论文标题
MNN：一种普遍有效的推理引擎
MNN: A Universal and Efficient Inference Engine
论文作者
论文摘要
在移动设备上部署深度学习模型最近引起了越来越多的关注。但是，在设备上设计有效的推理引擎是模型兼容性，设备多样性和资源限制的巨大挑战。为了应对这些挑战，我们建议移动神经网络（MNN），这是一种针对移动应用程序量身定制的通用和高效的推理引擎。在本文中，MNN的贡献包括：（1）提出一种称为预先推论的机制，该机制设法进行运行时优化； （2）对操作员的核内核优化，以实现最佳计算性能； （3）引入后端抽象模块，该模块可实现混合计划并保持发动机轻巧。广泛的基准实验表明，MNN对其他流行的轻量级深度学习框架表现出色。 MNN可向公众提供：https：//github.com/alibaba/mnn。
Deploying deep learning models on mobile devices draws more and more attention recently. However, designing an efficient inference engine on devices is under the great challenges of model compatibility, device diversity, and resource limitation. To deal with these challenges, we propose Mobile Neural Network (MNN), a universal and efficient inference engine tailored to mobile applications. In this paper, the contributions of MNN include: (1) presenting a mechanism called pre-inference that manages to conduct runtime optimization; (2)deliveringthorough kernel optimization on operators to achieve optimal computation performance; (3) introducing backend abstraction module which enables hybrid scheduling and keeps the engine lightweight. Extensive benchmark experiments demonstrate that MNN performs favorably against other popular lightweight deep learning frameworks. MNN is available to public at: https://github.com/alibaba/MNN.
