当前位置:网站首页>Cs231n notes (medium) -- applicable to 0 Foundation
Cs231n notes (medium) -- applicable to 0 Foundation
2022-07-05 15:55:00 【Small margin, rush】
Catalog
Pooling layer - Pooling layer - Convergence layer
Convolutional neural networks
Conventional neural networks : The input of neural network is a vector , Then in a series of Cryptic layer Change it in . Each hidden layer is composed of several neurons , Are connected to all neurons in the previous layer . In a hidden layer , Neurons are independent of each other and do not make any connections . The last full connection layer is called “ Output layer ”, In the classification problem , Its output value is regarded as the rating value of different categories .
Convolutional neural network aims at the situation that the input is all images , Adjust the structure more reasonably , Its Neurons are 3 Dimensional arrangement : Width 、 Height and depth , Neurons in the layer will only connect to a small area in the previous layer , Instead of a full connection .
Network structure
Convolution layer
With parameters , There are some learnable filter sets , Each filter is in space ( Width and height ) They are all relatively small , But the depth is the same as the input data .
When it comes to forward propagation , Each filter slides across the width and height of the input data ( More precisely, convolution ), Then calculate the inner product of the whole filter and any part of the input data , Generate a 2 Activation diagram of dimension (activation map), The activation diagram shows the response of the filter at each spatial location .
Feel the field : The neurons in the latter layer are in the sensory space of the neurons in the former layer It can also be defined as the area size mapped by the pixel points on the feature map of each layer in the convolutional neural network in the original image
Hyperparameters :
depth , step ( When sliding the filter , Moving pixel bits ), Zero fill ( use 0 Fill at the edge )
The spatial size of the output data body can be obtained by inputting the size of the data body (W), The size of receptive field of neurons in convolution layer (F), step (S) And the number of zero fills (P) To calculate .
(W-F +2P)/S+1
Parameters of the Shared : Used to control the number of parameters . If a feature is useful , You can share it
demonstration
- The size of the input data body is
- 4 A super parameter : The number of filters K, Space size of filter F, step S. Zero fill quantity P
- Width and height of output dimension :, among W and H by (W-F +2P)/S+1,D2=k
Convolution is essentially a dot product between the filter and the local area of the input data .
1x1 Convolution : The depth of the filter and the input data body is the same , For input yes [32x32x3], that 1x1 Convolution is efficient 3 Dimensional point product
Expansion convolution : There are some element gaps in the filter , The receptive field increases
Pooling layer - Pooling layer - Convergence layer
A convergence layer is periodically inserted between successive convolution layers , Gradually reduce the spatial size of the data body .
- There are two super parameters : The size F, step S, The size calculation of output data is the same as that of convolution layer
- Zero padding is rarely used in the convergence layer
Maximum convergence
Fully connected layer
In the full connection layer , Neurons are fully connected to all activation data in the previous layer , Refer to the conventional neural network
The only difference between the full connection layer and the convolution layer is that the neurons in the convolution layer are only connected to a local area in the input data , And the neurons in the convolution column share parameters . The full connection layer can be transformed into a convolution layer
The arrangement of layers
INPUT -> [[CONV -> RELU]*N -> POOL?]*M -> [FC -> RELU]*K -> FC
The combination of several small filter convolution layers is better than one large filter convolution layer
A structure in which multiple convolution layers alternate with nonlinear activation layers , It can extract deeper and better features than the structure of a single convolution layer . The disadvantage is , In back propagation , The convolution layer in the middle may lead to more memory consumption .
Q&A:
- Why use zero padding ? Using zero padding can keep the output data of the convolution layer and the input data unchanged in the spatial dimension in addition to the above mentioned
- Why use in convolution layer 1 Step size of ? Smaller step size is better , In steps of 1 It can let the spatial dimension downsampling be all in the charge of the convergence layer , The convolution layer is only responsible for transforming the depth of the input data volume .
common CNN
LeNet: The first convolutional neural network
AlexNet:ImageNet2012 champion , Network structure and LeNet similar , Use the convolution layer to obtain features
ZF Net:2013 Champion can modify the super parameters in the structure to realize AlexNet Improvement of , Specifically, the size of the intermediate convolution layer is increased , Make the step size and filter size of the first layer smaller
GoogLeNet: Significantly reduce the number of parameters in the network ,Inception.
VGGNet:2014 runner-up , It shows that the depth of the network is the key part of the excellent performance of the algorithm . Consume more computing resources , And more parameters are used , Cause more memory usage
ResNet:2015 champion , Used a lot Batch normalization
边栏推荐
- CODING DevSecOps 助力金融企业跑出数字加速度
- Write a go program with vscode in one article
- ionic cordova项目修改插件
- 2.3 learning content
- Basic JSON operations of MySQL 5.7
- Hongmeng system -- Analysis from the perspective of business
- First PR notes
- 我们为什么要学习数学建模?
- Maximum common subsequence
- Arduino controls a tiny hexapod 3D printing robot
猜你喜欢
21. [STM32] I don't understand the I2C protocol. Dig deep into the sequence diagram to help you write the underlying driver
Analytic hierarchy process of mathematical modeling (including Matlab code)
swiper. JS to achieve barrage effect
Fundamentals of data communication - Principles of IP routing
Value series solution report
JS knowledge points-01
MySQL overview
Codasip为RISC-V处理器系列增加Veridify安全启动功能
Appium automation test foundation - appium basic operation API (II)
I include of spring and Autumn
随机推荐
lv_font_conv离线转换
I include of spring and Autumn
19.[STM32]HC_SR04超声波测距_定时器方式(OLED显示)
JS topic - console log()
Advanced level of static and extern
DataArts Studio数据架构——数据标准介绍
Clock switching with multiple relationship
Array sorting num ranking merge in ascending order
项目中批量update
MySQL表字段调整
Why should we learn mathematical modeling?
Maximum common subsequence
Appium automation test foundation - appium basic operation API (I)
把 ”中台“ 的思想迁移到代码中去
记录一下树莓派搭建环境中遇到的坑。。。
Anti shake and throttling
16. [stm32] starting from the principle, I will show you the DS18B20 temperature sensor - four digit digital tube displays the temperature
sql中查询最近一条记录
20. [stm32] realize the function of intelligent garbage can by using ultrasonic module and steering gear
Vulnhub-Moneybox