Hands-On Generative Adversarial Networks with Keras

Related work

The Generative Adversarial Networks framework has received a lot of attention lately. Despite the youth of Generative Adversarial Networks, several publications ((Arjovsky and Bottou, 2017), (Salimans et al., 2016), (Zhao et al., 2016), (Radford et al., 2015)) have investigated the use of the GAN framework for sample generation and unsupervised feature learning. Following the procedure described in (Breuleux et al., 2011) and used in (Goodfellow et al., 2014a), earlier GAN papers evaluated the quality of the fake samples by fitting a Gaussian Parzen window to the fake samples and reporting the log-likelihood of the test set under this distribution. As mentioned in (Goodfellow et al., 2014a), this method has some drawbacks, ...