实践环境:
VS2015 + OPENCV4.5 (release build)
cpu :i7
对比了 darket 和 opencv dnn
darknet:
./darknet_no_gpu.exe detector test data/coco.data cfg/yolov3-tiny.cfg yolov3-tiny.weights -i 0 -thresh 0.25 data/dog.jpg --img-size 416 -ext_output
opencv-dnn:
#include <iostream>
#include <cstdlib>
#include <fstream>
#include<opencv2\dnn\dnn.hpp>
#include<opencv2\core.hpp>
#include<opencv2\highgui\highgui.hpp>
#include<opencv2\imgproc\imgproc.hpp>
using namespace cv;
using namespace cv::dnn;
using namespace std;
// Initialize the parameters
float confThreshold = 0.5; // Confidence threshold
float nmsThreshold = 0.4; // Non-maximum suppression threshold
int inpWidth = 416; // Width of network's input image
int inpHeight = 416; // Height of network's input imag
std::vector<std::string> classes;
// Draw the predicted bounding box
void drawPred(int classId, float conf, int left, int top, int right, int bottom, cv::Mat& frame)
{
//Draw a rectangle displaying the bounding box
cv::rectangle(frame, cv::Point(left, top), cv::Point(right, bottom), cv::Scalar(0, 0, 255));
//Get the label for the class name and its confidence
std::string label = cv::format("%.2f", conf);
if (!classes.empty())
{
CV_Assert(classId < (int)classes.size());
label = classes[classId] + ":" + label;
}
else
{
std::cout << "classes is empty..." << std::endl;
}
//Display the label at the top of the bounding box
int baseLine;
cv::Size labelSize = cv::getTextSize(label, cv::FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
top = std::max(top, labelSize.height);
cv::putText(frame, label, cv::Point(left, top), cv::FONT_HERSHEY_SIMPLEX, 0.5, cv::Scalar(255, 255, 255));
}
// Remove the bounding boxes with low confidence using non-maxima suppression
void postprocess(cv::Mat& frame, std::vector<cv::Mat>& outs)
{
std::vector<int> classIds;
std::vector<float> confidences;
std::vector<cv::Rect> boxes;
for (size_t i = 0; i < outs.size(); ++i)
{
// Scan through all the bounding boxes output from the network and keep only the
// ones with high confidence scores. Assign the box's class label as the class
// with the highest score for the box.
float* data = (float*)outs[i].data;
for (int j = 0; j < outs[i].rows; ++j, data += outs[i].cols)
{
cv::Mat scores = outs[i].row(j).colRange(5, outs[i].cols);
cv::Point classIdPoint;
double confidence;
// Get the value and location of the maximum score
cv::minMaxLoc(scores, 0, &confidence, 0, &classIdPoint);
if (confidence > confThreshold)
{
int centerX = (int)(data[0] * frame.cols);
int centerY = (int)(data[1] * frame.rows);
int width = (int)(data[2] * frame.cols);
int height = (int)(data[3] * frame.rows);
int left = centerX - width / 2;
int top = centerY - height / 2;
classIds.push_back(classIdPoint.x);
confidences.push_back((float)confidence);
boxes.push_back(cv::Rect(left, top, width, height));
}
}
}
// Perform non maximum suppression to eliminate redundant overlapping boxes with
// lower confidences
std::vector<int> indices;
cv::dnn::NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices);
for (size_t i = 0; i < indices.size(); ++i)
{
int idx = indices[i];
cv::Rect box = boxes[idx];
drawPred(classIds[idx], confidences[idx], box.x, box.y,
box.x + box.width, box.y + box.height, frame);
}
}
// Get the names of the output layers
std::vector<cv::String> getOutputsNames(const cv::dnn::Net& net)
{
static std::vector<cv::String> names;
if (names.empty())
{
//Get the indices of the output layers, i.e. the layers with unconnected outputs
std::vector<int> outLayers = net.getUnconnectedOutLayers();
//get the names of all the layers in the network
std::vector<cv::String> layersNames = net.getLayerNames();
// Get the names of the output layers in names
names.resize(outLayers.size());
for (size_t i = 0; i < outLayers.size(); ++i)
names[i] = layersNames[outLayers[i] - 1];
}
return names;
}
int main()
{
// Give the configuration and weight files for the model
string modelConfiguration = "D:\\yolov3\\cfg\\yolov3.cfg";
string modelWeights = "D:\\yolov3\\yolov3.weights";
// Load names of classes
string classesFile = "D:\\yolov3\\data\\coco.names";
ifstream ifs(classesFile.c_str());
string line;
clock_t start, finish;
while (getline(ifs, line))
{
classes.push_back(line);
}
//Load the network
Net net = readNetFromDarknet(modelConfiguration, modelWeights);
cv::Mat blob;
Mat frame0;
//Load test image
for (int i = 0; i < 100; ++i) {
Mat frame = imread("D:\\yolov3\\data\\dog.jpg");
//start time
start = clock();
//Create a 4D blob from a frame. 创建神经网络输入图像
blobFromImage(frame, blob, 1 / 255.0, cv::Size(inpWidth, inpHeight), Scalar(0, 0, 0), true, false);
//Sets the input to the network 设置输出
net.setInput(blob);
//Runs the forward pass to get output of the output layers 获取输出层结果
vector<Mat> outs;
net.forward(outs, getOutputsNames(net));
//Remove the bounding boxes with low confidence
postprocess(frame, outs);
finish = clock();
cout << "Run time is " << double(finish - start) / CLOCKS_PER_SEC << endl;
frame0 = frame;
}
//Put efficiency information. The function getPerfProfile returns the overall time for inference(t) and the timings for each of the layers(in layersTimes)
//输出前向传播的时间
vector<double> layersTimes;
double freq = getTickFrequency() / 1000;
double t = net.getPerfProfile(layersTimes) / freq;
string label = format("Inference time for a frame : %.2f ms", t);
putText(frame0, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 255));
imshow("result", frame0);
//保存图像
imwrite("D:\\yolov3\\result.jpg", frame0);
cv::waitKey(0);
}
检测结果 上看,几位速度快的自行车都不要了。 唉。 yolov3-tiny opencv dnn 还多认了一辆跑车。
再看看 yolov3 opencv dnn