OPENCV例子opencv-4.5.5\samples\dnn\classification.cpp的代码分析
使用DNN：blobFromImage进行分类的示例
示例main函数调用情况如下：
示例main函数流程图情况如下：
示例main函数UML逻辑图情况如下：
示例源代码如下：
#include
#include
#include
#include
#include
#include
#include "common.hpp"
std::string keys =
"{ help h | | Print help message. }"
"{ @alias | | An alias name of model to extract preprocessing parameters from models.yml file. }"模型的别名，用于从 models.yml 文件中提取预处理参数
"{ zoo | models.yml | An optional path to file with preprocessing parameters }"带有预处理参数的文件的可选路径
"{ input i | | Path to input image or video file. Skip this argument to capture frames from a camera.}" 输入图像或视频文件的路径。跳过此参数以从相机捕获帧
"{ initial_width | 0 | Preprocess input image by initial resizing to a specific width.}" 通过初始调整到特定宽度来预处理输入图像
"{ initial_height | 0 | Preprocess input image by initial resizing to a specific height.}" 通过初始调整到特定高度来预处理输入图像
"{ std | 0.0 0.0 0.0 | Preprocess input image by dividing on a standard deviation.}" 通过除以标准偏差来预处理输入图像
"{ crop | false | Preprocess input image by center cropping.}" 通过中心裁剪预处理输入图像
"{ framework f | | Optional name of an origin framework of the model. Detect it automatically if it does not set. }"模型的原始框架的可选名称。如果没有设置就自动检测
"{ needSoftmax | false | Use Softmax to post-process the output of the net.}" 使用 Softmax 对网络的输出进行后处理
"{ classes | | Optional path to a text file with names of classes. }"带有类名的文本文件的可选路径
"{ backend | 0 | Choose one of computation backends: "选择一个计算后端
"0: automatically (by default), "自动（默认）
"1: Halide language (http://halide-lang.org/), "卤化物语言
"2: Intel's Deep Learning Inference Engine (https://software.intel.com/openvino-toolkit), "英特尔的深度学习推理引擎
"3: OpenCV implementation, " OpenCV 实现
"4: VKCOM, "
"5: CUDA, "
"6: WebNN }"
"{ target | 0 | Choose one of target computation devices: "选择目标计算设备之一
"0: CPU target (by default), "
"1: OpenCL, "
"2: OpenCL fp16 (half-float precision), "
"3: VPU, "
"4: Vulkan, "
"6: CUDA, "
"7: CUDA fp16 (half-float preprocess) }";
using namespace cv;
using namespace blobFromImage;
std::vector<std::string> classes;
int main(int argc, char** argv)
{
CommandLineParser parser(argc, argv, keys);
const std::string modelName = parser.get<String>("@alias");
const std::string zooFile = parser.get<String>("zoo");
keys += genPreprocArguments(modelName, zooFile);
parser = CommandLineParser(argc, argv, keys);
parser.about("Use this script to run classification deep learning networks using OpenCV."); 使用此脚本使用 OpenCV 运行分类深度学习网络
if (argc == 1 || parser.has("help"))
{
parser.printMessage();
return 0;
}
int rszWidth = parser.get<int>("initial_width");
int rszHeight = parser.get<int>("initial_height");
float scale = parser.get<float>("scale");
Scalar mean = parser.get<Scalar>("mean");
Scalar std = parser.get<Scalar>("std");
bool swapRB = parser.get<bool>("rgb");
bool crop = parser.get<bool>("crop");
int inpWidth = parser.get<int>("width");
int inpHeight = parser.get<int>("height");
String model = findFile(parser.get<String>("model"));
String config = findFile(parser.get<String>("config"));
String framework = parser.get<String>("framework");
int backendId = parser.get<int>("backend");
int targetId = parser.get<int>("target");
bool needSoftmax = parser.get<bool>("needSoftmax");
std::cout<<"mean: "<<mean<<std::endl;
std::cout<<"std: "<<std<<std::endl;
// Open file with classes names.
if (parser.has("classes"))
{
std::string file = parser.get<String>("classes");
std::ifstream ifs(file.c_str());
if (!ifs.is_open())
CV_Error(Error::StsError, "File " + file + " not found");
std::string line;
while (std::getline(ifs, line))
{
classes.push_back(line);
}
}
if (!parser.check())
{
parser.printErrors();
return 1;
}
CV_Assert(!model.empty());
//! [Read and initialize network] 读取和初始化网络
Net net = readNet(model, config, framework);
net.setPreferableBackend(backendId);
net.setPreferableTarget(targetId);
//! [Read and initialize network] 读取和初始化网络
// Create a window
static const std::string kWinName = "Deep learning image classification in OpenCV";
namedWindow(kWinName, WINDOW_NORMAL);
//! [Open a video file or an image file or a camera stream] 打开视频文件或图像文件或摄像头视频流
VideoCapture cap;
if (parser.has("input"))
cap.open(parser.get<String>("input"));
else
cap.open(0);
//! [Open a video file or an image file or a camera stream]
// Process frames. 过程框架
Mat frame, blob;
while (waitKey(1) < 0)
{
cap >> frame;
if (frame.empty())
{
waitKey();
break;
}
if (rszWidth != 0 && rszHeight != 0)
{
resize(frame, frame, Size(rszWidth, rszHeight));
}
//! [Create a 4D blob from a frame] 从帧创建 4D blob
blobFromImage(frame, blob, scale, Size(inpWidth, inpHeight), mean, swapRB, crop);
// Check std values.
if (std.val[0] != 0.0 && std.val[1] != 0.0 && std.val[2] != 0.0)
{
// Divide blob by std.
divide(blob, std, blob);
}
//! [Create a 4D blob from a frame] 产生4维的数组blob用于神经网络
//! [Set input blob]
net.setInput(blob);
//! [Set input blob]
//! [Make forward pass]
// double t_sum = 0.0;
// double t;
int classId;
double confidence;
cv::TickMeter timeRecorder;
timeRecorder.reset();
Mat prob = net.forward();
double t1;
timeRecorder.start();
prob = net.forward();
timeRecorder.stop();
t1 = timeRecorder.getTimeMilli();
timeRecorder.reset();
for(int i = 0; i < 200; i++) {
//! [Make forward pass]
timeRecorder.start();
prob = net.forward();
timeRecorder.stop();
//! [Get a class with a highest score]得到最高分的分类
Point classIdPoint;
minMaxLoc(prob.reshape(1, 1), 0, &confidence, 0, &classIdPoint);
classId = classIdPoint.x;
//! [Get a class with a highest score]
// Put efficiency information.
// std::vector
// double freq = getTickFrequency() / 1000;
// t = net.getPerfProfile(layersTimes) / freq;
// t_sum += t;
}
if (needSoftmax == true)
{
float maxProb = 0.0;
float sum = 0.0;
Mat softmaxProb;
maxProb = *std::max_element(prob.begin<float>(), prob.end<float>());
cv::exp(prob-maxProb, softmaxProb);
sum = (float)cv::sum(softmaxProb)[0];
softmaxProb /= sum;
Point classIdPoint;
minMaxLoc(softmaxProb.reshape(1, 1), 0, &confidence, 0, &classIdPoint);
classId = classIdPoint.x;
}
std::string label = format("Inference time of 1 round: %.2f ms", t1);
std::string label2 = format("Average time of 200 rounds: %.2f ms", timeRecorder.getTimeMilli()/200);
putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
putText(frame, label2, Point(0, 35), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
// Print predicted class.
label = format("%s: %.4f", (classes.empty() ? format("Class #%d", classId).c_str() :
classes[classId].c_str()),
confidence);
putText(frame, label, Point(0, 55), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
imshow(kWinName, frame);
}
return 0;
}