中圖分類號： TN911.73；TP391
文獻標識碼： A
DOI：10.16157/j.issn.0258-7998.200263
中文引用格式： 肖國麟，楊春玲，陳宇. 基于權值交互思想的卷積神經網絡量化算法[J].電子技術應用，2020，46(10)：39-41.
英文引用格式： Xiao Guolin，Yang Chunling，Chen Yu. Convolutional neural network quantization algorithm based on weight interaction ideas[J]. Application of Electronic Technique，2020，46(10)：39-41.

Convolutional neural network quantization algorithm based on weight interaction ideas

Abstract： Traditional convolutional neural network quantization algorithms widely use symmetric uniform quantization operations to quantize models′ weights, without taking into account the correlation between the quantization of adjacent weights, that is, the quantization noise generated by the quantization operation of the previous weight can be made up after adjusting the quantitative direction of the next weights. Aiming at the above problems, a ternary convolutional neural network quantization algorithm based on the idea of weight interaction is proposed, the model compression ratio is 16 times. On the ImageNet dataset, the model prediction accuracy of ternarized AlexNet and ResNet-18 network only decrease less than 3%. This method achieves a high model compression ratio, has higher accuracy, and can be used to transplant convolutional neural networks to mobile platforms with limited computing resources.

Key words : ternary quantization；convolutional neural network；weight interaction；model compression