yolo系列用c写的,在工程中的部署特别方便。4月份yolov4横空出世,之前试了试效果,精度确实有了很大的提升,AB大神nb。最近需要在C++项目中使用yolov4,尝试了opencv的调用(见我的上一篇博客这里),yolov4官方也提供了C++接口,并不需要opencv4.4的版本,调用起来也特别简单。
使用官方接口调用,我们首先得编译darknet动态库,下载yolov4源码
git clone https://github.com/AlexeyAB/darknet.git
进入darknet目录下,修改makefile文件
cd darknet
vim Makefile
其中需要修改的几个地方,OPENCV=1,LIBSO=1,如果需要使用GPU,则设置GPU=1,CUDNN=1。
GPU=1
CUDNN=1
CUDNN_HALF=0
OPENCV=1
AVX=0
OPENMP=0
LIBSO=1
ZED_CAMERA=0
ZED_CAMERA_v2_8=0
计算能力根据自己GPU设定,由于我使用的titan v,所以计算能力为7.0,不使用GPU则忽略。
# Tesla A100 (GA100), DGX-A100, RTX 3080
# ARCH= -gencode arch=compute_80,code=[sm_80,compute_80]
# Tesla V100
ARCH= -gencode arch=compute_70,code=[sm_70,compute_70]
# GeForce RTX 2080 Ti, RTX 2080, RTX 2070, Quadro RTX 8000, Quadro RTX 6000, Quadro RTX 5000, Tesla T4, XNOR Tensor Cores
# ARCH= -gencode arch=compute_75,code=[sm_75,compute_75]
# Jetson XAVIER
# ARCH= -gencode arch=compute_72,code=[sm_72,compute_72]
# GTX 1080, GTX 1070, GTX 1060, GTX 1050, GTX 1030, Titan Xp, Tesla P40, Tesla P4
# ARCH= -gencode arch=compute_61,code=sm_61 -gencode arch=compute_61,code=compute_61
# GP100/Tesla P100 - DGX-1
# ARCH= -gencode arch=compute_60,code=sm_60
# For Jetson TX1, Tegra X1, DRIVE CX, DRIVE PX - uncomment:
# ARCH= -gencode arch=compute_53,code=[sm_53,compute_53]
# For Jetson Tx2 or Drive-PX2 uncomment:
# ARCH= -gencode arch=compute_62,code=[sm_62,compute_62]
修改自己的cuda和cudnn的路径,然后make,之后会生成一个libdarknet.so动态库。
ifeq ($(GPU), 1)
COMMON+= -DGPU -I/usr/local/cuda-10.1/include/
CFLAGS+= -DGPU
ifeq ($(OS),Darwin) #MAC
LDFLAGS+= -L/usr/local/cuda-10.1/lib -lcuda -lcudart -lcublas -lcurand
else
LDFLAGS+= -L/usr/local/cuda-10.1/lib64 -lcuda -lcudart -lcublas -lcurand
endif
endif
ifeq ($(CUDNN), 1)
COMMON+= -DCUDNN
ifeq ($(OS),Darwin) #MAC
CFLAGS+= -DCUDNN -I/usr/local/cuda-10.1.0/include
LDFLAGS+= -L/usr/local/cuda-10.1.0/lib -lcudnn
else
CFLAGS+= -DCUDNN -I/usr/local/cuda-10.1.0/include
LDFLAGS+= -L/usr/local/cuda-10.1.0/lib64 -lcudnn
endif
endif
检测部分很简单,需要用到刚刚编译的动态库,以及yolov4源码下的yolo_v2_class.hpp。
其实就那么几步,首先加载网络
string classesFile = "./yolo/coco.names";
string modelConfig = "./yolo/yolov4.cfg";
string modelWeights = "./yolo/yolov4.weights";
//加载类别名
vector<string> classes;
ifstream ifs(classesFile.c_str());
string line;
while (getline(ifs, line)) classes.push_back(line);
//加载网络模型,0是指定第一块GPU
Detector detector(modelConfig, modelWeights, 0);
然后将读取的Mat图像转为yolo输入格式
shared_ptr<image_t> detImg = detector.mat_to_image_resize(frame);
然后检测
vector<bbox_t> outs = detector.detect_resized(*detImg, frame.cols, frame.rows, 0.25);
over了,是不是很简单。
实际上上面转为yolo输入格式和检测两步只需调用一个函数
vector<bbox_t> outs = detector.detect(frame, 0.25);
输出结果结构体bbox_t可以在yolo_v2_class.hpp看到,包括检测框左上角坐标,高和宽,置信度,类别等,有了它们画图也很简单了。
struct bbox_t {
unsigned int x, y, w, h; // (x,y) - top-left corner, (w, h) - width & height of bounded box
float prob; // confidence - probability that the object was found correctly
unsigned int obj_id; // class of object - from range [0, classes-1]
unsigned int track_id; // tracking id for video (0 - untracked, 1 - inf - tracked object)
unsigned int frames_counter; // counter of frames on which the object was detected
float x_3d, y_3d, z_3d; // center of object (in Meters) if ZED 3D Camera is used
};
下面附上完整代码
#include
#include
#include
#include
#include
#include "yolo_v2_class.hpp"
using namespace std;
using namespace cv;
#define GPU
//画出检测框和相关信息
void DrawBoxes(Mat &frame, vector<string> classes, int classId, float conf, int left, int top, int right, int bottom)
{
//画检测框
rectangle(frame, Point(left, top), Point(right, bottom), Scalar(255, 178, 50), 3);
//该检测框对应的类别和置信度
string label = format("%.2f", conf);
if (!classes.empty())
{
CV_Assert(classId < (int)classes.size());
label = classes[classId] + ":" + label;
}
//将标签显示在检测框顶部
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);
}
//画出检测结果
void Drawer(Mat &frame, vector<bbox_t> outs, vector<string> classes)
{
//获取所有最佳检测框信息
for (int i = 0; i < outs.size(); i++)
{
DrawBoxes(frame, classes, outs[i].obj_id, outs[i].prob, outs[i].x, outs[i].y,
outs[i].x + outs[i].w, outs[i].y + outs[i].h);
}
}
int main(void)
{
string classesFile = "./yolo/coco.names";
string modelConfig = "./yolo/yolov4.cfg";
string modelWeights = "./yolo/yolov4.weights";
//加载类别名
vector<string> classes;
ifstream ifs(classesFile.c_str());
string line;
while (getline(ifs, line)) classes.push_back(line);
//加载网络模型,0是指定第一块GPU
Detector detector(modelConfig, modelWeights, 0);
string mode = "video";
//图像
if (mode == "image")
{
Mat frame = imread("./data/test.jpg");
//Mat图像转为yolo输入格式
shared_ptr<image_t> detImg = detector.mat_to_image_resize(frame);
//前向预测
vector<bbox_t> outs = detector.detect_resized(*detImg, frame.cols, frame.rows, 0.25);
//画图
Drawer(frame, outs, classes);
imwrite("./data/result.jpg", frame);
}
//视频
else if (mode == "video")
{
VideoCapture cap("./data/test.avi");
Size size(1920, 1080);
VideoWriter writer("./data/result.avi", cv::VideoWriter::fourcc('M', 'J', 'P', 'G'), 25, size);
while (1)
{
Mat frame;
cap >> frame;
if (frame.empty())
break;
//Mat图像转为yolo输入格式
shared_ptr<image_t> detImg = detector.mat_to_image_resize(frame);
//前向预测
vector<bbox_t> outs = detector.detect_resized(*detImg, frame.cols, frame.rows, 0.25);
//画图
Drawer(frame, outs, classes);
writer << frame;
}
cap.release();
}
return 0;
}
代码我放到了github上。
1、需要用到刚刚编译的libdarknet.so,将它放到项目lib目录下,另外需要用到yolov4源码下的yolo_v2_class.hpp文件。
2、将coco.names、yolov4.cfg、yolov4.weights三个文件放到项目yolo目录下,我放到了百度网盘中,提取码:2zfk。
3、在detection.cpp中修改自己检测图像或视频的路径,然后编译
make