arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.04060cs.CV
收藏

量化神经网络的简化部署

Streamlined Deployment for Quantized Neural Networks

Norwegian University of Science and Technology(挪威科技大学)

Yaman Umuroglu, Magnus Jahre

摘要:

在计算能力有限的设备上运行深度神经网络(DNN)模型是一项挑战,因为需要大量的计算和内存。量化神经网络(QNN)已成为解决这一问题的潜在方案,有望以更低的计算成本提供大部分DNN精度优势。然而,在现有的移动CPU上收获这些好处是一个挑战,因为在大多数指令集架构(ISA)中不原生地支持对高度量化的数据库的操作。在这项工作中,我们首先描述了一个精简流程,将所有的QNN推理操作转换为整数。之后,我们提供了基于一次处理一个位位置(位串行)的技术,以展示如何使用常见的按位操作有效地部署QNN。我们通过微基准测试和量化的AlexNet在移动CPU上展示了QNN的潜力,它比优化的8位基线快3.5倍。我们的位串行矩阵乘法库可在GitHub上获得,网址为https://git.io/vhshn

英文摘要:

Running Deep Neural Network (DNN) models on devices with limited computational capability is a challenge due to large compute and memory requirements. Quantized Neural Networks (QNNs) have emerged as a potential solution to this problem, promising to offer most of the DNN accuracy benefits with much lower computational cost. However, harvesting these benefits on existing mobile CPUs is a challenge since operations on highly quantized datatypes are not natively supported in most instruction set architectures (ISAs). In this work, we first describe a streamlining flow to convert all QNN inference operations to integer ones. Afterwards, we provide techniques based on processing one bit position at a time (bit-serial) to show how QNNs can be efficiently deployed using common bitwise operations. We demonstrate the potential of QNNs on mobile CPUs with microbenchmarks and on a quantized AlexNet, which is 3.5x faster than an optimized 8-bit baseline. Our bit-serial matrix multiplication library is available on GitHub at https://git.io/vhshn

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。

↑