FiftyOne brings to us. If you're running this locally, we do have some new packages that we haven't seen yet. If you're running this in CoLab or anything else, make sure you're downloading it. But if you're running it in Codespaces, you should be good. But we're going to be using the pycocotools as well as the timm model library for some of this as well. Now, we are going to be loading "coco-2017" val. The nice thing about coco-2017 is…
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.