当前位置:网站首页>Image super resolution using deep revolutionary networks (srcnn) interpretation and Implementation
Image super resolution using deep revolutionary networks (srcnn) interpretation and Implementation
2022-07-06 03:27:00 【leon. shadow】
Image super-resolution using deep convolutional networks(SRCNN)
One 、 summary
Network structure
SRCNN The network structure is relatively simple , It is a three-layer convolution network , Activation function selection Relu.
- The first convolution : Realize the extraction of image features .( The number of convolution kernels is 64, The size is 9)
- The second convolution : Nonlinear mapping of features extracted from the first layer convolution .( The number of convolution kernels is 32, The size is 1[ original text ])
- The third convolution : Reconstruct the mapped features , Generate high resolution images ..( The number of convolution kernels is 1, The size is 5)
The evaluation index
PSNR( Peak signal to noise ratio ):PSNR The bigger the value is. , The better the reconstruction .
import numpy
import math
def psnr(img1, img2):
mse = numpy.mean( (img1 - img2) ** 2 )
if mse == 0:
return 100
PIXEL_MAX = 255.0
return 20 * math.log10(PIXEL_MAX / math.sqrt(mse))
Why only train YCbCr Of Y passageway ?
The image is converted into YCbCr Color space , Although the network only uses brightness channels (Y). then , The output of the network merges interpolated CbCr passageway , Output the final color image . We chose this step because we are not interested in color changes ( Stored in CbCr Information in the channel ) But only its brightness (Y passageway ); The fundamental reason is that compared with color difference , Human vision is more sensitive to brightness changes .
Loss function
The loss function is the mean square error (MSE)
1×1 The function of convolution ?
- Realize the change of dimension ( Increase or decrease dimension )
- Realize cross channel interaction and information integration
- Reduce computation
- It can achieve the effect equivalent to the full connection layer
Two 、 Code
model.py
from torch import nn
class SRCNN(nn.Module):
def __init__(self, num_channels=1):
super(SRCNN, self).__init__()
self.conv1 = nn.Conv2d(num_channels, 64, kernel_size=9, padding=9 // 2)
self.conv2 = nn.Conv2d(64, 32, kernel_size=5, padding=5 // 2)
self.conv3 = nn.Conv2d(32, num_channels, kernel_size=5, padding=5 // 2)
self.relu = nn.ReLU(inplace=True)
def forward(self, x):
x = self.relu(self.conv1(x))
x = self.relu(self.conv2(x))
x = self.conv3(x)
return x
In order to avoid boundary effect, the original text did not add padding, Instead, when calculating the loss value, only the pixels in the central area are calculated . The original text is not added padding, The size of the original drawing has passed srcnn Three-layer convolution of , The resolution will become smaller .
3、 ... and 、 experiment
Compare the convolution kernel size (filter size)、 Number of convolution nuclei (filter numbers) Experiment on the effect of restoration
Conclusion : The more convolution kernels , That is, the higher the dimension of the eigenvector , The better the experimental effect , But it will affect the speed of the algorithm , Therefore, comprehensive consideration is needed ; The larger the convolution kernel size of the other three convolution layers , The experimental effect will be slightly better , It will also affect the speed of the algorithm .
Compare the network layers (layer numbers) Experiment on the effect of restoration
Conclusion : Not the deeper the network , The better the result. , The opposite is true . The author also gives an explanation : because SRCNN There is no pooling layer and full connectivity layer , As a result, the network is very sensitive to initial parameters and learning rate , The result is that it is very difficult to converge during network training , Even if it converges, it may stop at the bad local minimum (bad local minimum) It's about , And even if you train enough time , Learned filter The dispersion of parameters is not good enough .
Experiment on the effect of channel on restoration
Conclusion :RGB Channel joint training is the best ;YCbCr Under the channel ,Cb、Cr Channels are basically not helpful for performance improvement , Based on Y The training effect of channel is better .
Four 、 Conclusion
SRCNN Propose a lightweight end-to-end network SRCNN To solve the super score problem , Indeed, at that time, it achieved better performance than traditional methods 、 Faster effect , In addition, the author will be based on SC( Sparse coding ) The super division method of is understood as a form of convolutional neural network , Are all highlights worth reading .
5、 ... and 、 Address of thesis
Address of thesis :https://arxiv.org/abs/1501.00092
边栏推荐
- 【SLAM】ORB-SLAM3解析——跟踪Track()(3)
- 2.2 fonctionnement stm32 GPIO
- BUUCTF刷题笔记——[极客大挑战 2019]EasySQL 1
- [risc-v] external interrupt
- Princeton University, Peking University & UIUC | offline reinforcement learning with realizability and single strategy concentration
- Pytorch load data
- Python implementation of maddpg - (1) openai maddpg environment configuration
- 【RISC-V】外部中断
- . Net 6 and Net core learning notes: Important issues of net core
- MADDPG的pythorch实现——(1)OpenAI MADDPG环境配置
猜你喜欢
蓝色样式商城网站页脚代码
Résumé des méthodes de reconnaissance des caractères ocr
Mysql database operation
施努卡:3d视觉检测应用行业 机器视觉3d检测
C language judgment, ternary operation and switch statement usage
Cubemx 移植正点原子LCD显示例程
Python implementation of maddpg - (1) openai maddpg environment configuration
Pointer written test questions ~ approaching Dachang
Precautions for single chip microcomputer anti reverse connection circuit
【概念】Web 基础概念认知
随机推荐
Pointer written test questions ~ approaching Dachang
Mysql database operation
【Rust 笔记】18-宏
【RISC-V】外部中断
Leetcode problem solving -- 173 Binary search tree iterator
SAP ALV单元格级别设置颜色
C language judgment, ternary operation and switch statement usage
Leetcode problem solving -- 99 Restore binary search tree
Exness foreign exchange: the governor of the Bank of Canada said that the interest rate hike would be more moderate, and the United States and Canada fell slightly to maintain range volatility
three. JS page background animation liquid JS special effect
Idea push rejected solution
如何做好功能测试
The solution of permission denied (750 permissions should be used with caution)
IPv6 comprehensive experiment
Daily question brushing plan-2-13 fingertip life
SWC介绍
Leetcode problem solving -- 108 Convert an ordered array into a binary search tree
Esbuild & SWC: a new generation of construction tools
电机控制反Park变换和反Clarke变换公式推导
Handwriting database client