From the course: Neural Networks and Convolutional Neural Networks Essential Training
Join today to access over 24,700 courses taught by industry experts.
Working with VGG16
From the course: Neural Networks and Convolutional Neural Networks Essential Training
Working with VGG16
- [Instructor] So we look at VGG16, which is the model created by the Visual Geometry Group at Oxford University, which won the 2014 ImageNet Competition, as it's one of the simpler models to understand. The VGG ImageNet team created both a larger, slower, and slightly more accurate model, VGG19, and a smaller, faster model, VGG16. Remember that as the winner of an ImageNet competition, the model would have to recognize 1000 categories of images. So let's head over to Keras to look at VGG in a little more detail. Fortunately for us, VGG16 comes with Keras. What we're going to do is use a world-class model and look at the steps involved in recognizing a random object. And we will see how well the VGG16 model manages this. So we import the relevant libraries from Keras. If this is the first time that you're going to be using the VGG16 model, the weights have to be downloaded from the author's GitHub site. The reason we do this is because instead of having to create and train VGG16 on…
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.
