In this chapter, we will use the CIFAR-10 dataset to build a convolution neural network for image classification. The CIFAR-10 dataset consists of 60,000 32 x 32 color images of 10 classes, with 6,000 images per class. These are further divided into five training batches and one test batch, each with 10,000 images.

The test batch contains exactly 1,000 randomly-selected images from each class. The training batches contain the remaining images in random order, but some training batches may contain more images from one class than another. Between them, the training batches contain exactly 5,000 images from each class. The ten outcome classes are airplane, automobile, bird, cat, deer, dog, frog, horse, ship, and truck. The classes are completely mutually exclusive. In addition, the format of the dataset is as follows:

• The first column: The label with 10 classes: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, and truck
• The next 1,024 columns: Red pixels in the range of 0 to 255
• The next 1,024 columns: Green pixels in the range of 0 to 255
• The next 1,024 columns: Blue pixels in the range of 0 to 255