记录一些常见GAN的学习资料

1.DCGAN (DCGAN — Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks)

【Paper】 :

            http://arxiv.org/abs/1511.06434

【github】 :

            https://github.com/carpedm20/DCGAN-tensorflow  tensorflow

            https://github.com/jacobgil/keras-dcgan    keras

            https://github.com/soumith/dcgan.torch  torch


2.WGAN(Wasserstein GAN)

【paper】: 

            https://arxiv.org/abs/1701.07875

【GitHub】:

            https://github.com/hwalsuklee/tensorflow-generative-model-collections

            https://github.com/Zardinality/WGAN-tensorflow
 

3.WGAN-GP (Improved Training of Wasserstein GAN)
【paper】:

            https://arxiv.org/abs/1704.00028

【GitHub】:

           https://link.zhihu.com/?target=https%3A//github.com/igul222/improved_wgan_training

           https://github.com/caogang/wgan-gp
 

4.LSGAN (Least Squares Generative Adversarial Networks)

【paper】

            https://arxiv.org/abs/1611.04076

【github】

            https://github.com/hwalsuklee/tensorflow-generative-model-collections

            https://github.com/guojunq/lsgan
 

5.BEGAN (Boundary Equilibrium GAN)

【paper】:

            https://arxiv.org/abs/1703.10717

【GitHub】:

            https://github.com/carpedm20/BEGAN-tensorflow

            https://github.com/Heumi/BEGAN-tensorflow

            https://github.com/carpedm20/BEGAN-pytorch
 

 

 

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值