gan1

Paper:

DCGAN: Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

WGAN: Wasserstein GAN

WGAN-GP:  Improved Training of Wasserstein GANs

LSGAN:  Least Squares Generative Adversarial Networks

SNGAN:  Spectral normalization for generative adversarial networks

RSGAN:  The relativistic discriminator: a key element missing from standard GAN

损失函数如下表所示：

 

 

   
   

   
————————————————
版权声明：本文为CSDN博主「MarTin Guo」的原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/Geoffrey_MT/article/details/81198504