paarthneekhara / dcgan

Deep Convolutional Generative Adversarial Networks - TensorFlow

DCGAN in TensorFlow

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.

Prerequisites

• Python 2.7 or Python 3.3+
• TensorFlow==0.10.0 or higher
• TensorLayer==1.2.6 or higher (already in this repo)

Usage

First, download dataset with:

$ python download.py celebA		[202599 face images]

To train a model with downloaded dataset:

$ python main.py