There are no reviews yet. Be the first to send feedback to the community and the maintainers!
Repository Details
Implementation of DCGAN paper with bernoulli distribution used as input noise vector and slight modification to train it better and skip modal collapse. The results are taken on anime dataset generated from doonami.ru website using 21k images as test samples and training on 50 epochs with learning-rate = 0.002 . Lots of slight modifications have been done to improve GANs training.
