Skip to content
/ SNGAN Public

A Pytorch implementation of "Spectral Normalization for Generative Adversarial Networks"

Notifications You must be signed in to change notification settings

isr-wang/SNGAN

Repository files navigation

Pytorch Implementation of SN-GAN with CIFAR10

Requirements

nsml

Paper

Spectral Normalization for Generative Adversarial Networks

Run Example

nsml run -d cifar10_python -a "--sn"                   # Spectralnorm
nsml run -d cifar10_python                             # No SN
nsml run -d cifar10_python -a "--sn --inception_score" # Calculate Inception score

Of course, executing python main.py will do well if you make empty functions for nsml.

Architecture

GAN Architecture is adopted from the papers' Appendix B.4 for CIFAR10

Results

Generated images

Loss

About

A Pytorch implementation of "Spectral Normalization for Generative Adversarial Networks"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages