{"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/nnstreamer-stream-processing-paradigm-for","title":"NNStreamer: Stream Processing Paradigm for Neural Networks, Toward Efficient Development and Execution of On-Device AI Applications","arxiv_id":"1901.04985","date":"2019-01-12","proceeding":null,"authors":["MyungJoo Ham","Ji Joong Moon","Geunsik Lim","Wook Song","Jaeyun Jung","Hyoungjoo Ahn","Sangjung Woo","Youngchul Cho","Jinhyuck Park","Sewon Oh","Hong-Seok Kim"],"abstract":"We propose nnstreamer, a software system that handles neural networks as\nfilters of stream pipelines, applying the stream processing paradigm to neural\nnetwork applications. A new trend with the wide-spread of deep neural network\napplications is on-device AI; i.e., processing neural networks directly on\nmobile devices or edge/IoT devices instead of cloud servers. Emerging privacy\nissues, data transmission costs, and operational costs signifies the need for\non-device AI especially when a huge number of devices with real-time data\nprocessing are deployed. Nnstreamer efficiently handles neural networks with\ncomplex data stream pipelines on devices, improving the overall performance\nsignificantly with minimal efforts. Besides, nnstreamer simplifies the neural\nnetwork pipeline implementations and allows reusing off-shelf multimedia stream\nfilters directly; thus it reduces the developmental costs significantly.\nNnstreamer is already being deployed with a product releasing soon and is open\nsource software applicable to a wide range of hardware architectures and\nsoftware platforms.","url_abs":"http://arxiv.org/abs/1901.04985v1","url_pdf":"http://arxiv.org/pdf/1901.04985v1.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":"nnstreamer-stream-processing-paradigm-for","repo_url":"https://github.com/nnstreamer/nnstreamer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}