The CIFAR-100 dataset is just like CIFAR-10, except that it has 100 classes containing 600 images each. There are 500 training images and 100 testing images per class. The 100 classes in CIFAR-100 are grouped into 20 superclasses. Each image comes with a fine label (the class to which it belongs) and a coarse label (the superclass to which it belongs). Here is the list of classes in CIFAR-100:
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 keyboard, lamp, telephone, and television |
Household furniture |
Bed, chair, couch, table, and wardrobe |
Insects |
Bee, beetle, butterfly, caterpillar, and cockroach |
Large carnivores |
Bear, leopard, lion, tiger, and wolf |
Large man-made outdoor things |
Bridge, castle, house, road, and skyscraper |
Large natural outdoor scenes |
Cloud, forest, mountain, plain, and sea |
Large omnivores and herbivores |
Camel, cattle, chimpanzee, elephant, and kangaroo |
Medium-sized mammals |
Fox, porcupine, possum, raccoon, and skunk |
Non-insect invertebrates |
Crab, lobster, snail, spider, and worm |
People |
Baby, boy, girl, man, and woman |
Reptiles |
Crocodile, dinosaur, lizard, snake, and turtle |
Small mammals |
Hamster, mouse, rabbit, shrew, and squirrel |
Trees |
Maple, oak, palm, pine, and willow |
Vehicles 1 |
Bicycle, bus, motorcycle, pickup truck, and train |
Vehicles 2 |
Lawn-mower, rocket, streetcar, tank, and tractor |