Dogs vs. Cats: Data augmentation using Keras

We train a convolutional neural network to classify images of dogs and cats. We show how Keras makes it easy to perform data augmentation, which helps to prevent overfitting. This example is taken from chapter 5 of Deep Learning with Python, first edition, by Francois Chollet, which is a book that I highly recommend reading. Here is a Python script (from chapter 5 of Chollet) that takes the 25k training images from the Dogs vs. Cats dataset and creates a smaller training dataset containing 2000 images, as well as validation and test datasets each containing 1000 images: https://drive.google.com/file/d/1wfGV...