基于滤波器裁剪的卷积神经网络加速算法

针对卷积神经网络（CNN）模型的压缩和加速问题，提出基于滤波器裁剪的新型卷积神经网络模型加速算法. 通过计算卷积层中滤波器的标准差值衡量该滤波器的重要程度，裁剪对神经网络准确率影响较小的滤波器及对应的特征图，可以有效地降低计算成本. 与裁剪权重不同，该算法不会导致网络稀疏连接，不需要应用特殊的稀疏矩阵计算库. 基于CIFAR-10数据集的实验结果表明，该滤波器裁剪算法能够对VGG-16和ResNet-110模型加速30%以上，通过微调继承的预训练参数可以使结果接近或达到原始模型的精度.

Convolutional neural network acceleration algorithm based on filters pruning

A new model acceleration algorithm of convolutional neural network (CNN) was proposed based on filters pruning in order to promote the compression and acceleration of the CNN model. The computational cost could be effectively reduced by calculating the standard deviation of filters in the convolutional layer to measure its importance and pruning filters with less influence on the accuracy of the neural network and its corresponding feature map. The algorithm did not cause the network to be sparsely connected unlike the method of pruning weight value, so there was no need of the support of special sparse convolution libraries. The experimental results based on the CIFAR-10 dataset show that the filters pruning algorithm can accelerate the VGG-16 and ResNet-110 models by more than 30%. Results can be close to or reach the accuracy of the original model by fine-tuning the inherited pre-training parameters.