m53297601
/
Paddle
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
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.
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'a186b53dfb'
${ noResults }
Paddle/v1_api_demo/vae
History
Luo Tao 46e60761d1
remove duplicated examples, and rename demo to v1_api_demo 		8 years ago
..
data remove duplicated examples, and rename demo to v1_api_demo 8 years ago
README.md remove duplicated examples, and rename demo to v1_api_demo 8 years ago
dataloader.py remove duplicated examples, and rename demo to v1_api_demo 8 years ago
vae_conf.py remove duplicated examples, and rename demo to v1_api_demo 8 years ago
vae_train.py remove duplicated examples, and rename demo to v1_api_demo 8 years ago

README.md

#Variational Autoencoder (VAE)

This demo implements VAE training described in the original paper (https://arxiv.org/abs/1312.6114).

In order to run the model, first download the MNIST dataset by running the shell script in ./data.

Then you can run the command below. The flag --useGpu specifies whether to use gpu for training (0 is cpu, 1 is gpu).

$python vae_train.py [--use_gpu 1]

The generated images will be stored in ./samples/ The corresponding models will be stored in ./params/