BNPrune: A Channel Level Pruning Method for Deep Neural Network used of Batch Normalization

2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)(2021)

引用 1|浏览3
暂无评分
摘要
Deep Neural Networks have become surprisingly popular in target detection due to its fast detection speed and high accuracy in recent years. However, it is difficult to apply deep neural network in edge equipment because of the problems of large amount of computation and complex model. In this paper, a channel level pruning method of neural network is improved, named as BNPrune, where BN indicates...
更多
查看译文
关键词
Deep learning,Training,Mechatronics,Computational modeling,Image edge detection,Conferences,Neural networks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要