Generative Adversarial Networks (GANs) in PyTorch
See https://medium.com/@devnag/generative-adversarial-networks-gans-in-50-lines-of-code-pytorch-e81b79659e3f#.sch4xgsa9 for the relevant blog post.
Run the sample code by typing:
...and you'll train two nets to battle it out on a shifted/scaled Gaussian distribution. The 'fake' distribution should match the 'real' one within a reasonable time.