激光与光电子学进展, 2020, 57 (4): 041011, 网络出版: 2020-02-20
基于灰色关联分析的卷积神经网络模型裁剪方法 下载: 903次
Method of Convolutional Neural Network Model Pruning Based on Gray Correlation Analysis
图像处理 模型裁剪 深度学习 卷积神经网络 灰色关联分析 模型加速 image processing model pruning deep learning convolutional neural network gray correlation analysis model acceleration
摘要
针对卷积神经网络巨大的计算量和存储量导致其难以应用于嵌入式终端设备的难题,提出了一种基于灰色关联分析的模型裁剪方法。利用基于灰色关联分析的裁剪方法处理经过数据训练后的权重模型文件,获得每个卷积核重要性的量化表示;每次裁剪从模型中删除量化结果值最小的卷积核,从而减少计算量,加快推理速度;对于新产生的模型,通过迭代训练来弥补其性能上的损失。实验结果表明,相比APoZ法、L1法,所提方法在同一推理速度提升下精度提高了5.3%和10.4%,在VGG-16模型上取得了相对于初始模型2.7倍的加速效果,存储量压缩为原来的1/13.5。
Abstract
A model pruning method based on gray correlation analysis is proposed to solve the problem that the convolutional neural network cannot be deployed on embedded devices due to the huge computation and memory space. For the weight model file after data training, the importance of each convolution kernel is quantized by using the pruning method based on gray correlation analysis. In each pruning, the convolution kernel with the minimum quantization result is deleted from the model so as to reduce the computation and accelerate the inferential speed. Iteration training is used to compensate for the performance loss of the new model. The experimental results show that compared with APoZ method and L1 method, the accuracy of the proposed method increases by 5.3% and 10.4% at the same inferential speed, the acceleration effect of VGG-16 model is 2.7 times that of the original model, and the memory space is reduced to 1/13.5.
黄世青, 白瑞林, 覃高鄂. 基于灰色关联分析的卷积神经网络模型裁剪方法[J]. 激光与光电子学进展, 2020, 57(4): 041011. Shiqing Huang, Ruilin Bai, Gaoe Qin. Method of Convolutional Neural Network Model Pruning Based on Gray Correlation Analysis[J]. Laser & Optoelectronics Progress, 2020, 57(4): 041011.