//Description: GAN
//Create Date: 2022-01-24 17:28:39
//Author: channy
An Introduction to Image Synthesis with Generative Adversarial Nets
原始GAN,输出仅依赖于随机噪声G(z)
给输入增加条件G(c, z)
原始GAN的G和D换成CNN
在CGAN的基础上增加分类器
使用 Wasserstein 距离来测量真实数据分布与学习分布之间的相似性,而不是像原始 GAN 那样使用 Jensen-Shannon 散度。
双向转换,G_ab和G_ba,D_a和D_b
You can also check out the same data in a tabular format with functionality to filter by year or do a quick search by title here.
Contributions are welcome. Add links through pull requests in gans.tsv file in the same format or create an issue to lemme know something I missed or to start a discussion.
Check out Deep Hunt - my weekly AI newsletter for this repo as blogpost and follow me on Twitter.
ReGAN - [ReGAN: RE[LAX | BAR | INFORCE] based Sequence Generation using GANs](https://arxiv.org/abs/1805.02788) (github) |