This is a Pytorch implementation of Wasserstein GANs with gradient penalty.
Link to the paper is : https://arxiv.org/pdf/1704.00028.pdf
We are using a Dataset consisting of around 15,700 images of cats, and then generating pictures of cats .The hyperparameters such as learning rate, n_critic, beta1, beta2 are assigned the same values as mentioned in the paper . The noise dimension is set to 100 as suggested in the paper.
iteration_1 :
iteration_10000 :
iteration_17000 :
iteration_25000 :