我使用opencv dnn分类,但结果与caffe预测不匹配。令我感到困惑的是,有些图像可能会得到类似于caffe的结果,而少数图像则没有。当我将BGR更改为RGB时,大多数结果都是错误的。
类似的结果:
不同的结果:
blobFromImage(norm_img,1.0,cv :: Size(64,64));当使用默认参数时将BGR更改为RGB,但结果会出错。所以我像这样使用blobFromImage(norm_img,1.0,cv :: Size (64,64),cv :: Scalar(),false); 。大部分结果会与caffe预测相匹配,为什么少数图像没有?
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <opencv2/core/utils/trace.hpp>
using namespace cv;
using namespace cv::dnn;
#include <fstream>
#include <iostream>
#include <cstdlib>
using namespace std;
/* Find best class for the blob (i. e. class with maximal probability) */
static void getMaxClass(const Mat &probBlob, int *classId, double *classProb)
{
Mat probMat = probBlob.reshape(1, 1); //reshape the blob to 1x1000 matrix
Point classNumber;
minMaxLoc(probMat, NULL, classProb, NULL, &classNumber);
*classId = classNumber.x;
}
static std::vector<String> readClassNames(const char *filename = "./config/type.txt")
{
std::vector<String> classNames;
std::ifstream fp(filename);
if (!fp.is_open())
{
std::cerr << "File with classes labels not found: " << filename << std::endl;
exit(-1);
}
std::string name;
while (!fp.eof())
{
std::getline(fp, name);
if (name.length())
classNames.push_back(name.substr(name.find(' ') + 1));
}
fp.close();
return classNames;
}
int main(int argc, char **argv)
{
CV_TRACE_FUNCTION();
String modelTxt = "./config/HCCR3755_res20_deploy.prototxt";
String modelBin = "./config/HCCR3755-res20_iter_790000.caffemodel";
String imageFile = "./config/b9.jpg";
Net net = dnn::readNetFromCaffe(modelTxt, modelBin);
if (net.empty())
{
std::cerr << "Can't load network by using the following files: " << std::endl;
std::cerr << "prototxt: " << modelTxt << std::endl;
std::cerr << "caffemodel: " << modelBin << std::endl;
exit(-1);
}
Mat img = imread(imageFile);
FileStorage fs("./config/mean.xml", FileStorage::READ);
Mat _mean;
fs["vocabulary"] >> _mean;
if (img.empty())
{
std::cerr << "Can't read image from the file: " << imageFile << std::endl;
exit(-1);
}
cv::Mat img_resize;
resize(img, img_resize, Size(64, 64));
cv::Mat img_float;
img_resize.convertTo(img_float, CV_32FC3);
cv::Mat norm_img;
cv::subtract(img_float, _mean, norm_img);
Mat inputBlob = blobFromImage(norm_img, 1.0, cv::Size(64, 64), cv::Scalar(),false); //Convert Mat to batch of images
Mat prob;
cv::TickMeter t;
for (int i = 0; i < 1; i++)
{
CV_TRACE_REGION("forward");
//! [Set input blob]
net.setInput(inputBlob, "data"); //set the network input
//! [Set input blob]
t.start();
//! [Make forward pass]
prob = net.forward("prob");
//std::cout << prob << std::endl;//compute output
//! [Make forward pass]
t.stop();
}
int classId;
double classProb;
getMaxClass(prob, &classId, &classProb);//find the best class
//! [Gather output]
//! [Print results]
std::vector<String> classNames = readClassNames();
std::cout << "Best class: #" << classId << " '" << classNames.at(classId) << "'" << std::endl;
std::cout << "Probability: " << classProb * 100 << "%" << std::endl;
//! [Print results]
std::cout << "Time: " << (double)t.getTimeMilli() / t.getCounter() << " ms (average from " << t.getCounter() << " iterations)" << std::endl;
getchar();
return 0;
} //main