PyTorch implementation of Spectral Normalization for Generative Adversarial Networks
git clone https://github.com/godisboy/SN-GAN.git
- Train the standard model for 32*32 image size
python train.py --cuda(optional)
- Train the Res-Generator and Res-Discriminator for 64*64 image size
python train-res.py --cuda --dataPath /Path/to/yourdataset/
- Result of SN-GAN on CIFAR10 dataset
- Generated samples with Standard Generator and ResDiscriminator
The ResBlock of Res-Generator is different from what implemented in original paper.
This repo use
UpsamplingBilinear instead of
Uppooling for Upsampling operation.
Based on the implementation DCGAN and official implementation with Chainer sngan_projection
Open Source Agenda is not affiliated with "SN GAN" Project. README Source: godisboy/SN-GAN