[Updated on 2018-09-30: thanks to Yoonju, we have this post translated in Korean!] [Updated on 2019-04-18: this post is also available on arXiv.] Generative adversarial network (GAN) has shown great results in many generative tasks to replicate the real-world rich content such as images, human language, and music. It is inspired by game theory: two models, a generator and a critic, are competing with each other while making each other stronger at the same time.
GANs in PyTorch: DCGAN, cGAN, LSGAN, InfoGAN, WGAN and more - CV Notes
Improving Generative Adversarial Network (GAN) - ppt download
From GAN to WGAN - MillionScope
Comparison of the three different GAN variants: Vanilla GAN, LSGAN and
generative models - How to interprete Discriminator and Generator loss in WGAN - Cross Validated
Comparing Beta-VAE to WGAN-GP for Time Series Augmentation to Improve Classification Performance
4. Generative Adversarial Networks - Generative Deep Learning [Book]
63 - PyTorch Wasserstein GAN (WGAN) Implementation from scratch, Deep Learning
How to Develop a Wasserstein Generative Adversarial Network (WGAN) From Scratch
PyLessons
WGAN: Wasserstein Generative Adversarial Networks
Generative Adversarial Networks - The Story So Far
A time-series Wasserstein GAN method for state-of-charge estimation of lithium-ion batteries - ScienceDirect
Synthetic flow-based cryptomining attack generation through Generative Adversarial Networks