Me and my colleagues (Federico Di Mattia, Paolo Galeone, Michele De Simoni) held the training: “Deep Diving into GANs: From Theory To Production” at PyCon X in Florence.

Figure 1 - PyConX

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.

The material is available on Github.

Take a look at the slides of the theory part:

The training is divided in 4 parts:

Here some photos of the tutorial: