Home

Awesome

GANs with spectral normalization and projection discriminator

This is an unofficial PyTorch implementation of sngan_projection

Miyato, Takeru, and Masanori Koyama. "cGANs with projection discriminator." arXiv preprint arXiv:1802.05637 (2018).

Dependencies:

Usage:

There are two ways to run the training script:

Parameters

ParametersFunction
--versionExperiment name
--trainSet the model stage, Ture---training stage; False---testing stage
--experiment_descriptionDescriptive text for this experiment
--total_stepTotally training step
--batch_sizeBatch size
--g_lrLearning rate of generator
--d_lrLearning rate of discriminator
--parallelEnable the parallel training
--datasetSet the dataset name,lsun,celeb,cifar10
--cudaSet GPU device number
--image_pathThe root dir to training dataset
--FID_mean_covThe root dir to dataset moments npz file

Results

We have reproduced the FID (in Cifar-10, best result is FID=17.2) result reported in the paper.

The convergence curve of FID is as follows:

image

CIFAR10 results

200K:

image

500K:

image

600K:

image

800K:

image

1000K:

image

Acknowledgement