ML solutions for Live Perception (TF Dev Summit '20)

Live Perception is a challenging scenario enabled by on-device ML, in real-time, and with low-latency. In this talk you will learn about best practices and how to use TensorFlow Lite and TF.js to enable Live Perception solutions by diving into the technical details of 3 unique ML solutions: Face Meshes, Hand Poses and Object cuboids. Speaker: Matthias Grundmann - Research Scientist Resources: BlazeFace → https://goo.gle/2Tves6j GitHub Face Detection (GPU) → https://goo.gle/39wK8NY GitHub BlazeFace → https://goo.gle/39uCX9f Octi → https://goo.gle/2PT1Bs2 Model Card - BlazeFace Face Detection → https://goo.gle/2TFVKHQ On-Device, Real-Time Hand Tracking with MediaPipe blog → https://goo.gle/3auULRq Face Mesh Demo → https://goo.gle/39uDFDr GitHub MediaPipe → https://goo.gle/38un7Kf Watch all TensorFlow Dev Summit 2020 sessions → https://goo.gle/TFDS20 Subscribe to the TensorFlow YouTube channel → https://goo.gle/TensorFlow