摘要： 浮栅器件(Flash)能够将存储和计算的特性相结合，实现存算一体化，但是单个浮栅单元最多只能存储位宽为4 bit的数据。面向Nor Flash，研究了卷积神经网络参数的低位宽量化，对经典的AlexNet、VGGNet以及ResNet通过量化感知训练。采用非对称量化，将模型参数从32位浮点数量化至4位定点数，模型大小变为原来的1/8，针对Cifar10数据集，4位量化模型的准确率相对于全精度网络仅下降不到2%。最后将量化完成的卷积神经网络模型使用Nor Flash阵列加速。Hspice仿真结果表明，相对于全精度模型，部署在Nor Flash阵列中的量化模型精度仅下降2.25%，验证了卷积神经网络部署在Nor Flash上的可行性。

中图分类号： TP183
文献标识码： A
DOI： 10.19358/j.issn.2096-5133.2021.06.007
引用格式： 陈雅倩，黄鲁. 基于浮栅器件的低位宽卷积神经网络研究[J].信息技术与网络安全，2021，40(6)：38-42.

Quantification research of convolutional neural network oriented Nor Flash

Abstract： Flash is one of the most promising candidates to bulid processing-in-memory(PIM)structures. However,the data width in one flash is 4bit at most. This article is oriented to Nor Flash and studies the quantitzation of convolution neural network. It performs quantitative perception training on the classic AlexNet, VGGNet and ResNet, and uses asymmetric quantization to quantify the model parameters from 32-bit floating point to 4-bit, and the model size becomes 1/8 of the original. For the Cifar10 data set, the accuracy of the 4-bit quantization model is only less than 2% lower than that of the full-precision network. Finally, the quantized convolutional neural network model is accelerated by the Nor Flash array. Hspice simulation results show that the accuracy of the quantized model bulided in the Nor Flash array is only reduced by 2.25% compared to the full-precision model. The feasibility of deploying the convolutional neural network on Nor Flash is verified.

Key words : convolution neural network；quantification；computation in memory；Nor Flash