Generative adversarial network: Difference between revisions
No edit summary |
|||
| Line 8: | Line 8: | ||
For iteration i | For iteration i | ||
For iteration j | For iteration j | ||
Update | Update Discriminator | ||
Update | Update Generator | ||
</pre> | </pre> | ||
==Variations== | ==Variations== | ||
===Wasserstein GAN=== | |||
[https://arxiv.org/pdf/1704.00028.pdf Paper]<br> | |||
[https://medium.com/@jonathan_hui/gan-wasserstein-gan-wgan-gp-6a1a2aa1b490 Medium post]<br> | |||
This new WGAN-GP loss function improves the stability of training. | |||
==Applications== | |||
===CycleGan=== | ===CycleGan=== | ||
===InfoGAN=== | ===InfoGAN=== | ||
Revision as of 13:19, 12 November 2019
GANs are generative adversarial networks. They were developed by Ian Goodfellow.
Goal: Learn to generate examples from the same distribution as your training set.
Basis Structure
GANs consist of a generator and a discriminator.
For iteration i
For iteration j
Update Discriminator
Update Generator
Variations
Wasserstein GAN
Paper
Medium post
This new WGAN-GP loss function improves the stability of training.
Applications
CycleGan
InfoGAN
SinGAN
Paper
Website
Github Official PyTorch Implementation
SinGAN: Learning a Generative Model from a Single Natural Image