Python Deep Learning - Second Edition

A CNN example with Keras and CIFAR-10

In Chapter 3, Deep Learning Fundamentals, we tried to classify the CIFAR-10 images with a fully-connected network, but we only managed 51% test accuracy. Let's see if we can do better with all the new things we've learned. This time we'll use CNN with data augmentation.

1. We'll start with the imports. We'll use all the layers we introduced in this chapter, as shown in the following example:

import kerasfrom keras.datasets import cifar10from keras.layers import Conv2D, MaxPooling2Dfrom keras.layers import Dense, Dropout, Activation, Flatten, BatchNormalizationfrom keras.models import Sequentialfrom keras.preprocessing.image import ImageDataGenerator

2. We'll define the mini batch_size for convenience, as ...