Creating a ConvNet to classify CIFAR-10

In this recipe, you will learn how to do classify images taken from CIFAR-10. The CIFAR-10 dataset consists of 60,000 32 x 32 color images in 10 classes, with 6,000 images per class. There are 50,000 training images and 10,000 test images. The following image is taken from https://www.cs.toronto.edu/~kriz/cifar.html:

Examples of CIFAR images

Getting ready

In this recipe, we use tflearn--a higher-level framework--which abstracts some of the TensorFlow internals and allows us to focus on the definition of deep networks. TFLearn is available at http://tflearn.org/ and this code is part of the standard distribution. (https://github.com/tflearn/tflearn/tree/master/examples)

...