Deep learning with OpenCV DNN module blog

velosomarcus · Apr 9, 2021 · 772d90a · 772d90a
1 parent e4af2fc
commit 772d90a
Show file tree

Hide file tree

Showing 21 changed files with 11,049 additions and 0 deletions.
diff --git a/Deep-Learning-with-OpenCV-DNN-Module/README.md b/Deep-Learning-with-OpenCV-DNN-Module/README.md
@@ -0,0 +1,89 @@
+# Deep Learning with OpenCV's DNN Module
+
+
+
+## Directory Structure
+
+**All the code files and folders follow the following structure.**
+
+```
+├── cpp
+│   ├── classify
+│   │   ├── classify.cpp
+│   │   └── CMakeLists.txt
+│   └── detection
+│       ├── detect_img
+│       │   ├── CMakeLists.txt
+│       │   └── detect_img.cpp
+│       └── detect_vid
+│           ├── CMakeLists.txt
+│           └── detect_vid.cpp
+├── input
+│   ├── classification_classes_ILSVRC2012.txt
+│   ├── DenseNet_121.caffemodel
+│   ├── DenseNet_121.prototxt
+│   ├── frozen_inference_graph.pb
+│   ├── image_1.jpg
+│   ├── image_2.jpg
+│   ├── object_detection_classes_coco.txt
+│   ├── ssd_mobilenet_v2_coco_2018_03_29.pbtxt.txt
+│   └── video_1.mp4
+├── python
+│   ├── classification
+│   │   ├── classify.py
+│   │   └── README.md
+│   └── detection
+│       ├── detect_img.py
+│       ├── detect_vid.py
+│       ├── image_result.jpg
+│       ├── README.md
+│       └── video_result.mp4
+└── README.md
+```
+
+
+
+## Instructions
+
+### Python
+
+To run the code in Python, please go into the `python` folder and execute the Python scripts in each of the respective sub-folders.
+
+### C++
+
+To run the code in C++, please go into the `cpp` folder, then go into each of the respective sub-folders and follow the steps below:
+
+```
+mkdir build
+cd build
+cmake ..
+cmake --build . --config Release
+cd ..
+./build/classify
+```
+
+```
+mkdir build
+cd build
+cmake ..
+cmake --build . --config Release
+cd ..
+./build/detect_img
+```
+
+```
+mkdir build
+cd build
+cmake ..
+cmake --build . --config Release
+cd ..
+./build/detect_vid
+```
+
+
+
+# AI Courses by OpenCV
+
+Want to become an expert in AI? [AI Courses by OpenCV](https://opencv.org/courses/) is a great place to start.
+
+[![img](https://camo.githubusercontent.com/18c5719ef10afe9607af3e87e990068c942ae4cba8bd4d72d21950d6213ea97e/68747470733a2f2f7777772e6c6561726e6f70656e63762e636f6d2f77702d636f6e74656e742f75706c6f6164732f323032302f30342f41492d436f75727365732d42792d4f70656e43562d4769746875622e706e67)](https://opencv.org/courses/)
diff --git a/Deep-Learning-with-OpenCV-DNN-Module/cpp/classify/CMakeLists.txt b/Deep-Learning-with-OpenCV-DNN-Module/cpp/classify/CMakeLists.txt
@@ -0,0 +1,21 @@
+cmake_minimum_required(VERSION 3.0.0)
+project(classify VERSION 0.1.0)
+
+include(CTest)
+enable_testing()
+
+
+find_package(OpenCV REQUIRED)
+find_package(Threads REQUIRED)
+
+add_executable(classify classify.cpp)
+
+set(CPACK_PROJECT_NAME ${PROJECT_NAME})
+set(CPACK_PROJECT_VERSION ${PROJECT_VERSION})
+include(CPack)
+
+set(CMAKE_CXX_STANDARD 11)
+set(CMAKE_CXX__STANDARD_REQUIRED ON)
+
+include_directories(${OpenCV_INCLUDE_DIRS})
+target_link_libraries(classify ${OpenCV_LIBS} ${CMAKE_THREAD_LIBS_INIT})
diff --git a/Deep-Learning-with-OpenCV-DNN-Module/cpp/classify/classify.cpp b/Deep-Learning-with-OpenCV-DNN-Module/cpp/classify/classify.cpp
@@ -0,0 +1,48 @@
+#include <iostream>
+#include <fstream>
+#include <opencv2/opencv.hpp>
+#include <opencv2/dnn.hpp>
+#include <opencv2/dnn/all_layers.hpp>
+
+using namespace std;
+using namespace cv;
+using namespace dnn;
+
+int main(int, char**) {
+    std::vector<std::string> class_names;
+    ifstream ifs(string("../../input/classification_classes_ILSVRC2012.txt").c_str());
+    string line;
+    while (getline(ifs, line))
+    {
+        class_names.push_back(line);
+    }  
+
+    // load the neural network model
+    auto model = readNet("../../input/DenseNet_121.prototxt", 
+                        "../../input/DenseNet_121.caffemodel", 
+                        "Caffe");
+
+    // load the image from disk
+    Mat image = imread("../../input/image_1.jpg");
+    // create blob from image
+    Mat blob = blobFromImage(image, 0.01, Size(224, 224), Scalar(104, 117, 123));
+
+    // set the input blob for the neural network
+    model.setInput(blob);
+    // forward pass the image blob through the model
+    Mat outputs = model.forward();
+
+    Point classIdPoint;
+    double final_prob;
+    minMaxLoc(outputs.reshape(1, 1), 0, &final_prob, 0, &classIdPoint);
+    int label_id = classIdPoint.x;
+
+    // Print predicted class.
+    string out_text = format("%s, %.3f", (class_names[label_id].c_str()), final_prob);
+    // put the class name text on top of the image
+    putText(image, out_text, Point(25, 50), FONT_HERSHEY_SIMPLEX, 1, Scalar(0, 255, 0),
+                2);
+
+    imshow("Image", image);
+    imwrite("result_image.jpg", image);
+}
diff --git a/Deep-Learning-with-OpenCV-DNN-Module/cpp/detection/detect_img/CMakeLists.txt b/Deep-Learning-with-OpenCV-DNN-Module/cpp/detection/detect_img/CMakeLists.txt
@@ -0,0 +1,21 @@
+cmake_minimum_required(VERSION 3.0.0)
+project(detect_img VERSION 0.1.0)
+
+include(CTest)
+enable_testing()
+
+
+find_package(OpenCV REQUIRED)
+find_package(Threads REQUIRED)
+
+add_executable(detect_img detect_img.cpp)
+
+set(CPACK_PROJECT_NAME ${PROJECT_NAME})
+set(CPACK_PROJECT_VERSION ${PROJECT_VERSION})
+include(CPack)
+
+set(CMAKE_CXX_STANDARD 11)
+set(CMAKE_CXX__STANDARD_REQUIRED ON)
+
+include_directories(${OpenCV_INCLUDE_DIRS})
+target_link_libraries(detect_img ${OpenCV_LIBS} ${CMAKE_THREAD_LIBS_INIT})
diff --git a/Deep-Learning-with-OpenCV-DNN-Module/cpp/detection/detect_img/detect_img.cpp b/Deep-Learning-with-OpenCV-DNN-Module/cpp/detection/detect_img/detect_img.cpp
@@ -0,0 +1,60 @@
+#include <iostream>
+#include <fstream>
+#include <opencv2/opencv.hpp>
+#include <opencv2/dnn.hpp>
+#include <opencv2/dnn/all_layers.hpp>
+
+using namespace std;
+using namespace cv;
+using namespace dnn;
+
+
+int main(int, char**) {
+    std::vector<std::string> class_names;
+    ifstream ifs(string("../../../input/object_detection_classes_coco.txt").c_str());
+    string line;
+    while (getline(ifs, line))
+    {
+        class_names.push_back(line);
+    }  
+
+    // load the neural network model
+    auto model = readNet("../../../input/frozen_inference_graph.pb", 
+                        "../../../input/ssd_mobilenet_v2_coco_2018_03_29.pbtxt.txt", 
+                        "TensorFlow");
+
+    // read the image from disk
+    Mat image = imread("../../../input/image_2.jpg");
+    int image_height = image.cols;
+    int image_width = image.rows;
+    //create blob from image
+    Mat blob = blobFromImage(image, 1.0, Size(300, 300), Scalar(127.5, 127.5, 127.5), 
+                            true, false);
+    //create blob from image
+    model.setInput(blob);
+    //forward pass through the model to carry out the detection
+    Mat output = model.forward();
+
+    Mat detectionMat(output.size[2], output.size[3], CV_32F, output.ptr<float>());
+
+    for (int i = 0; i < detectionMat.rows; i++){
+        int class_id = detectionMat.at<float>(i, 1);
+        float confidence = detectionMat.at<float>(i, 2);
+
+        // Check if the detection is of good quality
+        if (confidence > 0.4){
+            int box_x = static_cast<int>(detectionMat.at<float>(i, 3) * image.cols);
+            int box_y = static_cast<int>(detectionMat.at<float>(i, 4) * image.rows);
+            int box_width = static_cast<int>(detectionMat.at<float>(i, 5) * image.cols - box_x);
+            int box_height = static_cast<int>(detectionMat.at<float>(i, 6) * image.rows - box_y);
+            rectangle(image, Point(box_x, box_y), Point(box_x+box_width, box_y+box_height), Scalar(255,255,255), 2);
+            putText(image, class_names[class_id-1].c_str(), Point(box_x, box_y-5), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0,255,255), 1);
+        }
+    }    
+
+    imshow("image", image);
+    imwrite("image_result.jpg", image);
+    waitKey(0);
+    destroyAllWindows();
+
+}
diff --git a/Deep-Learning-with-OpenCV-DNN-Module/cpp/detection/detect_vid/CMakeLists.txt b/Deep-Learning-with-OpenCV-DNN-Module/cpp/detection/detect_vid/CMakeLists.txt
@@ -0,0 +1,21 @@
+cmake_minimum_required(VERSION 3.0.0)
+project(detect_vid VERSION 0.1.0)
+
+include(CTest)
+enable_testing()
+
+
+find_package(OpenCV REQUIRED)
+find_package(Threads REQUIRED)
+
+add_executable(detect_vid detect_vid.cpp)
+
+set(CPACK_PROJECT_NAME ${PROJECT_NAME})
+set(CPACK_PROJECT_VERSION ${PROJECT_VERSION})
+include(CPack)
+
+set(CMAKE_CXX_STANDARD 11)
+set(CMAKE_CXX__STANDARD_REQUIRED ON)
+
+include_directories(${OpenCV_INCLUDE_DIRS})
+target_link_libraries(detect_vid ${OpenCV_LIBS} ${CMAKE_THREAD_LIBS_INIT})
diff --git a/Deep-Learning-with-OpenCV-DNN-Module/cpp/detection/detect_vid/detect_vid.cpp b/Deep-Learning-with-OpenCV-DNN-Module/cpp/detection/detect_vid/detect_vid.cpp
@@ -0,0 +1,76 @@
+#include <iostream>
+#include <fstream>
+#include <opencv2/opencv.hpp>
+#include <opencv2/dnn.hpp>
+#include <opencv2/dnn/all_layers.hpp>
+
+using namespace std;
+using namespace cv;
+using namespace dnn;
+
+
+int main(int, char**) {
+    std::vector<std::string> class_names;
+    ifstream ifs(string("../../../input/object_detection_classes_coco.txt").c_str());
+    string line;
+    while (getline(ifs, line))
+    {
+        class_names.push_back(line);
+    }  
+
+    // load the neural network model
+    auto model = readNet("../../../input/frozen_inference_graph.pb", 
+                        "../../../input/ssd_mobilenet_v2_coco_2018_03_29.pbtxt.txt", 
+                        "TensorFlow");
+
+    // capture the video
+    VideoCapture cap("../../../input/video_1.mp4");
+    // get the video frames' width and height for proper saving of videos
+    int frame_width = static_cast<int>(cap.get(3));
+    int frame_height = static_cast<int>(cap.get(4));
+    // create the `VideoWriter()` object
+    VideoWriter out("video_result.avi", VideoWriter::fourcc('M', 'J', 'P', 'G'), 30, 
+                    Size(frame_width, frame_height));
+
+    while (cap.isOpened()) {
+        Mat image;
+        bool isSuccess = cap.read(image);
+
+        int image_height = image.cols;
+        int image_width = image.rows;
+        //create blob from image
+        Mat blob = blobFromImage(image, 1.0, Size(300, 300), Scalar(127.5, 127.5, 127.5), 
+                                true, false);
+        //create blob from image
+        model.setInput(blob);
+        //forward pass through the model to carry out the detection
+        Mat output = model.forward();
+
+        Mat detectionMat(output.size[2], output.size[3], CV_32F, output.ptr<float>());
+
+        for (int i = 0; i < detectionMat.rows; i++){
+            int class_id = detectionMat.at<float>(i, 1);
+            float confidence = detectionMat.at<float>(i, 2);
+
+            // Check if the detection is of good quality
+            if (confidence > 0.4){
+                int box_x = static_cast<int>(detectionMat.at<float>(i, 3) * image.cols);
+                int box_y = static_cast<int>(detectionMat.at<float>(i, 4) * image.rows);
+                int box_width = static_cast<int>(detectionMat.at<float>(i, 5) * image.cols - box_x);
+                int box_height = static_cast<int>(detectionMat.at<float>(i, 6) * image.rows - box_y);
+                rectangle(image, Point(box_x, box_y), Point(box_x+box_width, box_y+box_height), Scalar(255,255,255), 2);
+                putText(image, class_names[class_id-1].c_str(), Point(box_x, box_y-5), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0,255,255), 1);
+            }
+        }
+
+    //     imshow("image", image);
+        out.write(image);
+        int k = waitKey(10);
+        if (k == 113){
+            break;
+        }
+    }
+
+cap.release();
+destroyAllWindows();
+}
diff --git a/Deep-Learning-with-OpenCV-DNN-Module/input/DenseNet_121.caffemodel b/Deep-Learning-with-OpenCV-DNN-Module/input/DenseNet_121.caffemodel