Shantam Bajpai
-
DCGAN (Deep Convolutional Generative adversarial network)
-
WGAN (Wasserstein Generative Adversarial Network)
-
WGAN With Gradient Penalty
-
CGAN (Conditional Generative adversarial network)
-
EBGAN (Energy Based Generative Adversarial Network)
Calculate the Inception Scores and Compute the Fretchet Inception Distance.
The dataset used to train the Generative adversarial networks was the celeba dataset which is a large scale face attributes dataset with more than 200K Celebrity faces and the MNIST Dataset (For conditional Wasserstein GAN-GP).
DCGAN: https://arxiv.org/pdf/1511.06434.pdf
WGAN: https://arxiv.org/pdf/1701.07875.pdf
WGAN-GP: https://arxiv.org/pdf/1704.00028v3.pdf