Here's a very concise DCGAN implementation in Keras. Implementing arbitrary deep learning models doesn't get simpler than thathttps://colab.research.google.com/drive/1f3GOVrhwBrtltnwKrafzaKL3fKtIKqgb?usp=sharing …
-
-
thanks! very impressive that 30 epochs suffice to get reasonable faces. what about super high quality faces? are we talking about say 10x more epochs or much more than that?
-
You should use a more advanced model for that, like StyleGAN2.
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.