基于opencv的gpu与cpu对比程序，代码来自opencv的文档中
原文链接：
代码中有错误，关于GpuMat OpenCV代码中没有对其进行操作符运算的重载，所有编译的时候有错误。对于GpuMat的运算只能调用相关函数才行，后面我嫌麻烦就没有重写
<span style="font-size:18px;">// PSNR.cpp : 定义控制台应用程序的入口点。
// #include "stdafx.h" #include <iostream> // Console I/O
#include <sstream> // String to number conversion #include <opencv2/core/core.hpp> // Basic OpenCV structures
#include <opencv2/imgproc/imgproc.hpp>// Image processing methods for the CPU
#include <opencv2/highgui/highgui.hpp>// Read images
#include <opencv2/gpu/gpu.hpp> // GPU structures and methods using namespace std;
using namespace cv; double getPSNR(const Mat& I1, const Mat& I2); // CPU versions
Scalar getMSSIM( const Mat& I1, const Mat& I2); double getPSNR_GPU(const Mat& I1, const Mat& I2); // Basic GPU versions
Scalar getMSSIM_GPU( const Mat& I1, const Mat& I2); struct BufferPSNR // Optimized GPU versions
{ // Data allocations are very expensive on GPU. Use a buffer to solve: allocate once reuse later.
gpu::GpuMat gI1, gI2, gs, t1,t2; gpu::GpuMat buf;
};
double getPSNR_GPU_optimized(const Mat& I1, const Mat& I2, BufferPSNR& b); struct BufferMSSIM // Optimized GPU versions
{ // Data allocations are very expensive on GPU. Use a buffer to solve: allocate once reuse later.
gpu::GpuMat gI1, gI2, gs, t1,t2; gpu::GpuMat I1_2, I2_2, I1_I2;
vector<gpu::GpuMat> vI1, vI2; gpu::GpuMat mu1, mu2;
gpu::GpuMat mu1_2, mu2_2, mu1_mu2; gpu::GpuMat sigma1_2, sigma2_2, sigma12;
gpu::GpuMat t3; gpu::GpuMat ssim_map; gpu::GpuMat buf;
};
Scalar getMSSIM_GPU_optimized( const Mat& i1, const Mat& i2, BufferMSSIM& b); void help()
{
cout
<< "\n--------------------------------------------------------------------------" << endl
<< "This program shows how to port your CPU code to GPU or write that from scratch." << endl
<< "You can see the performance improvement for the similarity check methods (PSNR and SSIM)." << endl
<< "Usage:" << endl
<< "./gpu-basics-similarity referenceImage comparedImage numberOfTimesToRunTest(like 10)." << endl
<< "--------------------------------------------------------------------------" << endl
<< endl;
} int main(int argc, char *argv[])
{
help();
Mat I1 = imread("swan1.jpg",1); // Read the two images
Mat I2 = imread("swan2.jpg",1); if (!I1.data || !I2.data) // Check for success
{
cout << "Couldn't read the image";
return 0;
} BufferPSNR bufferPSNR;
BufferMSSIM bufferMSSIM; int TIMES;
stringstream sstr("500");
sstr >> TIMES;
double time, result; //------------------------------- PSNR CPU ----------------------------------------------------
time = (double)getTickCount(); for (int i = 0; i < TIMES; ++i)
result = getPSNR(I1,I2); time = 1000*((double)getTickCount() - time)/getTickFrequency();
time /= TIMES; cout << "Time of PSNR CPU (averaged for " << TIMES << " runs): " << time << " milliseconds."
<< " With result of: " << result << endl; //------------------------------- PSNR GPU ----------------------------------------------------
time = (double)getTickCount(); for (int i = 0; i < TIMES; ++i)
result = getPSNR_GPU(I1,I2); time = 1000*((double)getTickCount() - time)/getTickFrequency();
time /= TIMES; cout << "Time of PSNR GPU (averaged for " << TIMES << " runs): " << time << " milliseconds."
<< " With result of: " << result << endl;
/*
//------------------------------- PSNR GPU Optimized--------------------------------------------
time = (double)getTickCount(); // Initial call
result = getPSNR_GPU_optimized(I1, I2, bufferPSNR);
time = 1000*((double)getTickCount() - time)/getTickFrequency();
cout << "Initial call GPU optimized: " << time <<" milliseconds."
<< " With result of: " << result << endl; time = (double)getTickCount();
for (int i = 0; i < TIMES; ++i)
result = getPSNR_GPU_optimized(I1, I2, bufferPSNR); time = 1000*((double)getTickCount() - time)/getTickFrequency();
time /= TIMES; cout << "Time of PSNR GPU OPTIMIZED ( / " << TIMES << " runs): " << time
<< " milliseconds." << " With result of: " << result << endl << endl; //------------------------------- SSIM CPU -----------------------------------------------------
Scalar x;
time = (double)getTickCount(); for (int i = 0; i < TIMES; ++i)
x = getMSSIM(I1,I2); time = 1000*((double)getTickCount() - time)/getTickFrequency();
time /= TIMES; cout << "Time of MSSIM CPU (averaged for " << TIMES << " runs): " << time << " milliseconds."
<< " With result of B" << x.val[0] << " G" << x.val[1] << " R" << x.val[2] << endl; //------------------------------- SSIM GPU -----------------------------------------------------
time = (double)getTickCount(); for (int i = 0; i < TIMES; ++i)
x = getMSSIM_GPU(I1,I2); time = 1000*((double)getTickCount() - time)/getTickFrequency();
time /= TIMES; cout << "Time of MSSIM GPU (averaged for " << TIMES << " runs): " << time << " milliseconds."
<< " With result of B" << x.val[0] << " G" << x.val[1] << " R" << x.val[2] << endl; //------------------------------- SSIM GPU Optimized--------------------------------------------
time = (double)getTickCount();
x = getMSSIM_GPU_optimized(I1,I2, bufferMSSIM);
time = 1000*((double)getTickCount() - time)/getTickFrequency();
cout << "Time of MSSIM GPU Initial Call " << time << " milliseconds."
<< " With result of B" << x.val[0] << " G" << x.val[1] << " R" << x.val[2] << endl; time = (double)getTickCount(); for (int i = 0; i < TIMES; ++i)
x = getMSSIM_GPU_optimized(I1,I2, bufferMSSIM); time = 1000*((double)getTickCount() - time)/getTickFrequency();
time /= TIMES; cout << "Time of MSSIM GPU OPTIMIZED ( / " << TIMES << " runs): " << time << " milliseconds."
<< " With result of B" << x.val[0] << " G" << x.val[1] << " R" << x.val[2] << endl << endl;
return 0;
*/
getchar();
} double getPSNR(const Mat& I1, const Mat& I2)
{
Mat s1;
absdiff(I1, I2, s1); // |I1 - I2|
s1.convertTo(s1, CV_32F); // cannot make a square on 8 bits
s1 = s1.mul(s1); // |I1 - I2|^2 Scalar s = sum(s1); // sum elements per channel double sse = s.val[0] + s.val[1] + s.val[2]; // sum channels if( sse <= 1e-10) // for small values return zero
return 0;
else
{
double mse =sse /(double)(I1.channels() * I1.total());
double psnr = 10.0*log10((255*255)/mse);
return psnr;
}
} double getPSNR_GPU_optimized(const Mat& I1, const Mat& I2, BufferPSNR& b)
{
b.gI1.upload(I1);
b.gI2.upload(I2); b.gI1.convertTo(b.t1, CV_32F);
b.gI2.convertTo(b.t2, CV_32F); gpu::absdiff(b.t1.reshape(1), b.t2.reshape(1), b.gs);
gpu::multiply(b.gs, b.gs, b.gs); double sse = gpu::sum(b.gs, b.buf)[0]; if( sse <= 1e-10) // for small values return zero
return 0;
else
{
double mse = sse /(double)(I1.channels() * I1.total());
double psnr = 10.0*log10((255*255)/mse);
return psnr;
}
} double getPSNR_GPU(const Mat& I1, const Mat& I2)
{
gpu::GpuMat gI1, gI2, gs, t1,t2; gI1.upload(I1);
gI2.upload(I2); gI1.convertTo(t1, CV_32F);
gI2.convertTo(t2, CV_32F); gpu::absdiff(t1.reshape(1), t2.reshape(1), gs);
gpu::multiply(gs, gs, gs); Scalar s = gpu::sum(gs);
double sse = s.val[0] + s.val[1] + s.val[2]; if( sse <= 1e-10) // for small values return zero
return 0;
else
{
double mse =sse /(double)(gI1.channels() * I1.total());
double psnr = 10.0*log10((255*255)/mse);
return psnr;
}
} Scalar getMSSIM( const Mat& i1, const Mat& i2)
{
const double C1 = 6.5025, C2 = 58.5225;
/***************************** INITS **********************************/
int d = CV_32F; Mat I1, I2;
i1.convertTo(I1, d); // cannot calculate on one byte large values
i2.convertTo(I2, d); Mat I2_2 = I2.mul(I2); // I2^2
Mat I1_2 = I1.mul(I1); // I1^2
Mat I1_I2 = I1.mul(I2); // I1 * I2 /*************************** END INITS **********************************/ Mat mu1, mu2; // PRELIMINARY COMPUTING
GaussianBlur(I1, mu1, Size(11, 11), 1.5);
GaussianBlur(I2, mu2, Size(11, 11), 1.5); Mat mu1_2 = mu1.mul(mu1);
Mat mu2_2 = mu2.mul(mu2);
Mat mu1_mu2 = mu1.mul(mu2); Mat sigma1_2, sigma2_2, sigma12; GaussianBlur(I1_2, sigma1_2, Size(11, 11), 1.5);
sigma1_2 -= mu1_2; GaussianBlur(I2_2, sigma2_2, Size(11, 11), 1.5);
sigma2_2 -= mu2_2; GaussianBlur(I1_I2, sigma12, Size(11, 11), 1.5);
sigma12 -= mu1_mu2; ///////////////////////////////// FORMULA ////////////////////////////////
Mat t1, t2, t3; t1 = 2 * mu1_mu2 + C1;
t2 = 2 * sigma12 + C2;
t3 = t1.mul(t2); // t3 = ((2*mu1_mu2 + C1).*(2*sigma12 + C2)) t1 = mu1_2 + mu2_2 + C1;
t2 = sigma1_2 + sigma2_2 + C2;
t1 = t1.mul(t2); // t1 =((mu1_2 + mu2_2 + C1).*(sigma1_2 + sigma2_2 + C2)) Mat ssim_map;
divide(t3, t1, ssim_map); // ssim_map = t3./t1; Scalar mssim = mean( ssim_map ); // mssim = average of ssim map
return mssim;
} Scalar getMSSIM_GPU( const Mat& i1, const Mat& i2)
{
const float C1 = 6.5025f, C2 = 58.5225f;
/***************************** INITS **********************************/
gpu::GpuMat gI1, gI2, gs1, t1,t2; gI1.upload(i1);
gI2.upload(i2); gI1.convertTo(t1, CV_MAKE_TYPE(CV_32F, gI1.channels()));
gI2.convertTo(t2, CV_MAKE_TYPE(CV_32F, gI2.channels())); vector<gpu::GpuMat> vI1, vI2;
gpu::split(t1, vI1);
gpu::split(t2, vI2);
Scalar mssim; for( int i = 0; i < gI1.channels(); ++i )
{
gpu::GpuMat I2_2, I1_2, I1_I2; gpu::multiply(vI2[i], vI2[i], I2_2); // I2^2
gpu::multiply(vI1[i], vI1[i], I1_2); // I1^2
gpu::multiply(vI1[i], vI2[i], I1_I2); // I1 * I2 /*************************** END INITS **********************************/
gpu::GpuMat mu1, mu2; // PRELIMINARY COMPUTING
gpu::GaussianBlur(vI1[i], mu1, Size(11, 11), 1.5);
gpu::GaussianBlur(vI2[i], mu2, Size(11, 11), 1.5); gpu::GpuMat mu1_2, mu2_2, mu1_mu2;
gpu::multiply(mu1, mu1, mu1_2);
gpu::multiply(mu2, mu2, mu2_2);
gpu::multiply(mu1, mu2, mu1_mu2); gpu::GpuMat sigma1_2, sigma2_2, sigma12; gpu::GaussianBlur(I1_2, sigma1_2, Size(11, 11), 1.5);
//sigma1_2 = sigma1_2 - mu1_2;
gpu::subtract(sigma1_2,mu1_2,sigma1_2); gpu::GaussianBlur(I2_2, sigma2_2, Size(11, 11), 1.5);
//sigma2_2 = sigma2_2 - mu2_2; gpu::GaussianBlur(I1_I2, sigma12, Size(11, 11), 1.5);
(Mat)sigma12 =(Mat)sigma12 - (Mat)mu1_mu2;
//sigma12 = sigma12 - mu1_mu2 ///////////////////////////////// FORMULA ////////////////////////////////
gpu::GpuMat t1, t2, t3; // t1 = 2 * mu1_mu2 + C1;
// t2 = 2 * sigma12 + C2;
// gpu::multiply(t1, t2, t3); // t3 = ((2*mu1_mu2 + C1).*(2*sigma12 + C2))
//
// t1 = mu1_2 + mu2_2 + C1;
// t2 = sigma1_2 + sigma2_2 + C2;
// gpu::multiply(t1, t2, t1); // t1 =((mu1_2 + mu2_2 + C1).*(sigma1_2 + sigma2_2 + C2)) gpu::GpuMat ssim_map;
gpu::divide(t3, t1, ssim_map); // ssim_map = t3./t1; Scalar s = gpu::sum(ssim_map);
mssim.val[i] = s.val[0] / (ssim_map.rows * ssim_map.cols); }
return mssim;
} Scalar getMSSIM_GPU_optimized( const Mat& i1, const Mat& i2, BufferMSSIM& b)
{
int cn = i1.channels(); const float C1 = 6.5025f, C2 = 58.5225f;
/***************************** INITS **********************************/ b.gI1.upload(i1);
b.gI2.upload(i2); gpu::Stream stream; stream.enqueueConvert(b.gI1, b.t1, CV_32F);
stream.enqueueConvert(b.gI2, b.t2, CV_32F); gpu::split(b.t1, b.vI1, stream);
gpu::split(b.t2, b.vI2, stream);
Scalar mssim; for( int i = 0; i < b.gI1.channels(); ++i )
{
gpu::multiply(b.vI2[i], b.vI2[i], b.I2_2, stream); // I2^2
gpu::multiply(b.vI1[i], b.vI1[i], b.I1_2, stream); // I1^2
gpu::multiply(b.vI1[i], b.vI2[i], b.I1_I2, stream); // I1 * I2 //gpu::GaussianBlur(b.vI1[i], b.mu1, Size(11, 11), 1.5, 0, BORDER_DEFAULT, -1, stream);
//gpu::GaussianBlur(b.vI2[i], b.mu2, Size(11, 11), 1.5, 0, BORDER_DEFAULT, -1, stream); gpu::multiply(b.mu1, b.mu1, b.mu1_2, stream);
gpu::multiply(b.mu2, b.mu2, b.mu2_2, stream);
gpu::multiply(b.mu1, b.mu2, b.mu1_mu2, stream); //gpu::GaussianBlur(b.I1_2, b.sigma1_2, Size(11, 11), 1.5, 0, BORDER_DEFAULT, -1, stream);
//gpu::subtract(b.sigma1_2, b.mu1_2, b.sigma1_2, stream);
//b.sigma1_2 -= b.mu1_2; - This would result in an extra data transfer operation //gpu::GaussianBlur(b.I2_2, b.sigma2_2, Size(11, 11), 1.5, 0, BORDER_DEFAULT, -1, stream);
//gpu::subtract(b.sigma2_2, b.mu2_2, b.sigma2_2, stream);
//b.sigma2_2 -= b.mu2_2; //gpu::GaussianBlur(b.I1_I2, b.sigma12, Size(11, 11), 1.5, 0, BORDER_DEFAULT, -1, stream);
//gpu::subtract(b.sigma12, b.mu1_mu2, b.sigma12, stream);
//b.sigma12 -= b.mu1_mu2; //here too it would be an extra data transfer due to call of operator*(Scalar, Mat)
gpu::multiply(b.mu1_mu2, 2, b.t1, stream); //b.t1 = 2 * b.mu1_mu2 + C1;
//gpu::add(b.t1, C1, b.t1, stream);
gpu::multiply(b.sigma12, 2, b.t2, stream); //b.t2 = 2 * b.sigma12 + C2;
//gpu::add(b.t2, C2, b.t2, stream); gpu::multiply(b.t1, b.t2, b.t3, stream); // t3 = ((2*mu1_mu2 + C1).*(2*sigma12 + C2)) //gpu::add(b.mu1_2, b.mu2_2, b.t1, stream);
//gpu::add(b.t1, C1, b.t1, stream); //gpu::add(b.sigma1_2, b.sigma2_2, b.t2, stream);
//gpu::add(b.t2, C2, b.t2, stream); gpu::multiply(b.t1, b.t2, b.t1, stream); // t1 =((mu1_2 + mu2_2 + C1).*(sigma1_2 + sigma2_2 + C2))
gpu::divide(b.t3, b.t1, b.ssim_map, stream); // ssim_map = t3./t1; stream.waitForCompletion(); Scalar s = gpu::sum(b.ssim_map, b.buf);
mssim.val[i] = s.val[0] / (b.ssim_map.rows * b.ssim_map.cols); }
return mssim;
}</span>
实现效果：
基于opencv的gpu与cpu对比程序，代码来自opencv的文档中的更多相关文章
- C# 基于NPOI+Office COM组件 实现20行代码在线预览文档（word，excel，pdf，txt，png）
由于项目需要,需要一个在线预览office的功能,小编一开始使用的是微软提供的方法,简单快捷,但是不符合小编开发需求, 就另外用了:将文件转换成html文件然后预览html文件的方法.对微软提供的方法 ...
- 关于运行“基于极限学习机ELM的人脸识别程序”代码犯下的一些错误
代码来源 基于极限学习机ELM的人脸识别程序 感谢文章主的分享 我的环境是 win10 anaconda Command line client (version 1.6.5)(conda 4.3.3 ...
- 创建MFC应用程序的类型：单文档+多文档+基于对话框
单文档支持文档视图架构.数据的保存--(读取--改动)文档类功能--显示(视图类功能),比較方便. 基于对话框,主窗体是对话框类型.能够方便的使用控件,所见即所得的编程,比較方便. 单文档类似&quo ...
- MFC多文档中opencv处理图像打开、保存
需要在C**Doc和C**View中进行相应修改 图像打开: Doc.cpp中: BOOL CCVMFCDoc::Load(IplImage** pp, LPCTSTR csFilename) { I ...
- 基于数据库的自动化生成工具，自动生成JavaBean、数据库文档、框架代码等(v5.8.8版)
TableGo v5.8.8版震撼发布,此次版本更新如下: 1.新增两个扩展字段,用于生成自定义模板时使用. 2.自定义模板新增模板目录,可以选择不同分类目录下的模 ...
- c语言小程序以及java生成注释文档方法
c语言小程序:sizeof和strlen() sizeof运算符以字节为单位给出数据的大小,strlen()函数以字符为单位给出字符串的长度,字符和字节不是一回事. char类型用于存储字母和标点符号 ...
- JDBC Java 程序从 MySQL 数据库中读取数据，并备份到 xml 文档中
MySQL 版本:Server version: 5.7.17-log MySQL Community Server (GPL) 相关内容:JDBC Java 程序从 MySQL 数据库中读取数据,并 ...
- Caffe常用算子GPU和CPU对比
通过整理LeNet.AlexNet.VGG16.googLeNet.ResNet.MLP统计出的常用算子(不包括ReLU),表格是对比. Prelu Cpu版 Gpu版 for (int i = 0; ...
- 【opencv入门篇】 10个程序快速上手opencv【下】
导言:本系列博客目的在于能够在vs快速上手opencv,理论知识涉及较少,大家有兴趣可以查阅其他博客深入了解相关的理论知识,本博客后续也会对图像方向的理论进一步分析,敬请期待:) 上篇传送:http: ...
随机推荐
- JQuery插件使用之Validation 快速完成表单验证的几种方式
JQuery的Validation插件可以到http://plugins.jquery.com/上去下载.今天来分享一下,关于这个插件的使用. 简易使用 这第一种方式可谓是傻瓜式的使用,我们只需要按照 ...
- Android Studio 不得不知的20大快捷键
如何进入设置快捷键的界面: Android Studio -> References -> Keymap 使用的Keymaps为 Eclipse(Mac OS X)如下图所示: 1 展开和 ...
- 3.QT中的debug相关的函数，以及文件锁的使用
1 新建项目T33Debug main.cpp #include <QDebug> #include <QFile> #include <QMutex> ...
- 1. React介绍 React开发环境搭建 React第一个程序
什么是 React React 是 Facebook 发布的 JavaScript 库,以其高性能和独特的设计理念受到了广泛关注. React的开发背景 Faceboo ...
- picasso图片缓存框架
picasso是Square公司开源的一个Android图形缓存库,地址http://square.github.io/picasso/,可以实现图片下载和缓存功能. picasso使用简单,如下 [ ...
- 从二进制数据流中构造GDAL可以读取的图像数据
在很多时候,我们的图像数据往往都不是文件方式存储在磁盘上,而是可能从网络或者数据库中获取的是二进制的图像数据流.最简单的方式和最容易想到的方式就是将这个文件流保存到磁盘上形成一个文件,然后再使用GDA ...
- 5.创建表，使用alter进行表信息的增删改，Oracle回收站,集合运算
1 Oracle基于用户的管理方案 2 DDL语句可以管理数据库的对象有:视图 索引 序列 同义词 约束 3 创建一个表,有2个条件(1 有权限:2有表空间) Oracle给你提 ...
- UE4使用widget创建UI界面播放视频
我的目的非常简单,点击按钮,播放或暂停场景中的视频 1.准备了一个mp4视频资源,为视频资源创建了一个Media Texture,在Media Player中选择导入进来的视频资源,再为Media T ...
- 【设计模式】java设计模式总述及观察者模式
今天在准备腾讯的面试时想起来要复习一下设计模式,而刚好前几天在参加网易的在线考试的时候,也出了一道关于设计模式的选择题,主要是考察观察者模式,虽然那道题自己做对了,但觉得还是应该好好总结一下设计模式的 ...
- iOS中 Animation 动画大全 韩俊强的博客
每日更新关注:http://weibo.com/hanjunqiang 新浪微博! iOS开发者交流QQ群: 446310206 1.iOS中我们能看到的控件都是UIView的子类,比如UIButt ...