Hardware Accelerators for Machine Learning (CS 217)

MNIST

The MNIST database of handwritten digits has a training set of 60,000 examples, and a test set of 10,000 examples. The digits have been size-normalized and centered in a fixed-size 28x28 image.
image source

CIFAR-10

The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.
image source

ImageNet

A large image database that has over ten million URLs of images that were hand-annotated using Amazon Mechanical Turk to indicate what objects are pictured.
source
image source

back