The first implementation of object recognition we are going to do is in Python and involves the Keras framework. To train and evaluate the model, we are going to use a public dataset called CIFAR-10 (http://www.cs.toronto.edu/~kriz/cifar.html). It consists of 60,000 (50,000 for training and 10,000 for testing) small (32 x 32 pixels) color images divided into 10 classes (airplane, automobile, bird, cat, deer, dog, frog, horse, ship, and truck). These 10 classes are mutually exclusive. The CIFAR-10 dataset (163 MB) is freely downloadable from http://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz.
The prerequisites for this implementation are Python 2.7.x, Keras, TensorFlow (it is used as the Keras backend), NumPy, and ...
