Article Source

• Generative Adversarial Networks and TF-GAN

Generative Adversarial Networks and TF-GAN

In this session of Machine Learning Tech Talks, Research Engineer Joel Shor will discuss a very cool development and technique in machine learning called Generative Adversarial Networks (GANs) and a library that offers open source to help make training and evaluating GANs easier.

Chapters

• Introduction
• Demos from Google
• What is a GAN?
• What are GANs good for?
• Deep dive: Metrics
• Deep dive: Self-attention GAN
• How to get started

Resources

• Boundless video → https://goo.gle/3AfOjf0
• GANSynth project page → https://goo.gle/3xcm8vr
• Batch equalization paper → https://goo.gle/2TgkudL
• Superresolution colab → https://goo.gle/3y5xbqi
• Image-to-image translation colab → https://goo.gle/3hmwYrZ
• CycleGAN colab → https://goo.gle/3dwKyrG
• Inception Score implementation → https://goo.gle/3ydL322
• Frechet Inception Distance implementation → https://goo.gle/2UMTfYo
• Self-Attention GAN implementation → https://goo.gle/3627o6q
• TF-GAN examples → https://goo.gle/3w3xvEE