https://github.com/rubenszimbres/gan-project-2018
GAN in Tensorflow to be run via Linux command line
https://github.com/rubenszimbres/gan-project-2018
dcgan dcgan-mnist-tutorial dcgan-tensorflow gan generative-adversarial-network generative-adversarial-networks linux-kernel tensorflow tensorflow-models
Last synced: 2 months ago
JSON representation
GAN in Tensorflow to be run via Linux command line
- Host: GitHub
- URL: https://github.com/rubenszimbres/gan-project-2018
- Owner: RubensZimbres
- Created: 2018-04-30T11:34:01.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2018-05-04T11:20:55.000Z (over 7 years ago)
- Last Synced: 2025-04-07T02:22:07.988Z (6 months ago)
- Topics: dcgan, dcgan-mnist-tutorial, dcgan-tensorflow, gan, generative-adversarial-network, generative-adversarial-networks, linux-kernel, tensorflow, tensorflow-models
- Language: Python
- Homepage:
- Size: 1.8 MB
- Stars: 22
- Watchers: 3
- Forks: 16
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Generative Adversarial Networks in Tensorflow - Linux Shell
My GitHub project on GANs to be run via Windows/Linux shell command
Instructions:
```
$ git clone https://github.com/RubensZimbres/GAN-Project-2018
$ cd GAN-Project-2018
```
If you are sure all the libraries in requirements.txt are installed, go to $ python main.py ...
```
$ conda install --yes --file requirements.txt
$ python main.py --epoch=4000 --learning_rate=0.0002 --your_login=rubens
```
Arguments:
--epoch: default=5000
--learning_rate: default=0.0001
--sample_size: default=60
--gen_hidden: # hidden nodes in generator: default=80
--disc_hidden: # hidden nodes in discriminator: default=80
--your_login: your login in your OS: default:rubens
Tensorboard will start AFTER you close the pop-up (GAN output with MNIST digits)
