Benchmark Datasets

Updated: 2020-12-31

BLEU, a metric for measuring the performance of human language translated by machines.

Dataset Name Rows Columns Cells Description
MNIST 60,000 784 >39.2M 60K 28×28 images
Higgs 10,000,000 28 280M
Molecular 150,000 2,871 430M
CIFAR-10 RGB 32x32 pixel images across 10 categories

CIFAR-10 Categories: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, and truck.