DCGAN in TensorFlow
TensorFlow / TensorLayer implementation of Deep Convolutional Generative Adversarial Networks which is a stabilize Generative Adversarial Networks.
Looking for Text to Image Synthesis ? click 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.
Prerequisites
Usage
First, download images to data/celebA
:
$ python download.py celebA [202599 face images]
Second, train the GAN:
$ python main.py
Result on celebA