physhik / dcgan

A Tensorflow Implementation of "Deep Convolutional Generative Adversarial Networks" - (EASY to READ)

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

• Python 2.7 or Python 3.3+
• TensorFlow==1.0+
• TensorLayer==1.4+

Usage

First, download images to data/celebA:

$ python download.py celebA		[202599 face images]

Second, train the GAN:

$ python main.py

Result on celebA