win10+VS2015+opencv3.4.3调用darknet模型

opencv必须大于等于3.4.2

opencv在线文档：

https://docs.opencv.org/trunk/db/d30/classcv_1_1dnn_1_1Net.html#a98ed94cb6ef7063d3697259566da310b

参考文章：

https://blog.51cto.com/gloomyfish/2095418

https://blog.csdn.net/windfly_al/article/details/84873767

https://blog.csdn.net/shanglianlm/article/details/80030569

blobFromImage函数

• 第一个参数，InputArray image，表示输入的图像，可以是opencv的mat数据类型。
• 第二个参数，scalefactor，这个参数很重要的，如果训练时，是归一化到0-1之间，那么这个参数就应该为0.00390625f （1/256），否则为1.0
• 第三个参数，size，应该与训练时的输入图像尺寸保持一致。
• 第四个参数，mean，这个主要在caffe中用到，caffe中经常会用到训练数据的均值。tf中貌似没有用到均值文件。
• 第五个参数，swapRB，是否交换图像第1个通道和最后一个通道的顺序。
• 第六个参数，crop，如果为true，就是裁剪图像，如果为false，就是等比例放缩图像。

#include "stdafx.h"
#include <fstream>
#include <sstream>
#include <iostream>
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>

#include <opencv2/highgui.hpp>
#include<vector>


using namespace std;
using namespace cv;
using namespace dnn;

vector<string> classes;

vector<String> getOutputsNames(Net&net)
{
	static vector<String> names;
	if (names.empty())
	{
		//返回加载模型中所有层的输入和输出形状(shape)
		vector<int> outLayers = net.getUnconnectedOutLayers();

		//get the names of all the layers in the network
		vector<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;
}
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame)
{
	//Draw a rectangle displaying the bounding box
	rectangle(frame, Point(left, top), Point(right, bottom), Scalar(255, 178, 50), 3);

	//Get the label for the class name and its confidence
	string label = format("%.5f", conf);
	if (!classes.empty())
	{
		CV_Assert(classId < (int)classes.size());
		label = classes[classId] + ":" + label;
	}

	//Display the label at the top of the bounding box
	int baseLine;
	Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
	top = max(top, labelSize.height);
	rectangle(frame, Point(left, top - round(1.5*labelSize.height)), Point(left + round(1.5*labelSize.width), top + baseLine), Scalar(255, 255, 255), FILLED);
	putText(frame, label, Point(left, top), FONT_HERSHEY_SIMPLEX, 0.75, Scalar(0, 0, 0), 1);
}

void postprocess(Mat& frame, const vector<Mat>& outs, float confThreshold, float nmsThreshold)
{
	vector<int> classIds;
	vector<float> confidences;
	vector<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)
		{
			Mat scores = outs[i].row(j).colRange(5, outs[i].cols);
			Point classIdPoint;
			double confidence;
			// Get the value and location of the maximum score
			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(Rect(left, top, width, height));
			}
		}
	}

	// Perform non maximum suppression to eliminate redundant overlapping boxes with
	// lower confidences
	vector<int> indices;
	NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices);
	for (size_t i = 0; i < indices.size(); ++i)
	{
		int idx = indices[i];
		Rect box = boxes[idx];
		drawPred(classIds[idx], confidences[idx], box.x, box.y,
			box.x + box.width, box.y + box.height, frame);
	}
}

int main()
{
	
	
	//1.加载网络模型
	String model_def = "/home/oliver/darknet-master/cfg/yolov3.cfg";
	String weights = "/home/oliver/darknet-master/yolov3.weights";
	Net net = readNetFromDarknet(model_def, weights);
	if (net.empty())
	{
		printf("Could not load net...\n");
		return 0;
	}

	//2.加载分类信息
	/*vector<string> classNamesVec;
	ifstream classNamesFile("D:/vcprojects/images/dnn/yolov2-tiny-voc/voc.names");
	if (classNamesFile.is_open())
	{
		string className = "";
		while (std::getline(classNamesFile, className))
			classNamesVec.push_back(className);
	}*/
	string names_file = "/home/oliver/darknet-master/data/coco.names";
	ifstream ifs(names_file.c_str());
	string line;
	while (getline(ifs, line)) classes.push_back(line);

	// 3.加载图像
	Mat frame = imread("D:/vcprojects/images/fastrcnn.jpg");
	Mat inputBlob = blobFromImage(frame, 1 / 255.F, Size(416, 416), Scalar(), true, false);
	net.setInput(inputBlob, "data");

	string img_path = "/home/oliver/darknet/data/dog.jpg";


	int in_w, in_h;
	double thresh = 0.5;
	double nms_thresh = 0.25;
	in_w = in_h = 608;

	/*要求网络在支持的地方使用特定的计算后端
	*如果opencv是用intel的推理引擎库编译的，那么dnn_backend_default意味着dnn_backend_interrusion_引擎
	*否则等于dnn_backend_opencv。
	*/
	net.setPreferableBackend(DNN_BACKEND_OPENCV);
	//要求网络对特定目标设备进行计算
	net.setPreferableTarget(DNN_TARGET_CPU);


	//read image and forward
	VideoCapture capture(2);// VideoCapture:OENCV中新增的类，捕获视频并显示出来
	while (1)
	{
		Mat frame, blob;
		capture >> frame;


		blobFromImage(frame, blob, 1 / 255.0, Size(in_w, in_h), Scalar(), true, false);

		vector<Mat> mat_blob;
		imagesFromBlob(blob, mat_blob);

		//Sets the input to the network
		net.setInput(blob);

		// Runs the forward pass to get output of the output layers
		vector<Mat> outs;
		net.forward(outs, getOutputsNames(net));

		postprocess(frame, outs, thresh, nms_thresh);

		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(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 255));

		imshow("res", frame);

		waitKey(10);
	}
	return 0;
}