In this tutorial you will learn how to use opencv_dnn module for image classification by using GoogLeNet trained network from Caffe model zoo.
We will demonstrate results of this example on the following picture.
#include <fstream>
#include <sstream>
#include <iostream>
#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.}"
"{ initial_width | 0 | Preprocess input image by initial resizing to a specific width.}"
"{ initial_height | 0 | Preprocess input image by initial resizing to a specific height.}"
"{ std | 0.0 0.0 0.0 | Preprocess input image by dividing on a standard deviation.}"
"{ crop | false | Preprocess input image by center cropping.}"
"{ framework f | | Optional name of an origin framework of the model. Detect it automatically if it does not set. }"
"{ needSoftmax | false | Use Softmax to post-process the output of the net.}"
"{ 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, "
"4: VKCOM, "
"5: CUDA, "
"6: WebNN }"
"{ target | 0 | Choose one of target computation devices: "
"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 dnn;
std::vector<std::string> classes;
int main(int argc, char** argv)
{
const std::string modelName = parser.get<
String>(
"@alias");
const std::string zooFile = parser.get<
String>(
"zoo");
keys += genPreprocArguments(modelName, zooFile);
parser.about("Use this script to run classification deep learning networks using OpenCV.");
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");
bool swapRB = parser.get<bool>("rgb");
bool crop = parser.get<
bool>(
"crop");
int inpWidth = parser.get<int>("width");
int inpHeight = parser.get<int>("height");
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;
if (parser.has("classes"))
{
std::string file = parser.get<
String>(
"classes");
std::ifstream ifs(file.c_str());
if (!ifs.is_open())
while (std::getline(ifs,
line))
{
}
}
if (!parser.check())
{
parser.printErrors();
return 1;
}
Net net =
readNet(model, config, framework);
net.setPreferableBackend(backendId);
net.setPreferableTarget(targetId);
static const std::string kWinName = "Deep learning image classification in OpenCV";
if (parser.has("input"))
else
{
cap >> frame;
if (frame.empty())
{
break;
}
if (rszWidth != 0 && rszHeight != 0)
{
}
if (
std.val[0] != 0.0 &&
std.val[1] != 0.0 &&
std.val[2] != 0.0)
{
}
net.setInput(blob);
int classId;
double confidence;
Mat prob = net.forward();
double t1;
prob = net.forward();
for(int i = 0; i < 200; i++) {
prob = net.forward();
classId = classIdPoint.
x;
}
if (needSoftmax == true)
{
float maxProb = 0.0;
maxProb = *std::max_element(prob.
begin<
float>(), prob.
end<
float>());
cv::exp(prob-maxProb, softmaxProb);
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);
label = format("%s: %.4f", (classes.empty() ? format("Class #%d", classId).c_str() :
classes[classId].c_str()),
confidence);
}
return 0;
}
Designed for command line parsing.
Definition: utility.hpp:818
n-dimensional dense array class
Definition: mat.hpp:811
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.
MatIterator_< _Tp > end()
Returns the matrix iterator and sets it to the after-last matrix element.
MatIterator_< _Tp > begin()
Returns the matrix iterator and sets it to the first matrix element.
_Tp x
x coordinate of the point
Definition: types.hpp:201
a Class to measure passing time.
Definition: utility.hpp:295
void start()
starts counting ticks.
Definition: utility.hpp:304
void stop()
stops counting ticks.
Definition: utility.hpp:310
void reset()
resets internal values.
Definition: utility.hpp:374
double getTimeMilli() const
returns passed time in milliseconds.
Definition: utility.hpp:333
Class for video capturing from video files, image sequences or cameras.
Definition: videoio.hpp:715
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.
Scalar mean(InputArray src, InputArray mask=noArray())
Calculates an average (mean) of array elements.
void exp(InputArray src, OutputArray dst)
Calculates the exponent of every array element.
void divide(InputArray src1, InputArray src2, OutputArray dst, double scale=1, int dtype=-1)
Performs per-element division of two arrays or a scalar by an array.
Scalar sum(InputArray src)
Calculates the sum of array elements.
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.
Point2i Point
Definition: types.hpp:209
std::string String
Definition: cvstd.hpp:152
Size2i Size
Definition: types.hpp:370
Scalar_< double > Scalar
Definition: types.hpp:696
cv::String findFile(const cv::String &relative_path, bool required=true, bool silentMode=false)
Try to find requested data file.
#define CV_Error(code, msg)
Call the error handler.
Definition: base.hpp:320
#define CV_Assert(expr)
Checks a condition at runtime and throws exception if it fails.
Definition: base.hpp:342
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,...
Net readNet(const String &model, const String &config="", const String &framework="")
Read deep learning network represented in one of the supported formats.
@ WINDOW_NORMAL
the user can resize the window (no constraint) / also use to switch a fullscreen window to a normal s...
Definition: highgui.hpp:187
void imshow(const String &winname, InputArray mat)
Displays an image in the specified window.
int waitKey(int delay=0)
Waits for a pressed key.
void namedWindow(const String &winname, int flags=WINDOW_AUTOSIZE)
Creates a window.
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.
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.
@ FONT_HERSHEY_SIMPLEX
normal size sans-serif font
Definition: imgproc.hpp:872
@ StsError
unknown /unspecified error
Definition: base.hpp:71
void scale(cv::Mat &mat, const cv::Mat &range, const T min, const T max)
Definition: quality_utils.hpp:90
"black box" representation of the file storage associated with a file on disk.
Definition: core.hpp:106