The Zuru ML Team (me, Federico Di Mattia, Paolo Galeone, Michele De Simoni) will present the tutorial: “Deep Diving into GANs: From Theory to Production with TensorFlow 2.0” at EuroSciPy in Bilbao, the 2nd of September 2019.
We will be showcasing all the shiny new APIs introduced by TensorFlow 2.0 by showing how to build a GAN from scratch and how to “productionize” it by leveraging the AshPy (see also here for more details) Python package that allows to easily design, prototype, train and export Machine Learning models defined in TensorFlow 2.0.
The workshop is composed of:
- Theoretical introduction
- GANs from Scratch in TensorFlow 2.0
- High-performance input data pipeline with TensorFlow Datasets
- Introduction to the AshPy API
- Implementing, training, and visualizing DCGAN using AshPy
- Production deployment using Google Cloud ML Engine and Google Cloud Functions
The materials of the workshop will be openly provided via GitHub (see here) prior to the event and will be run on Colab leveraging the free GPU.