This is a Pytorch implementation for the paper "An Empirical Study on GANs with Margin Cosine Loss and Relativistic Discriminator". https://arxiv.org/abs/2110.11293

• python 3.7.3
• pytorch 1.2.0
• tensorflow 2.0.0
• torchtext 0.4.0
• torchvision 0.4.0
• mnist

• Run 0_prepare_dataset.py to automatically download, process and store images of CIFAR10, STL10, MNIST datasets. CAT dataset can be downloaded here.
• Download FID stats for CIFAR-10 at http://bioinf.jku.at/research/ttur/ttur_stats/fid_stats_cifar10_train.npz

• Run 1_train.sh to train our proposed loss function RMCosGAN along with other loss functions on four datasets.

DCGAN Architecture for CIFAR-10, MNIST and STL-10 datasets

DCGAN Architecture for CAT dataset

60 randomly-generated images with RMCosGAN at FID=31.34 trained on CIFAR-10 dataset

60 randomly-generated images with RMCosGAN at FID=13.17 trained on MNIST dataset

60 randomly-generated images with RMCosGAN FID=52.16 trained on STL-10 dataset

60 randomly-generated images with RMCosGAN at FID=9.48 trained on CAT dataset

Please cite our paper if RMCosGAN is used:

@article{RMCosGAN,
  title={An Empirical Study on GANs with Margin Cosine Loss and Relativistic Discriminator},
  author={Cuong Nguyen, Tien-Dung Cao, Tram Truong-Huu, Binh T.Nguyen},
  journal={},
  year={}
}

If this implementation is useful, please cite or acknowledge this repository on your work.

Cuong Nguyen (team@entropyart.io),

Tien-Dung Cao (dung.cao@ttu.edu.vn),

Tram Truong-Huu (tram.truong-huu@ieee.org),

Binh T.Nguyen (ngtbinh@hcmus.edu.vn)