From the course: Hands-On Introduction to Transformers for Computer Vision
Join today to access over 24,700 courses taught by industry experts.
Running a pretrained model for classification - PyTorch Tutorial
From the course: Hands-On Introduction to Transformers for Computer Vision
Running a pretrained model for classification
- [Instructor] Hey, everyone. Welcome to chapter three, video three. We are going to be doing vision transformers for classification, but for real this time or in a more real fashion. Now that we're acquainted with transformers in FiftyOne, we're going to do our first go at using a transformer on a dataset with a little less cheating. That's so what we're going to slowly make our way through this course by pulling more and more out of the helper functions and actually understanding what is happening. So in this time, we are going to inference using Hugging Face transformers, using our ImageNet sample from FiftyOne. But this time we're building the inference pipeline ourselves. So go ahead and load that ImageNet 50 samples again. This is going to be another random 50, so if it doesn't look like mine, don't worry. And this is going to launch in the app again. We scroll down here, we are going to run some inference. Now you should remember that from our last video, if you want to do it…
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.