Generative Adversarial Networks (GANs) is a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Papers for GANs:
- GANs are an interesting idea that were first introduced in 2014 by a group of researchers at the University of Montreal lead by Ian Goodfellow.
- Goodfellow, Ian, et al. “Generative adversarial nets.” Advances in Neural Information Processing Systems. 2014.
- Here’s a list of what started as a fun activity compiling all named GANs.
- The GAN Zoo from Github
Code for GANs:
- Generative Adversarial Networks (GANs) in 50 lines of code (PyTorch)
- Github Link: https://github.com/devnag/pytorch-generative-adversarial-networks
- A tensorflow implementation of “Deep Convolutional Generative Adversarial Networks”