add mobilenet c++ sample

models/image_classification_mobilenet/CMakeLists.txt

@@ -0,0 +1,29 @@
+cmake_minimum_required(VERSION 3.2)
+set(project_name "opencv_zoo_image_classification_mobilenet")
+
+PROJECT (${project_name})
+
+set(OPENCV_VERSION "4.7.0")
+set(OPENCV_INSTALLATION_PATH "" CACHE PATH "Where to look for OpenCV installation")
+find_package(OpenCV ${OPENCV_VERSION} REQUIRED HINTS ${OPENCV_INSTALLATION_PATH})
+# Find OpenCV, you may need to set OpenCV_DIR variable
+# to the absolute path to the directory containing OpenCVConfig.cmake file
+# via the command line or GUI
+
+file(GLOB SourceFile
+    "demo.cpp")
+# If the package has been found, several variables will
+# be set, you can find the full list with descriptions
+# in the OpenCVConfig.cmake file.
+# Print some message showing some of them
+message(STATUS "OpenCV library status:")
+message(STATUS "    config: ${OpenCV_DIR}")
+message(STATUS "    version: ${OpenCV_VERSION}")
+message(STATUS "    libraries: ${OpenCV_LIBS}")
+message(STATUS "    include path: ${OpenCV_INCLUDE_DIRS}")
+
+# Declare the executable target built from your sources
+add_executable(${project_name} ${SourceFile})
+
+# Link your application with OpenCV libraries
+target_link_libraries(${project_name} PRIVATE ${OpenCV_LIBS})

models/image_classification_mobilenet/README.md

@@ -17,6 +17,8 @@ Results of accuracy evaluation with [tools/eval](../../tools/eval).
 
 ## Demo
 
+### Python
+
 Run the following command to try the demo:
 
 ```shell
@@ -29,6 +31,24 @@ python demo.py --input /path/to/image --model v2
 python demo.py --help
 ```
 
+### C++
+
+Install latest OpenCV and CMake >= 3.24.0 to get started with:
+
+```shell
+# A typical and default installation path of OpenCV is /usr/local
+cmake -B build -D OPENCV_INSTALLATION_PATH=/path/to/opencv/installation .
+cmake --build build
+
+# detect on camera input
+./build/opencv_zoo_image_classification_mobilenet
+# detect on an image
+./build/opencv_zoo_image_classification_mobilenet -m=/path/to/model -i=/path/to/image -v
+# get help messages
+./build/opencv_zoo_image_classification_mobilenet -h
+```
+
+
 ## License
 
 All files in this directory are licensed under [Apache 2.0 License](./LICENSE).

models/image_classification_mobilenet/demo.cpp

@@ -0,0 +1,133 @@
+#include <vector>
+#include <string>
+#include <utility>
+
+#include <opencv2/opencv.hpp>
+#include "labelsimagenet1k.h"
+
+using namespace std;
+using namespace cv;
+using namespace dnn;
+
+vector< pair<dnn::Backend, dnn::Target> > backendTargetPairs = {
+        std::make_pair<dnn::Backend, dnn::Target>(dnn::DNN_BACKEND_OPENCV, dnn::DNN_TARGET_CPU),
+        std::make_pair<dnn::Backend, dnn::Target>(dnn::DNN_BACKEND_CUDA, dnn::DNN_TARGET_CUDA),
+        std::make_pair<dnn::Backend, dnn::Target>(dnn::DNN_BACKEND_CUDA, dnn::DNN_TARGET_CUDA_FP16),
+        std::make_pair<dnn::Backend, dnn::Target>(dnn::DNN_BACKEND_TIMVX, dnn::DNN_TARGET_NPU),
+        std::make_pair<dnn::Backend, dnn::Target>(dnn::DNN_BACKEND_CANN, dnn::DNN_TARGET_NPU) };
+
+
+std::string keys =
+"{ help  h          |                                               | Print help message. }"
+"{ model m          | image_classification_mobilenetv1_2022apr.onnx | Usage: Set model type, defaults to image_classification_mobilenetv1_2022apr.onnx (v1) }"
+"{ 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.}"
+"{ rgb              | true                                          | swap R and B plane.}"
+"{ crop             | false                                         | Preprocess input image by center cropping.}"
+"{ vis v            | true                                          | Usage: Specify to open a new window to show results.}"
+"{ backend bt       | 0                                             | Choose one of computation backends: "
+"0: (default) OpenCV implementation + CPU, "
+"1: CUDA + GPU (CUDA), "
+"2: CUDA + GPU (CUDA FP16), "
+"3: TIM-VX + NPU, "
+"4: CANN + NPU}";
+
+
+int main(int argc, char** argv)
+{
+    CommandLineParser parser(argc, argv, keys);
+
+    parser.about("Use this script to run classification deep learning networks in opencv Zoo using OpenCV.");
+    if (parser.has("help"))
+    {
+        parser.printMessage();
+        return 0;
+    }
+
+    int rszWidth = parser.get<int>("initial_width");
+    int rszHeight = parser.get<int>("initial_height");
+    bool swapRB = parser.get<bool>("rgb");
+    bool crop = parser.get<bool>("crop");
+    bool vis = parser.get<bool>("vis");
+    String model = parser.get<String>("model");
+    int backendTargetid = parser.get<int>("backend");
+
+    if (model.empty())
+    {
+        CV_Error(Error::StsError, "Model file " + model + " not found");
+    }
+    vector<string> labels = getLabelsImagenet1k();
+
+    Net net = readNet(samples::findFile(model));
+    net.setPreferableBackend(backendTargetPairs[backendTargetid].first);
+    net.setPreferableTarget(backendTargetPairs[backendTargetid].second);
+    //! [Open a video file or an image file or a camera stream]
+    VideoCapture cap;
+    if (parser.has("input"))
+        cap.open(samples::findFile(parser.get<String>("input")));
+    else
+        cap.open(0);
+    if (!cap.isOpened())
+        CV_Error(Error::StsError, "Cannot opend video or file");
+    Mat frame, blob;
+    static const std::string kWinName = model;
+    int nbInference = 0;
+    while (waitKey(1) < 0)
+    {
+        cap >> frame;
+        if (frame.empty())
+        {
+            cout << "Frame is empty" << endl;
+            waitKey();
+            break;
+        }
+
+        if (rszWidth != 0 && rszHeight != 0)
+        {
+            resize(frame, frame, Size(rszWidth, rszHeight));
+        }
+        Image2BlobParams paramMobilenet;
+        paramMobilenet.datalayout = DNN_LAYOUT_NCHW;
+        paramMobilenet.ddepth = CV_32F;
+        paramMobilenet.mean = Scalar(123.675, 116.28, 103.53);
+        paramMobilenet.scalefactor = Scalar(1 / (255. * 0.229), 1 / (255. * 0.224), 1 / (255. * 0.225));
+        paramMobilenet.size = Size(224, 224);
+        paramMobilenet.swapRB = swapRB;
+        if (crop)
+            paramMobilenet.paddingmode = DNN_PMODE_CROP_CENTER;
+        else
+            paramMobilenet.paddingmode = DNN_PMODE_NULL;
+        //! [Create a 4D blob from a frame]
+        blobFromImageWithParams(frame, blob, paramMobilenet);
+
+        //! [Set input blob]
+        net.setInput(blob);
+        Mat prob = net.forward();
+
+        //! [Get a class with a highest score]
+        Point classIdPoint;
+        double confidence;
+        minMaxLoc(prob.reshape(1, 1), 0, &confidence, 0, &classIdPoint);
+        int classId = classIdPoint.x;
+        std::string label = format("%s: %.4f", (labels.empty() ? format("Class #%d", classId).c_str() :
+            labels[classId].c_str()),
+            confidence);
+        if (vis)
+        {
+            putText(frame, label, Point(0, 55), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
+            imshow(kWinName, frame);
+        }
+        else
+        {
+            cout << label << endl;
+            nbInference++;
+            if (nbInference > 100)
+            {
+                cout << nbInference << " inference made. Demo existing" << endl;
+                break;
+            }
+        }
+    }
+    return 0;
+}