Intro to Python for Computer Science and Data Science: Learning to Program with AI, Big Data and The Cloud

Exercises

Convolutional Neural Networks

1. 16.1 (Image Recognition: The Fashion-MNIST Dataset) Keras comes bundled with the Fashion-MNIST database of fashion articles which, like the MNIST digits dataset, provides 28-by-28 grayscale images. Fashion-MNIST contains clothing-article images labeled in 10 categories—0 (T-shirt/top), 1 (Trouser), 2 (Pullover), 3 (Dress), 4 (Coat), 5 (Sandal), 6 (Shirt), 7 (Sneaker), 8 (Bag), 9 (Ankle boot)—with 60,000 training samples and 10,000 testing samples. Modify this chapter’s convnet example to load and process Fashion-MNIST rather than MNIST—this requires simply importing the correct module, loading the data then running the model with these images and labels, then re-run the entire example. How well does ...