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 +1,117 @@
+#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.}"
+"{ 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");
+ 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(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(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;
+ 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);
+ putText(frame, label, Point(0, 55), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
+ imshow(kWinName, frame);
+ }
+ return 0;
+}