The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images. This dataset is used to train convolutional neural networks so that these trained models can be used on other classification problems. The classes are completely mutually exclusive.
The 10 classes are: airplane, automobile, bird, cat , deer, dog , frog, horse, ship, truck