MNIST
(Modified National Institute Standards and Technology database)
- Contains grayscale 28x28 images of handwritten digits (from 0 to 9)
- Contains 60'000 training images and 10'000 testing images.
CIFAR-10
(Canadian Institute For Advanced REsearch)
- Contains 60'000 32x32 color images in 10 different classes
- There are 6'000 images of each class (airplane, car, bird, cat, deer, dog, frog, horse, ship, truck)
ImageNet
Full original dataset (ImageNet-21K or ImageNet-22K):
- Over 14'000'000 images in over 20'000 categories
- Images are colored, but size vary (from ~50x50 to ~4000x3000)
There are various popular subsets like ImageNet-1K
Since 2010, ImageNet project runs annual software contest (ILSVRC).