You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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.