基于滤波器裁剪的卷积神经网络加速算法

李浩,赵文杰,韩波

Convolutional neural network acceleration algorithm based on filters pruning

Hao LI,Wen-jie ZHAO,Bo HAN

表 3 不同裁剪方法的准确率对比

Tab.3 Accuracy comparison of different pruning methods

% 裁剪算法 微调 随机初值训练 多次迭代训练 m=20 m=40 m=60 m=20 m=40 m=60 m=20 m=40 m=60 标准差 72.37 64.85 53.36 72.41 64.93 53.31 72.65 65.16 54.45 APoZ 71.14 62.82 52.63 71.11 63.12 52.67 71.39 63.31 53.44 L1范数 72.28 64.77 53.35 72.33 64.76 53.39 72.47 64.81 53.56 Random 71.45 63.34 51.92 71.49 63.40 52.01 71.67 63.82 52.76 Mean Activation 71.62 63.42 51.39 71.61 63.59 51.41 71.83 63.71 52.13