Bookmark and Share

"Building Efficient CNN Models for Mobile and Embedded Applications," a Presentation from Facebook

Peter Vajda, Research Scientist at Facebook, presents the "Building Efficient CNN Models for Mobile and Embedded Applications" tutorial at the May 2018 Embedded Vision Summit.

Recent advances in efficient deep learning models have led to many potential applications in mobile and embedded devices. In this talk, Vajda discusses state-of-the-art model architectures, and introduces Facebook's work on real-time style transfer and pose estimation on mobile phones.