From the course: TensorFlow 2.0: Working with Images
Unlock the full course today
Join today to access over 23,200 courses taught by industry experts.
Review of neural networks
From the course: TensorFlow 2.0: Working with Images
Review of neural networks
- [Man] As I've mentioned TensorFlow neural networks and working with Tableau data is the first course in this series. Here I covered the Fashion-MNIST Dataset. Now, if you haven't seen that course, this video will provide a quick overview of the Fashion-MNIST Dataset. the Fashion-MNIST Dataset is made up of images from the fashion chains, Zalando. It contains a training set of 60,000 images and a test set of 10,000 images. Now each image is a 28 by 28 grayscale image, associated with the labels from the 10 classes. Each training and test example is assigned to one of the following labels. So for example label zero refers to a T-shirt and label one is a trouser and so on. Now this is what the neural network that we use to help us classify the 10 categories of the Fashion-MNIST Dataset looks like. We had 784 input nodes. And each of these nodes corresponds to a pixel of that image. We then have two hidden layers with…
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.