From: Evaluation of maxout activations in deep learning across several big data domains
Dataset | Train | Test |
---|---|---|
Amazon4M | 3,600,000 | 400,000 |
Sentiment140 | 1,440,000 | 160,000 |
Amazon | 900,000 | 100,000 |
Yelp1M | 899,611 | 99,957 |
Yelp500K | 386,154 | 42,907 |
Google Speech Commands | 94,824 | 11,005 |
MS-Celeb | 91,683 | 5000 |
MNIST | 60,000 | 10,000 |
Fashion-MNIST | 60,000 | 10,000 |
CIFAR-10 | 50,000 | 10,000 |
CIFAR-100 | 50,000 | 10,000 |
IDMT-SMT-Audio-Effects | 37,065 | 4119 |
IRMAS | 18,103 | 2012 |
LFW | 5400 | 600 |
Medicare Part B | 2618 | 200 |
Medicare Part D | 1836 | 200 |
DMEPOS | 1070 | 200 |
Combined CMS | 846 | 100 |