rethinking the inception architecture for computer vision
来源:互联网 发布:周杰伦侯佩岑 知乎 编辑:程序博客网 时间:2024/05/16 07:00
Google在GoogleNet中提出了inception概念之后,又提出了inception_2,inception_3,都在这篇论文中谈及。
文章地址为http://arxiv.org/pdf/1512.00567v3.pdf
四个通用的设计原则(General Design Principles):
1. Avoid representational bottlenecks,especially early in the network。
2.Higher dimensional representations are easier to process locally within a network。
3. Spatial aggregation can be done over lower dimensional embeddings without much or any loss in representational power。
4.Balance the width and depth of the network 。
Factorizing Convolutions with Large Filter Szie(对大尺寸的过滤器进行分解)这样可以减少参数个数和计算量,训练速度更快。
1.Factorization into smaller convolutions
5*5的卷积是3*3的卷积的25/9=2.78倍的时间开销。
将原本5*5的卷积用一个多层网络(两层的3*3的卷积)来替代,参数更少,同样的输入
2.Spatial factorization into asymmetric convolutions
将一个3*3的卷积用两层网络来替代,3*1加1*3的两层架构,计算量减小33%,如果用两层2*2卷积来替代,计算量减小11%。
所以,后面就用1*n和n*1来替代n*n的卷积,实验中发现,这种分解方法在网络的前面几层效果不好,但在中间时效果非常好(如果是m*m的特征图谱,m的范围在12到20之间),在这里是在7*7的卷积上用1*7加7*1替代效果最好。
Utility of Auxiliary Classifiers(辅助分类器的利用)
这个在v1版本里就有用到,在inception_4a/output和inception_4e/output后池化卷积全连接后做loss和top_1,top_5的计算。
Efficient Grid Size Reduction
- rethinking the inception architecture for computer vision
- Rethinking the Inception Architecture for Computer Vision
- Inception-v3:"Rethinking the Inception Architecture for Computer Vision"
- Inception V3(Rethinking the Inception Architecture for Computer Vision)
- Rethinking the Inception Architecture for Computer Vision 笔记
- 论文笔记 | Rethinking the Inception Architecture for Computer Vision
- READING NOTE: Rethinking the Inception Architecture for Computer Vision
- 《Rethinking the Inception Architecture for Computer Vision》笔记
- 网络模型 Inception V2/V3-Rethinking the Inception Architecture for Computer Vision
- googLeNet--Inception四部曲三Rethinking the Inception Architecture for Computer Vision
- [深度学习论文笔记][Image Classification] Rethinking the Inception Architecture for Computer Vision
- Inception系列2_Rethinking the Inception Architecture for Computer Vision
- Flexible Models for Computer Vision
- Datasets for Computer Vision Research
- ISP Pipeline for Computer Vision
- The Middlebury Computer Vision Pages
- Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art
- Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art
- Hadoop - Hadoop开发环境搭建
- Activity四种启动模式
- 关于LRU算法
- sql的join图解
- Cookie和Session详解
- rethinking the inception architecture for computer vision
- restoredefaultpath matlab
- hdu 1358 Period(求循环节)
- python自学总结
- 关于android5.0一些主题颜色的介绍
- 设计模式之观察者模式
- 字符串匹配
- Android MeasuerSpec的由来及使用
- 商业级项目登录模块源码分析