Convolutional Neural Network Model Compression Algorithm Based on Factor Analysis
Aiming at the problems of large parameter scale and long operation time of complex convolutional neu-ral network models,an effective convolutional neural network model compression algorithm was proposed.The fac-tor analysis was introduced to compress the convolutional neural network in this algorithm.Firstly,the four-di-mensional weight tensor of the convolutional kernel was transformed into a two-dimensional matrix.The correla-tion matrix was calculated and the singular value decomposition was performed.Secondly,the appropriate number of factors and the factor load matrix were determined by controlling the variance contribution rate.Finally,a more representative convolution kernel was reconstructed.Through the verification on three data sets of Catdog,CI-FAR10 and CIFAR100,the experimental results show that the compression rate of AlexNet and ResNet parame-ters can reach 30.7%-68.2%,and the running time can be reduced by 17.53%-37.21%under ensuring the accuracy of convolutional neural network.Thus,the advantages of the proposed algorithm in the compression rate and operational efficiency are verified.A possible framework was provided for the model compression of convolu-tional neural networks based on factor analysis.
model compressionfactor analysisconvolutional neural networksimage classification
NETL
NSTL
万方数据
维普
