From the course: Transfer Learning for Images Using PyTorch: Essential Training
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
VGG16
From the course: Transfer Learning for Images Using PyTorch: Essential Training
VGG16
- [Instructor] We'll us VGG-16 which was the runner-up to the 2014 ImageNet competition, or to give it it's full name, the ImageNet Large Scale Visual Recognition Competition. Now VGG-16 is one of the simpler models and so easier to visualize. As part of the ImageNet competition, it would have to classify 1000 categories of images. This diagram shows you the architecture of the VGG-16 model. It was created by Karen Simonyan and Andrew Zisserman from the University of Oxford. You can check out their paper if your interested. So how do you use it? Well, you feed a color image that is of size 244x224x3 in to the model. The three represents the fact that it is a color image with three channels, red, green, and blue. And as you can see, there are two components to the model, the features section and the classifier. The VGG model's architecture is made up of multiple convolution layers with ReLU, followed by max-pooling for…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
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.