Generative Adversarial Networks and TF-GAN (ML Tech Talks)

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.

0:00 – Introduction
1:29 – Demos from Google
11:42 – What is a GAN?
27:14 – What are GANs good for?
41:59 – Deep dive: Metrics
54:05 – Deep dive: Self-attention GAN
57:47 – How to get started

Boundless video →
GANSynth project page →
Batch equalization paper →
Superresolution colab →
Image-to-image translation colab →
CycleGAN colab →
Inception Score implementation →
Frechet Inception Distance implementation →
Self-Attention GAN implementation →
TF-GAN examples →

Catch more ML Tech Talks →
Subscribe to TensorFlow →

product: TensorFlow – General; re_ty: Publish;