TBN: Convolutional Neural Network with Ternary Inputs and Binary Weights
ECCV2018

本文的思路就是: 对 weight 进行二值量化+ scaling factor α , 对于 网络层的输入 进行 ternary value {−1,0,1} without the scaling factor

3 Ternary-Binary Networks
3.1 Convolution with Matrix Multiplication
use matrix multiplication to implement the convolution layer ⟨I,W,∗⟩
ten2mat 将一组滤波器 weight filters W can be reshaped to a matrix
ten2mat reshape the matrix back to output tensor C


3.2 Binary Weights

3.3 Ternary Inputs
the scaling factors of the binary inputs does not affect the performance of XNOR-Networks
这里我们不采用 scaling factor 了



3.4 Ternary-Binary Dot Product
这样卷积就没有乘法运算了,只有 位运算和 加减


量化梯度求导采用:


provides ∼ 32× memory savings and 40× faster convolutional operations

11

二值网络--TBN: Convolutional Neural Network with Ternary Inputs and Binary Weights相关推荐

  1. 模型量化--TBN:Convolutional Neural Network with Ternary Inputs and Binary Weights

    TBN:Convolutional Neural Network with Ternary Inputs and Binary Weights ECCV_2018 paper TBN 用 高效的 XO ...

  2. 深度学习【6】二值网络(Binarized Neural Networks)学习与理解

    http://blog.csdn.net/linmingan/article/details/51008830 Binarized Neural Networks: Training Neural N ...

  3. 二值网络--Optimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracy

    Optimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracy IEEE Winter Con ...

  4. 二值网络--XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

    XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks ECCV2016 http://allenai ...

  5. 二值网络--Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation

    Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation https: ...

  6. 二值网络训练--Training Competitive Binary Neural Networks from Scratch

    Training Competitive Binary Neural Networks from Scratch https://github.com/hpi-xnor/BMXNet-v2 MXNet ...

  7. 活体检测论文研读二:Learn Convolutional Neural Network for Face Anti-Spoofing

    Learn Convolutional Neural Network for Face Anti-Spoofing 论文简介 ➢指出手工制作的特征例如LBP.LBP-TOP无法捕捉到真假脸之间最具区别 ...

  8. 热图像增强之TEN网络(Thermal Image Enhancement using Convolutional Neural Network)

    热图像增强之TEN网络(Thermal Image Enhancement using Convolutional Neural Network) 摘要 随着商品自主手机的出现,在极端条件下,如夜间. ...

  9. 二值网络训练--A Empirical Study of Binary Neural Networks' Optimisation

    A Empirical Study of Binary Neural Networks' Optimisation ICLR2019 https://github.com/mi-lad/studyin ...

最新文章

  1. 和qc哪个发展更好_一图一表让你秒懂什么叫QC/QA/QM
  2. Android的事件分发实例分析
  3. ICCV 2019 | 从多视角RGB图像生成三维网格模型Pixel2Mesh++
  4. iptables简单应用
  5. 毕业设计-基于Python爬虫的疫情数据可视化系统
  6. Python 异步 IO 、协程、asyncio、async/await、aiohttp
  7. (7)Zynq AXI_GP接口介绍
  8. 疑似一加7 Pro 5G版通过3C认证:配备30W快充头
  9. 电商设计师必备素材|快速组合自己想要的场景和落版文字
  10. 状态服务器与无状态服务器(要点)
  11. 拓端tecdat|用R语言模拟混合制排队随机服务排队系统
  12. .net 开源混淆器 ConfuserEx
  13. java 图片格式判断_Java判断文件是否为图片
  14. java short int 转换_基本类型'short'-Java中的强制转换
  15. 如何写一个NES模拟器(一)
  16. HTTP:SSL证书简介!
  17. 华硕ubuntu安装
  18. line-height绝对值和相对值的区别
  19. ALCNet——红外小目标检测网络论文阅读
  20. 有声阅读狂欢下更需要冷静,荔枝、蜻蜓、喜马拉雅们需要上车

热门文章

  1. Nat. Mach. Intell.| 机器学习显著降低药物组合筛选成本
  2. 【错误归纳】selenium.common.exceptions.WebDriverException: Message: unknown error
  3. 人类dna信息量_多大容量的硬盘才能装下全部人类的DNA?
  4. python tk text scrollbar_tk.Scrollbar控件的使用
  5. python format的功能_python format是什么
  6. 宏基因组数据提交GSA指南
  7. 测序发展史,150年的风雨历程 (第二版)
  8. pandas使用groupby函数、first函数、last函数分别获得每个分组的第一行和最后一行数据(first/last row of each group in dataframe)
  9. R语言效用分析 ( 效能分析、Power analysis)、除了pwr包之外还有其它包、例如、基因研究中的效能分析、MBESS包可用于各种形式的效能分析和最少样本量确定、其他效用分析包的简要介绍
  10. Removed k rows containing missing values