修剪
特征(语言学)
计算机科学
计算
人工智能
频道(广播)
人工神经网络
图形
模式识别(心理学)
信息丢失
噪音(视频)
作者
Yang Liu,Hu Jianqiang,Xiaobao Zhou,Jiaxin Wu
摘要
Neural networks have the problems of excessive number of parameters and computation due to data noise and redundant filters, which limits the application of neural networks. A feature map pruning method using channel attention (FPC) is proposed to address the problem of excessive accuracy loss of existing pruning methods. Experiments show that the feature graph pruning method using channel attention has better pruning effect with the same accuracy loss.
科研通智能强力驱动
Strongly Powered by AbleSci AI