arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2101.06371cs.LGcs.AIcs.SE
收藏

NNStreamer:高效敏捷地开发设备上AI系统

NNStreamer: Efficient and Agile Development of On-Device AI Systems

Samsung Research, Samsung Electronics(三星电子三星研究院)

MyungJoo Ham, Jijoong Moon, Geunsik Lim, Jaeyun Jung, Hyoungjoo Ahn, Wook Song, Sangjung Woo, Parichay Kapoor, Dongju Chae, Gichan Jang, Yongjoo Ahn, Jihoon Lee

摘要:

我们提出了NNStreamer,一个软件系统,处理神经网络作为流管道的过滤器,应用流处理范式的深度神经网络应用。随着深度神经网络应用的广泛普及,一个新趋势是设备上人工智能。它是在移动设备或边缘/物联网设备上处理神经网络,而不是云服务器。新出现的隐私问题、数据传输成本和运营成本意味着对设备上AI的需求,特别是如果我们部署了大量设备。NNStreamer可有效处理设备上具有复杂数据流管道的神经网络,以最小的努力显著提高整体性能。此外,NNStreamer简化了实现,并允许直接重用现成的媒体过滤器,这大大降低了开发成本。我们已经在广泛的产品和平台上部署了NNStreamer,包括Galaxy系列和各种消费电子设备。实验结果表明,在开发成本和提高性能的管道架构和NNStreamer的减少。它是由Linux Foundation AI孵化的开源项目,可向公众提供,适用于各种硬件和软件平台。

英文摘要:

We propose NNStreamer, a software system that handles neural networks as filters of stream pipelines, applying the stream processing paradigm to deep neural network applications. A new trend with the wide-spread of deep neural network applications is on-device AI. It is to process neural networks on mobile devices or edge/IoT devices instead of cloud servers. Emerging privacy issues, data transmission costs, and operational costs signify the need for on-device AI, especially if we deploy a massive number of devices. NNStreamer efficiently handles neural networks with complex data stream pipelines on devices, significantly improving the overall performance with minimal efforts. Besides, NNStreamer simplifies implementations and allows reusing off-the-shelf media filters directly, which reduces developmental costs significantly. We are already deploying NNStreamer for a wide range of products and platforms, including the Galaxy series and various consumer electronic devices. The experimental results suggest a reduction in developmental costs and enhanced performance of pipeline architectures and NNStreamer. It is an open-source project incubated by Linux Foundation AI, available to the public and applicable to various hardware and software platforms.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑