C++ 基于预训练caffe模型的图像分类
我正在visual studio中做一个关于使用预先训练好的caffe模型进行图像分类的项目,openCV3.4.0,C++ 我面临着一些错误:C++ 基于预训练caffe模型的图像分类,c++,opencv,visual-c++,caffe,object-recognition,C++,Opencv,Visual C++,Caffe,Object Recognition,我正在visual studio中做一个关于使用预先训练好的caffe模型进行图像分类的项目,openCV3.4.0,C++ 我面临着一些错误: readNet:Identifier未找到 blobFromImage:function不接受7个参数 我从你的电脑上复制了代码 请帮帮我,因为我是新手。提前谢谢 代码: const char* keys = "{ help h | | Print help message. }" "{ input i | | Path to inp
readNet:Identifier
未找到blobFromImage:function
不接受7个参数const char* keys =
"{ help h | | Print help message. }"
"{ input i | | Path to input image or video file. Skip this argument to capture frames from a camera.}"
"{ model m | | Path to a binary file of model contains trained weights. "
"It could be a file with extensions .caffemodel (Caffe), "
".pb (TensorFlow), .t7 or .net (Torch), .weights (Darknet) }"
"{ config c | | Path to a text file of model contains network configuration. "
"It could be a file with extensions .prototxt (Caffe), .pbtxt (TensorFlow), .cfg (Darknet) }"
"{ framework f | | Optional name of an origin framework of the model. Detect it automatically if it does not set. }"
"{ classes | | Optional path to a text file with names of classes. }"
"{ mean | | Preprocess input image by subtracting mean values. Mean values should be in BGR order and delimited by spaces. }"
"{ scale | 1 | Preprocess input image by multiplying on a scale factor. }"
"{ width | | Preprocess input image by resizing to a specific width. }"
"{ height | | Preprocess input image by resizing to a specific height. }"
"{ rgb | | Indicate that model works with RGB input images instead BGR ones. }"
"{ backend | 0 | Choose one of computation backends: "
"0: default C++ backend, "
"1: Halide language (http://halide-lang.org/), "
"2: Intel's Deep Learning Inference Engine (https://software.seek.intel.com/deep-learning-deployment)}"
"{ target | 0 | Choose one of target computation devices: "
"0: CPU target (by default),"
"1: OpenCL }";
using namespace cv;
using namespace dnn;
std::vector<std::string> classes;
int main(int argc, char** argv)
{
CommandLineParser parser(argc, argv, keys);
parser.about("Use this script to run classification deep learning networks using OpenCV.");
if (argc == 1 || parser.has("help"))
{
parser.printMessage();
return 0;
}
float scale = parser.get<float>("scale");
Scalar mean = parser.get<Scalar>("mean");
bool swapRB = parser.get<bool>("rgb");
CV_Assert(parser.has("width"), parser.has("height"));
int inpWidth = parser.get<int>("width");
int inpHeight = parser.get<int>("height");
String model = parser.get<String>("model");
String config = parser.get<String>("config");
String framework = parser.get<String>("framework");
int backendId = parser.get<int>("backend");
int targetId = parser.get<int>("target");
// 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);
}
}
CV_Assert(parser.has("model"));
Net net = readNet(model, config, framework);
net.setPreferableBackend(backendId);
net.setPreferableTarget(targetId);
// Create a window
static const std::string kWinName = "Deep learning image classification in OpenCV";
namedWindow(kWinName, WINDOW_NORMAL);
VideoCapture cap;
if (parser.has("input"))
cap.open(parser.get<String>("input"));
else
cap.open(0);
// Process frames.
Mat frame, blob;
while (waitKey(1) < 0)
{
cap >> frame;
if (frame.empty())
{
waitKey();
break;
}
blobFromImage(frame, blob, scale, Size(inpWidth, inpHeight), mean, swapRB, false);
net.setInput(blob);
Mat prob = net.forward();
Point classIdPoint;
double confidence;
minMaxLoc(prob.reshape(1, 1), 0, &confidence, 0, &classIdPoint);
int classId = classIdPoint.x;
// Put efficiency information.
std::vector<double> layersTimes;
double freq = getTickFrequency() / 1000;
double t = net.getPerfProfile(layersTimes) / freq;
std::string label = format("Inference time: %.2f ms", t);
putText(frame, label, Point(0, 15), 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, 40), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
imshow(kWinName, frame);
}
return 0;
}
const char*键=
“{help h | |打印帮助消息。}”
“{input i | |输入图像或视频文件的路径。跳过此参数可从相机捕获帧。}”
{model m | |模型二进制文件的路径包含经过训练的权重
它可能是一个扩展名为.caffemodel(Caffe)的文件
.pb(TensorFlow)、.t7或.net(Torch)、.weights(Darknet)}
{config c | |模型的文本文件的路径包含网络配置
它可以是扩展名为.prototxt(Caffe)、.pbtxt(TensorFlow)、.cfg(Darknet)}的文件
“{framework f | |模型的原始框架的可选名称。如果未设置,则自动检测它。}”
“{classes | |具有类名称的文本文件的可选路径。}”
“{mean | |通过减去平均值预处理输入图像。平均值应按BGR顺序并用空格分隔。}”
“{scale | 1 |通过乘以比例因子对输入图像进行预处理。}”
“{width | |通过调整到特定宽度来预处理输入图像。}”
“{height | |通过调整到特定高度来预处理输入图像。}”
“{rgb | |表示模型使用rgb输入图像而不是BGR图像。}”
{后端| 0 |选择一个计算后端:
“0:默认C++后端”
“1:卤化物语言(http://halide-lang.org/), "
“2:英特尔的深度学习推理机(https://software.seek.intel.com/deep-learning-deployment)}"
{target | 0 |选择一个目标计算设备:
0:CPU目标(默认情况下)
“1:OpenCL}”;
使用名称空间cv;
使用名称空间dnn;
std::向量类;
int main(int argc,字符**argv)
{
CommandLineParser解析器(argc、argv、键);
about(“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();
返回0;
}
float scale=parser.get(“scale”);
标量平均值=parser.get(“平均值”);
boolswaprb=parser.get(“rgb”);
CV_断言(parser.has(“宽度”)、parser.has(“高度”);
int inpWidth=parser.get(“宽度”);
int inpHeight=parser.get(“高度”);
字符串模型=parser.get(“模型”);
String config=parser.get(“config”);
stringframework=parser.get(“framework”);
int backendId=parser.get(“backend”);
int targetId=parser.get(“target”);
//打开具有类名称的文件。
if(parser.has(“类”))
{
std::string file=parser.get(“类”);
std::ifstream ifs(file.c_str());
如果(!ifs.is_open())
CV_错误(错误::stror,“文件”+文件+“未找到”);
std::字符串行;
while(std::getline(ifs,line))
{
类。推回(行);
}
}
CV_断言(parser.has(“model”);
Net=readNet(模型、配置、框架);
net.setPreferableBackend(backendId);
net.setPreferableTarget(targetId);
//创建一个窗口
static const std::string kWinName=“OpenCV中的深度学习图像分类”;
namedWindow(kWinName,窗口正常);
视频捕捉帽;
if(parser.has(“输入”))
cap.open(parser.get(“input”);
其他的
上限开放(0);
//处理框架。
垫架,水滴;
while(等待键(1)<0)
{
cap>>框架;
if(frame.empty())
{
waitKey();
打破
}
blobFromImage(帧、blob、比例、大小(inpWidth、inpHeight)、平均值、swapRB、false);
net.setInput(blob);
Mat prob=net.forward();
点分类点;
双重信心;
minMaxLoc(概率重塑(1,1),0和置信度,0和分类点);
int classId=classIdPoint.x;
//把效率信息放进去。
std::向量分层时间;
double freq=getTickFrequency()/1000;
double t=net.getPerfProfile(layersTimes)/freq;
std::string label=格式(“推断时间:%.2f ms”,t);
putText(帧、标签、点(0,15)、字体(HERSHEY)单纯形、0.5、标量(0,255,0));
//打印预测类。
label=format(“%s:%.4f)”,(classes.empty()?format(“Class#%d”,classId)。c#u str():
类[classId].c_str()),
信心);
putText(帧、标签、点(0,40)、字体(HERSHEY)单纯形、0.5、标量(0,255,0));
imshow(kWinName,frame);
}
返回0;
}
您复制的代码指的是开发分支3.4.1-dev,与您正在使用的版本(3.4.0)相比,该分支有相当大的差异
根据文档,只有一次方法readNet不可用(因此出现错误)
升级到branch 3.4.1-dev或使用为您的版本提供的示例。您复制的代码指的是开发分支3.4.1-dev,与您使用的版本(3.4.0)相比,该分支有相当大的差异 根据文档,只有一次方法readNet不可用(因此出现错误)
升级到branch 3.4.1-dev或使用为您的版本提供的示例。在机器学习中,使用经过训练的模型通常称为推理。在机器学习中,使用经过训练的模型通常称为推理。