Learn to understand and implement a Deep Convolutional GAN (generative adversarial network) to generate realistic images, with Ian Goodfellow, the inventor of GANs, and Jun-Yan Zhu, the creator of CycleGANs.
Overview
Syllabus
- Introduction to Generative Adversarial Networks
- Introduction to this course, prerequisites, and your course instructor.
- Generative Adversarial Networks
- Ian Goodfellow, the inventor of GANs, introduces you to these exciting models. You'll also implement your own GAN on the MNIST dataset.
- Training a Deep Convolutional GANs
- In this lesson, you'll implement a Deep Convolution GAN to generate complex color images.
- Image to Image Translation
- Jun-Yan Zhu, one of the creators of the CycleGAN, will lead you through Pix2Pix and CycleGAN formulations that learn to do image-to-image translation tasks.
- Modern GANs
- In this lesson, you will implement more advanced GAN architectural techniques that have had a significant impact on the realism of generated images.
- Face Generation
- Define two adversarial networks, a generator, and a discriminator, and train them until you can generate realistic faces.
Taught by
nd0013 Thomas Hossler
