TensorFlow / TensorLayer implementation of Deep Convolutional Generative Adversarial Networks which is a stabilize Generative Adversarial Networks.
- 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.
- Python 2.7 or Python 3.3+
- TensorFlow==0.10.0 or higher
- TensorLayer==1.2.6 or higher (already in this repo)
First, download dataset with:
$ python download.py celebA [202599 face images]
To train a model with downloaded dataset:
$ python main.py