CNNdroid: GPU-Accelerated Execution of Trained Deep Convolutional Neural Networks on Android

November 23, 2015 · Entered Twilight · 🏛 ACM Multimedia

"Last commit was 8.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: Android Studio Project Template, CNNdroid Complete Developers Guide and Installation Instruction.pdf, CNNdroid Source Package, Demo Android Applications, LICENSE, NetFile Examples, Parameter Generation Scripts, README.md, Virtual Machine(ACM mm'16)

Authors Seyyed Salar Latifi Oskouei, Hossein Golestani, Matin Hashemi, Soheil Ghiasi arXiv ID 1511.07376 Category cs.DC: Distributed Computing Cross-listed cs.CV Citations 106 Venue ACM Multimedia Repository https://github.com/ENCP/CNNdroid ⭐ 542 Last Checked 1 month ago

Abstract

Many mobile applications running on smartphones and wearable devices would potentially benefit from the accuracy and scalability of deep CNN-based machine learning algorithms. However, performance and energy consumption limitations make the execution of such computationally intensive algorithms on mobile devices prohibitive. We present a GPU-accelerated library, dubbed CNNdroid, for execution of trained deep CNNs on Android-based mobile devices. Empirical evaluations show that CNNdroid achieves up to 60X speedup and 130X energy saving on current mobile devices. The CNNdroid open source library is available for download at https://github.com/ENCP/CNNdroid