Which of the two leading automatic-differentiation libraries — TensorFlow 2 or PyTorch — should you use for your deep learning models? My opinions, bolstered by recent usage data, are detailed in this talk that I gave at MLconf in November.

Thanks to Courtney Burton and Richard Rivera for inviting me to speak. It was an honor!

Abstract

This talk begins with a survey of the primary families of Deep Learning approaches: Convolutional Neural Networks, Recurrent Neural Networks, Generative Adversarial Networks, and Deep Reinforcement Learning. Via interactive demos, the meat of the talk will appraise the two leading Deep Learning libraries: TensorFlow and PyTorch. With respect to both model development and production deployment, the strengths and weaknesses of the two libraries will be covered — with a particular focus on TensorFlow 2 release that formally integrates the easy-to-use, high-level Keras API into the library.