CIFAR-10 and CIFAR-100 are labeled subsets of the 80 Million Tiny Images dataset collected by Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton for image classification research. CIFAR-10 contains 60,000 32×32 color images in 10 mutually exclusive object classes, with 50,000 training and 10,000 test images. CIFAR-100 has the same number and size of images but spans 100 fine-grained classes grouped into 20 superclasses, with 500 training and 100 test images per class. Each image is represented as RGB pixel values, and CIFAR-100 provides both fine and coarse labels, making the datasets standard benchmarks for training and evaluating machine learning and computer vision models.