Skip to content

Implementation of the deep convolutional GAN paper titled "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks" using PyTorch and PyTorch Lightning.

License

Notifications You must be signed in to change notification settings

the-neural-networker/deep-convolutional-gan

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

36 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Deep Convolutional GANs with PyTorch

Description

Pytorch implementation of the deep convolutional GAN paper titled "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks" using PyTorch. Link to the original paper by Radford, A., Metz, L. and Chintala, S. You can also find the vanilla GAN paper by Goodfellow, I. et al. for training details.

DCGAN Generator

How to run

First, install dependencies (a new python virtual environment is recommended).

# clone project   
git clone https://github.com/visualCalculus/deep-convolutional-gan

# install project   
cd deep-convolutional-gan
pip install -e .
pip install -r requirements.txt

Next, navigate to dcgan folder and run train.py with appropriate command line arguments.

# module folder
cd dcgan

# run module
python train.py --gpus=1 --max_epochs=5 --dataset=MNIST --image_size=32 --batch_size=128 --z_dim=100
--z_filter_shape=2 --n_channels=1 --learning_rate=2e-4 --beta1=0.5

Results

DCGAN trained for 10 epochs on MNIST.

result1

DCGAN trained for 50 epochs on CIFAR10.

result2

Citation

@misc{visualCalculus2021dcgan,
  title={deep-convolutional-gan},
  author={Tejomay, Abhiroop},
  publisher={GitHub}
  journal={GitHub repository},
  year={2021},
  howpublished={\url{https://github.com/visualCalculus/deep-convolutional-gan}}
}

About

Implementation of the deep convolutional GAN paper titled "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks" using PyTorch and PyTorch Lightning.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages