利用模型剪裁和编译器优化实现移动平台上的深度神经网络实时推断（CS LG）---刘持诚

高端移动平台迅速成为广泛的深度神经网络（DNN）应用的主要计算设备。然而，这些设备上受限的计算和存储资源仍然给实时 DNN 推理执行带来了巨大的挑战。为了解决这个问题，我们提出了一套硬件友好的结构化模型剪枝和编译器优化技术来加速 DNN 在移动设备上的执行。这个演示表明，这些优化技术可以实现多种 DNN 应用的实时移动执行，包括样式转移、DNN 着色和超级分辨率。

原文题目：Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization

原文：High-end mobile platforms rapidly serve as primary computing devices for a wide range of Deep Neural Network (DNN) applications. However, the constrained computation and storage resources on these devices still pose significant challenges for real-time DNN inference executions. To address this problem, we propose a set of hardware-friendly structured model pruning and compiler optimization techniques to accelerate DNN executions on mobile devices. This demo shows that these optimizations can enable real-time mobile execution of multiple DNN applications, including style transfer, DNN coloring and super resolution.

原文作者：Wei Niu, Pu Zhao, Zheng Zhan, Xue Lin, Yanzhi Wang, Bin Ren

原文地址：https://arxiv.org/abs/2004.11250