Researchers accelerate sparse inference on XNNPack and TensorFlow Lite for realtime apps March 9, 2021 by admin Tweet XNNPack and TensorFlow Lite now support efficient inference of sparse networks. Researchers demonstrated substantial speedups in inference times on realtime gesture detection and background blur apps. Read more… Neowin Related Posts:Nvidia announces TensorRT 8, slashes BERT inference…Google Research launches MoveNet with TensorFlow.js APILinux Lite 6.4 released with WebP support, runs on…Microsoft adds Authenticator Lite for Outlook on iOS…AT&T partners with Samsung to launch a kids'…