[Pycon] [new paper] "Michele De Simoni" - Deep Diving into GANs: form theory to production

[info a pycon.it]

Title: Deep Diving into GANs: form theory to production
Duration: 240 (includes Q&A)
Q&A Session: 0
Language: en
Type: Talk

Abstract: GANs are the new hottest topic in the ML arena; however, they present a challenge for the researchers and the engineers alike. Their design, and most importantly, the code implementation has been causing headaches to the ML practitioners, especially when moving to production.

Starting from the very basic of what a GAN is, passing trough Tensorflow implementation, using the most cutting-edge APIs available in the framework, and finally, production-ready serving at scale using Google Cloud ML Engine.

Tags: [u'gan', u'gans', u'Keras', u'tensorflow', u'deep learning', u'generative-models']