cs231n lecture9 CNN Architectures

最新推荐文章于 2022-11-25 21:37:40 发布

feitianlzk

最新推荐文章于 2022-11-25 21:37:40 发布

阅读量255

点赞数

分类专栏： AI

本文链接：https://blog.csdn.net/feitianlzk/article/details/79626383

版权

本文介绍了CNN（卷积神经网络）的几种经典架构，包括AlexNet、VGG、GoogleNet（含Inception模块）和ResNet。AlexNet引入了局部响应归一化，VGG网络加深了网络层数并使用小尺寸滤波器。GoogleNet的Inception模块展示了网络内网络的设计，而ResNet通过残差学习解决了深网优化问题。此外，文章还提及了一些通用技巧，如瓶颈层和学习率调整策略。

摘要由CSDN通过智能技术生成

AlexNet

CONV - MAXPOOL - NORM(not common)
CONV - MAXPOOL - NORM
CONV - CONV - CONV - MAXPOOL
FC - FC - FC
local response normalization

VGG

deeper (16-19layers)
small filter (3x3 CONV stride 1, pad 1)
2 x 2 MAX POOL, stride 2
stack of 3x3 has same effective receptive field as 7x7(three stacks)
- more nonlinearity
- fewer parameters
2nd in classication, 1st in localization
VGG16, VGG19
FC7 feature(4096) generailize well to other tasks
detection: multiple instance
localization: one instance

GoogleNet

22 layers
No fc layers
“Inception” module
- a good local network topology(network within a network)
stack inception modules on top of each other
In: conv pool conv pool + inception x
Auxiliary classifcation outputs to inject additioanl gradient at lower layers (AvgPool-1x1Conv-FC-FC-Softmax)