Generative Lecture 5: Generative Adversarial Networks (GAN)
This note introduces GANs through distribution matching and adversarial training, then explains Wasserstein distance, WGAN, and the use of weight clipping and gradient penalties.
TAG
共有 1 篇文章提到了这个关键词。
This note introduces GANs through distribution matching and adversarial training, then explains Wasserstein distance, WGAN, and the use of weight clipping and gradient penalties.