Stacked MNIST

Introduced by Metz et al. in Unrolled Generative Adversarial Networks

The Stacked MNIST dataset is derived from the standard MNIST dataset with an increased number of discrete modes. 240,000 RGB images in the size of 32×32 are synthesized by stacking three random digit images from MNIST along the color channel, resulting in 1,000 explicit modes in a uniform distribution corresponding to the number of possible triples of digits.

Source: Inclusive GAN: Improving Data and Minority Coverage in Generative Models


Paper Code Results Date Stars

Dataset Loaders

No data loaders found. You can submit your data loader here.



  • Unknown