OpenCV  4.1.2
Open Source Computer Vision
samples/dnn/classification.cpp

Check the corresponding tutorial for more details

#include <fstream>
#include <sstream>
#include <opencv2/dnn.hpp>
#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. }"
"{ zoo | models.yml | An optional path to file with preprocessing parameters }"
"{ input i | | Path to input image or video file. Skip this argument to capture frames from a camera.}"
"{ 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. }"
"{ backend | 0 | Choose one of computation backends: "
"0: automatically (by default), "
"1: Halide language (http://halide-lang.org/), "
"2: Intel's Deep Learning Inference Engine (https://software.intel.com/openvino-toolkit), "
"3: OpenCV implementation }"
"{ target | 0 | Choose one of target computation devices: "
"0: CPU target (by default), "
"1: OpenCL, "
"2: OpenCL fp16 (half-float precision), "
"3: VPU }";
using namespace cv;
using namespace dnn;
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.");
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");
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");
// 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());
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";
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())
{
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;
}
cv::Mat::reshape
Mat reshape(int cn, int rows=0) const
Changes the shape and/or the number of channels of a 2D matrix without copying the data.
cv::FONT_HERSHEY_SIMPLEX
normal size sans-serif font
Definition: imgproc.hpp:812
cv::String
std::string String
Definition: cvstd.hpp:150
cv::Point_< int >
cv::CommandLineParser::check
bool check() const
Check for parsing errors.
cv::dnn::readNet
Net readNet(const String &model, const String &config="", const String &framework="")
Read deep learning network represented in one of the supported formats.
cv::CommandLineParser::get
T get(const String &name, bool space_delete=true) const
Access arguments by name.
Definition: utility.hpp:898
cv::samples::findFile
cv::String findFile(const cv::String &relative_path, bool required=true, bool silentMode=false)
Try to find requested data file.
cv::WINDOW_NORMAL
the user can resize the window (no constraint) / also use to switch a fullscreen window to a normal s...
Definition: highgui.hpp:183
cv::VideoCapture
Class for video capturing from video files, image sequences or cameras.
Definition: videoio.hpp:603
cv::waitKey
int waitKey(int delay=0)
Waits for a pressed key.
cv::Point_::x
_Tp x
x coordinate of the point
Definition: types.hpp:186
dnn.hpp
highgui.hpp
cv::namedWindow
void namedWindow(const String &winname, int flags=WINDOW_AUTOSIZE)
Creates a window.
cv::Scalar_< double >
cv::quality::quality_utils::scale
void scale(cv::Mat &mat, const cv::Mat &range, const T min, const T max)
Definition: quality_utils.hpp:90
cv::Error::StsError
unknown /unspecified error
Definition: base.hpp:71
cv::Size
Size2i Size
Definition: types.hpp:347
cv::line
void line(InputOutputArray img, Point pt1, Point pt2, const Scalar &color, int thickness=1, int lineType=LINE_8, int shift=0)
Draws a line segment connecting two points.
CV_Error
#define CV_Error(code, msg)
Call the error handler.
Definition: base.hpp:320
cv::imshow
void imshow(const String &winname, InputArray mat)
Displays an image in the specified window.
cv::minMaxLoc
void minMaxLoc(InputArray src, double *minVal, double *maxVal=0, Point *minLoc=0, Point *maxLoc=0, InputArray mask=noArray())
Finds the global minimum and maximum in an array.
cv::getTickFrequency
double getTickFrequency()
Returns the number of ticks per second.
cv::Scalar
Scalar_< double > Scalar
Definition: types.hpp:669
cv::putText
void putText(InputOutputArray img, const String &text, Point org, int fontFace, double fontScale, Scalar color, int thickness=1, int lineType=LINE_8, bool bottomLeftOrigin=false)
Draws a text string.
cv::Point
Point2i Point
Definition: types.hpp:194
CV_Assert
#define CV_Assert(expr)
Checks a condition at runtime and throws exception if it fails.
Definition: base.hpp:342
cv::Mat
n-dimensional dense array class
Definition: mat.hpp:791
cv::dnn::blobFromImage
Mat blobFromImage(InputArray image, double scalefactor=1.0, const Size &size=Size(), const Scalar &mean=Scalar(), bool swapRB=false, bool crop=false, int ddepth=CV_32F)
Creates 4-dimensional blob from image. Optionally resizes and crops image from center,...
cv::CommandLineParser::about
void about(const String &message)
Set the about message.
cv::CommandLineParser
Designed for command line parsing.
Definition: utility.hpp:831
cv
"black box" representation of the file storage associated with a file on disk.
Definition: affine.hpp:51
imgproc.hpp
cv::CommandLineParser::printErrors
void printErrors() const
Print list of errors occurred.
cv::CommandLineParser::printMessage
void printMessage() const
Print help message.
cv::mean
Scalar mean(InputArray src, InputArray mask=noArray())
Calculates an average (mean) of array elements.
cv::CommandLineParser::has
bool has(const String &name) const
Check if field was provided in the command line.
cv::VideoCapture::open
virtual bool open(const String &filename, int apiPreference=CAP_ANY)
Opens a video file or a capturing device or an IP video stream for video capturing.