A training dataset of 50,000 32 x 32 pixel color images labeled over 100 categories and 10,000 test images, this dataset is similar to CIFAR-10, but it has 100 classes with 600 images in each class. Five-hundred training images and 100 testing images are in each class. The 100 classes in CIFAR-100 are grouped into 20 superclasses. Each image comes with a coarse label (the superclass to which it belongs) and a fine label (the class to which it belongs).
A list of classes in CIFAR-100 is as follows:
| Superclass | Classes |
| aquatic mammals | beaver, dolphin, otter, seal, and whale |
| fish | aquarium fish, flatfish, ray, shark, and trout |
| flowers | orchids, poppies, roses, sunflowers, and tulips |
| food containers | bottles, bowls, cans, cups, and plates |
| fruit and vegetables | apples, mushrooms, oranges, pears, and sweet peppers |
| household electrical devices | clock, computer... |
