As described by:
Adapted from initial DCGAN code:
https://github.com/carpedm20/DCGAN-tensorflow
Structure of GAN can be varied from 8x8 to 512x512 and onwards. Everything above 8x8 will try to load a model trained on the previous resolution.
python main.py 8
python main.py 16
...
python main.py 512
[========== Original README ==========]
Tensorflow implementation of Deep Convolutional Generative Adversarial Networks which is a stabilize Generative Adversarial Networks. The referenced torch code can be found here.
- Brandon Amos wrote an excellent blog post and image completion code based on this repo.
- To avoid the fast convergence of D (discriminator) network, G (generator) network is updated twice for each D network update, which differs from original paper.