What is the CIFAR-10 and CIFAR-100 Dataset in TensorFlow?

There are a few datasets that are part of tensorflow and widely used in Machine Learning. CIFARCanadian Institute For Advanced Research contains subsets of 80 million small pictures collected in datasets CIFAR-10 and CIFAR-100. These were originally collected by Alex Krizhevsky, Geoffrey Hinton, and Vinod Nair. There are a total of 60,000 images in these datasets, both of which have the following composition:

1. Training: Five training batches, each with 10,000 images.

2. Testing: One test batch with 10,000 images.

CIFAR-10

CIFAR-10 consists of 10 classes, i.e., airplanes, cars, birds, cats, deer, dogs, frogs, horses, ships, and trucks.

Key Features of CIFAR-10:

1. 10,000 test images, 1000 images per class. Test images are randomly-selected images from each class.

2. 50,000 training images, 5000 images per class. The rest of images (minus the test images from total images) are comprised of training images. However, some training images may contain more images in one class.

3. The classes in the dataset are entirely mutually exclusive.

4. CIFAR-10 consists of 60,000 32 X 32 images (low resolution). They are mostly used in Convolutional Neural Network (CNN) models.

CIFAR-100

Just like CIFAR-10, CIFAR-100 also contains 60,000 images. However, instead of 10 classes in CIFAR-10, CIFAR-100 consists of 100 classes with 20 superclasses. All the images in this dataset contain two labels, coarse label (defines the superclass of the image) and a fine label (defines the class of the label).

Key features of CIFAR-10

1. 10,000 test images, 100 test images per class for 100 classes.

2. 50,000 training images, 500 images per class for 100 classes

Superclass: Classes

Let’s look at the classes and superclasses of the CIFAR-100 dataset.

Below are the classes in the CIFAR-100 dataset:

1. Flowers: Orchids, poppies, roses, sunflowers, tulips.

2. Fish: Aquarium fish, flatfish, ray, shark, trout.

3. Aquatic mammals: Beaver, dolphin, otter, seal, whale.

4. Food containers: Bottles, bowls, cans, cups, plates.

5. Household electrical devices: Clock, lamp, telephone, television, computer keyboard.

6. Fruit and vegetables: Apples, mushrooms, oranges, pears, sweet peppers.

7. Household furniture: Table, Chair, couch, wardrobe, bed.

8. Insects: bee, beetle, butterfly, caterpillar, cockroach.

9. Large natural outdoor scenes: Cloud, forest, mountain, plain, sea.

10. Large human-made outdoor things: Bridge, castle, house, road, skyscraper.

11. Large carnivores: Bear, leopard, lion, tiger, wolf.

12. Medium-sized mammals: Fox, porcupine, possum, raccoon, skunk.

13. Large Omnivores and herbivores: Camel, cattle, chimpanzee, elephant, kangaroo.

14. Non-insect: invertebrates Crab, lobster, snail, spider, worm.

15. Reptiles: Crocodile, dinosaur, lizards, snake, turtle.

16. Trees: Maple, oak, palm, pine, willow.

17. People girl, man, women, baby, boy.

18. Small mammals: Hamster, rabbit, mouse, shrew, squirrel.

19. Vehicles 1: Bicycle, bus, motorcycle, pickup truck, train.

20. Vehicles 2: Lawn-mower, rocket, streetcar, tractor, tank.