jimfleming / DCGAN-tensorflow

A tensorflow implementation of Deep Convolutional Generative Adversarial Networks

DCGAN in Tensorflow

Tensorflow implementation of Deep Convolutional Generative Adversarial Networks which is a stabilize Generative Adversarial Networks. The referenced torch code can be found here.

To avoid the fast convergence of D (discriminator) network, G (generatior) network is updatesd twice for each D network update which is a different from original paper.

Online Demo

link

Prerequisites

• Python 2.7 or Python 3.3+
• Tensorflow
• SciPy
• (Optional) Align&Cropped Images.zip : Large-scale CelebFaces Dataset

Usage

First, download dataset with:

$ mkdir data
$ python download.py --datasets celebA

To train a model with celebA dataset:

$ python main.py --dataset celebA --is_train True --is_crop True

To test with an existing model:

$ python main.py --dataset celebA --is_crop True

Or, you can use your own dataset (without central crop) by:

$ mkdir data/DATASET_NAME
... add images to data/DATASET_NAME ...
$ python main.py --dataset DATASET_NAME --is_train True
$ python main.py --dataset DATASET_NAME

Results

After 6th epoch:

After 10th epoch:


With asian face dataset (with high noises):

More results can be found here and here.

Training details

Details of the loss of Discriminator and Generator (with custom dataset not celebA).

Details of the histogram of true and fake result of discriminator (with custom dataset not celebA).

Author

Taehoon Kim / @carpedm20