cs231n-notes-Lecture-9：AlexNet/VGGNet/GoogleNet/ResNet_stanford vgg but deeper, more non-linearities and -优快云博客

本文链接：https://blog.youkuaiyun.com/ravi_jay/article/details/82758151

本文介绍了几种主流的卷积神经网络架构，包括AlexNet、VGGNet、GoogleNet及ResNet，并探讨了小卷积核的优势，更深网络的设计理念及残差网络如何解决深层网络优化难题。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Lecture 9 CNN Architectures

AlexNet

在这里插入图片描述

VGGNet

Small filters
Why?
- Stack of three 3x3 conv (stride 1) layers has same effective receptive field as one 7x7 conv layer
- But deeper, more non-linearities
- And fewer parameters: $3 * (3^2C^2)$ vs. $7^2C^2$ for C channels per layer
Deeper networks

在这里插入图片描述

GoogleNet

Deeper networks : 22layers.
efficient computation : Efficient “Inception” module.
No Fc layers.
Only 5 million parameters, 12x less than AlexNet. Most parameters in AlexNet or VGGNet are in fc layers.
Computational complexity.
Computational complexity solution : use “bottleneck” (1*1 convolutions, less filters) to reduce feature depth.

在这里插入图片描述

ResNet

Deeper Models may be harder to optimize although they have the ability to achiveve the same peformance theoretically because the additional layers can learn identify mapping.
But it’s ideal. Here is the solution of ResNet.

Residual: learn what should be added to or subtracted from the original input X. Intuitively, it’s easier to learn the bias than a direct mapping. The bias can be only a small change or zeros.

在这里插入图片描述

Training ResNet in practice:

Batch Normalization after every CONV layer
Xavier/2 initialization from He et al.
SGD + Momentum (0.9)
Learning rate: 0.1, divided by 10 when validation error plateaus
Mini-batch size 256
Weight decay of 1e-5
No dropout used

Experimental Results

Able to train very deep networks without degrading (152 layers on ImageNet, 1202 on Cifar)
Deeper networks now achieve lowing training error as expected
Swept 1st place in all ILSVRC and COCO 2015 competitions

在这里插入图片描述