其他分享
首页 > 其他分享> > 2 AI论文笔记--Rethinking the Inception Architecture for Computer Vision

2 AI论文笔记--Rethinking the Inception Architecture for Computer Vision

作者:互联网

2 AI论文笔记–Rethinking the Inception Architecture for Computer Vision

原文地址:https://arxiv.org/abs/1512.00567

还不错的笔记:

1、InceptionV1-V4演进:https://blog.csdn.net/qq_30815237/article/details/89046890

2、别人的笔记https://blog.csdn.net/qq_39109729/article/details/109117613
论文课程学习来自—知识星球—同济子豪兄


该文章主要了解:


以下是论文的部分讲解

文章结构:

Abstract

1 Introduction (前言)

2 General Design Principles (通用设计原则)

3 Factorizing Convolutions with Large Filter Size (分解大卷积核的卷积)

​ 3.1 Factorization into smaller convolutions (将5x5卷积分解为两个3x3卷积)

​ 3.2 Spatial Factorization into Asymmetric Convolutions

4 Utility of Auxiliary Classifiers (辅助分类器的作用)

5 Efficient Grid Size Reduction (高效下采样技巧)

6 Inception-v2

7 Model Regularization via Label Smoothing

8 Training Methodology

9 Performance on Lower Resolution Input

10 Experimental Results and Comparisons

11 Conclusions


Abstract

1 Introduction

2 General Design Principles!!!!!!

3 Factorizing Convolutions with Large Filter Size (分解大卷积核的卷积)

4 Efficient Grid Size Reduction(高效的下采样技巧)

标签:Rethinking,Inception,AI,feature,网络,--,map,特征,卷积
来源: https://blog.csdn.net/weixin_44994302/article/details/117486142