You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Paddle/demo/gan
wangyang59 9a02bd419c
fixed a small bug in demo/gan/README.md and testMatrix.py
8 years ago
..
data unified cifar/mnist/uniform gan training in demo 8 years ago
.gitignore unified cifar/mnist/uniform gan training in demo 8 years ago
README.md fixed a small bug in demo/gan/README.md and testMatrix.py 8 years ago
gan_conf.py add readme and comments in demo/gan 8 years ago
gan_conf_image.py add readme and comments in demo/gan 8 years ago
gan_trainer.py add readme and comments in demo/gan 8 years ago

README.md

Generative Adversarial Networks (GAN)

This demo implements GAN training described in the original GAN paper (https://arxiv.org/abs/1406.2661) and DCGAN (https://arxiv.org/abs/1511.06434).

The general training procedures are implemented in gan_trainer.py. The neural network configurations are specified in gan_conf.py (for synthetic data) and gan_conf_image.py (for image data).

In order to run the model, first download the corresponding data by running the shell script in ./data. Then you can run the command below. The flag -d specifies the training data (cifar, mnist or uniform) and flag --useGpu specifies whether to use gpu for training (0 is cpu, 1 is gpu).

$python gan_trainer.py -d cifar --useGpu 1

The generated images will be stored in ./cifar_samples/