摘要
随着深度学习网络的不断发展,卷积神经网络在图像识别与处理领域的正确率已达到甚至超越人类水平。但是,越来越复杂的网络结构导致庞大的计算模型体积和计算量,不利于模型的移植利用。基于此,分别介绍了网络压缩加速的典型方法并进行比较,在保证算法准确率损失最少的前提下,尽可能使算法具有可移植性,充分体现卷积神经网络算法的应用价值。
With the continuous development of deep learning network,the accuracy of convolutional neural network in image recognition and processing has reached or even surpassed human level.However,more and more complex network structure leads to huge computing model volume and computation,which is not conducive to the transplantation and utilization of the model.Based on this,the typical methods of network compression and acceleration are introduced and compared.On the premise of guaranteeing the least loss of accuracy,the algorithm can be transplanted as far as possible,which fully reflects the application value of convolutional neural network algorithm.
作者
李思奇
Li Siqi(Beijing Wuzi University,Beijing 101149,China)
出处
《信息与电脑》
2019年第11期21-23,共3页
Information & Computer
关键词
卷积神经网络
网络压缩
网络加速
模型移植
convolutional neural network
network compression
network acceleration
model transplantation
