• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Artificial Neural Networks >Local Normalization Based BN Layer Pruning
【24h】

Local Normalization Based BN Layer Pruning

机译：基于局部归一化的BN层修剪

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Compression and acceleration of convolutional neural network (CNN) have raised extensive research interest in the past few years. In this paper, we proposed a novel channel-level pruning method based on gamma (scaling parameters) of Batch Normalization layer to compress and accelerate CNN models. Local gamma normalization and selection was proposed to address the over-pruning issue and introduce local information into channel selection. After that, an ablation based beta (shifting parameters) transfer, and knowledge distillation based fine-tuning were further applied to improve the performance of the pruned model. The experimental results on CIFAR-10, CIFAR-100 and LFW datasets suggest that our approach can achieve much more efficient pruning in terms of reduction of parameters and FLOPs, e.g., 8.64× compression and 3.79× acceleration of VGG were achieved on CIFAR, with slight accuracy loss.
机译：在过去的几年中，卷积神经网络（CNN）的压缩和加速引起了广泛的研究兴趣。在本文中，我们提出了一种基于批处理归一化层的伽玛（缩放参数）的通道级修剪方法，以压缩和加速CNN模型。提出了局部伽玛归一化和选择以解决过度修剪问题并将局部信息引入信道选择。此后，进一步应用了基于消融的beta（移动参数）传递和基于知识蒸馏的微调，以提高修剪模型的性能。在CIFAR-10，CIFAR-100和LFW数据集上的实验结果表明，就参数和FLOP的减少而言，我们的方法可以实现更有效的修剪，例如，在CIFAR上实现了VGG的8.64倍压缩和3.79倍VGG加速，轻微的精度损失。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号