{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fast-and-energy-efficient-cnn-inference-on","title":"Fast and Energy-Efficient CNN Inference on IoT Devices","arxiv_id":"1611.07151","date":"2016-11-22","proceeding":null,"authors":["Mohammad Motamedi","Daniel Fong","Soheil Ghiasi"],"abstract":"Convolutional Neural Networks (CNNs) exhibit remarkable performance in\nvarious machine learning tasks. As sensor-equipped internet of things (IoT)\ndevices permeate into every aspect of modern life, it is increasingly important\nto run CNN inference, a computationally intensive application, on resource\nconstrained devices. We present a technique for fast and energy-efficient CNN\ninference on mobile SoC platforms, which are projected to be a major player in\nthe IoT space. We propose techniques for efficient parallelization of CNN\ninference targeting mobile GPUs, and explore the underlying tradeoffs.\nExperiments with running Squeezenet on three different mobile devices confirm\nthe effectiveness of our approach. For further study, please refer to the\nproject repository available on our GitHub page:\nhttps://github.com/mtmd/Mobile_ConvNet","url_abs":"http://arxiv.org/abs/1611.07151v1","url_pdf":"http://arxiv.org/pdf/1611.07151v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fast-and-energy-efficient-cnn-inference-on","repo_url":"https://github.com/mtmd/Mobile_ConvNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"fire-module","method_name":"Fire Module"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"squeezenet","method_name":"SqueezeNet"},{"method_slug":"xavier-initialization","method_name":"Xavier Initialization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}