Semantic segmentation sample.

modules/core/include/opencv2/core.hpp

@@ -3159,7 +3159,7 @@ protected:
 
 struct Param {
     enum { INT=0, BOOLEAN=1, REAL=2, STRING=3, MAT=4, MAT_VECTOR=5, ALGORITHM=6, FLOAT=7,
-           UNSIGNED_INT=8, UINT64=9, UCHAR=11 };
+           UNSIGNED_INT=8, UINT64=9, UCHAR=11, SCALAR=12 };
 };
 
 
@@ -3252,6 +3252,14 @@ template<> struct ParamType<uchar>
     enum { type = Param::UCHAR };
 };
 
+template<> struct ParamType<Scalar>
+{
+    typedef const Scalar& const_param_type;
+    typedef Scalar member_type;
+
+    enum { type = Param::SCALAR };
+};
+
 //! @} core_basic
 
 } //namespace cv

modules/core/src/command_line_parser.cpp

@@ -104,6 +104,12 @@ static void from_str(const String& str, int type, void* dst)
         ss >> *(double*)dst;
     else if( type == Param::STRING )
         *(String*)dst = str;
+    else if( type == Param::SCALAR)
+    {
+        Scalar& scalar = *(Scalar*)dst;
+        for (int i = 0; i < 4 && !ss.eof(); ++i)
+            ss >> scalar[i];
+    }
     else
         CV_Error(Error::StsBadArg, "unknown/unsupported parameter type");
 

samples/data/dnn/enet-classes.txt

@@ -0,0 +1,20 @@
+Unlabeled
+Road
+Sidewalk
+Building
+Wall
+Fence
+Pole
+TrafficLight
+TrafficSign
+Vegetation
+Terrain
+Sky
+Person
+Rider
+Car
+Truck
+Bus
+Train
+Motorcycle
+Bicycle

samples/dnn/README.md

@@ -20,7 +20,14 @@
 | GoogLeNet | `1.0` | `224x224` | `104 117 123` | BGR |
 | [SqueezeNet](https://github.com/DeepScale/SqueezeNet) | `1.0` | `227x227` | `0 0 0` | BGR |
 
+### Semantic segmentation
+|    Model | Scale |   Size WxH|   Mean subtraction | Channels order |
+|---------------|-------|-----------|--------------------|-------|
+| [ENet](https://github.com/e-lab/ENet-training) | `0.00392 (1/255)` | `1024x512` | `0 0 0` | RGB |
+| FCN8s | `1.0` | `500x500` | `0 0 0` | BGR |
+
 ## References
 * [Models downloading script](https://github.com/opencv/opencv_extra/blob/master/testdata/dnn/download_models.py)
 * [Configuration files adopted for OpenCV](https://github.com/opencv/opencv_extra/tree/master/testdata/dnn)
 * [How to import models from TensorFlow Object Detection API](https://github.com/opencv/opencv/wiki/TensorFlow-Object-Detection-API)
+* [Names of classes from different datasets](https://github.com/opencv/opencv/tree/master/samples/data/dnn)

samples/dnn/classification.cpp

@@ -1,5 +1,4 @@
 #include <fstream>
-#include <iostream>
 #include <sstream>
 
 #include <opencv2/dnn.hpp>
@@ -17,17 +16,17 @@ const char* keys =
     "{ 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. }"
     "{ mean        | | Preprocess input image by subtracting mean values. Mean values should be in BGR order and delimited by spaces. }"
-    "{ scale       |  1 | Preprocess input image by multiplying on a scale factor. }"
+    "{ scale       | 1 | Preprocess input image by multiplying on a scale factor. }"
-    "{ width       | -1 | Preprocess input image by resizing to a specific width. }"
+    "{ width       |   | Preprocess input image by resizing to a specific width. }"
-    "{ height      | -1 | Preprocess input image by resizing to a specific height. }"
+    "{ height      |   | Preprocess input image by resizing to a specific height. }"
-    "{ rgb         |    | Indicate that model works with RGB input images instead BGR ones. }"
+    "{ rgb         |   | Indicate that model works with RGB input images instead BGR ones. }"
-    "{ backend     |  0 | Choose one of computation backends: "
+    "{ backend     | 0 | Choose one of computation backends: "
-                         "0: default C++ backend, "
+                        "0: default C++ backend, "
-                         "1: Halide language (http://halide-lang.org/), "
+                        "1: Halide language (http://halide-lang.org/), "
-                         "2: Intel's Deep Learning Inference Engine (https://software.seek.intel.com/deep-learning-deployment)}"
+                        "2: Intel's Deep Learning Inference Engine (https://software.seek.intel.com/deep-learning-deployment)}"
-    "{ target      |  0 | Choose one of target computation devices: "
+    "{ target      | 0 | Choose one of target computation devices: "
-                         "0: CPU target (by default),"
+                        "0: CPU target (by default),"
-                         "1: OpenCL }";
+                        "1: OpenCL }";
 
 using namespace cv;
 using namespace dnn;
@@ -45,7 +44,9 @@ int main(int argc, char** argv)
     }
 
     float scale = parser.get<float>("scale");
+    Scalar mean = parser.get<Scalar>("mean");
     bool swapRB = parser.get<bool>("rgb");
+    CV_Assert(parser.has("width"), parser.has("height"));
     int inpWidth = parser.get<int>("width");
     int inpHeight = parser.get<int>("height");
     String model = parser.get<String>("model");
@@ -54,19 +55,6 @@ int main(int argc, char** argv)
     int backendId = parser.get<int>("backend");
     int targetId = parser.get<int>("target");
 
-    // Parse mean values.
-    Scalar mean;
-    if (parser.has("mean"))
-    {
-        std::istringstream meanStr(parser.get<String>("mean"));
-        std::vector<float> meanValues;
-        float val;
-        while (meanStr >> val)
-            meanValues.push_back(val);
-        CV_Assert(meanValues.size() == 3);
-        mean = Scalar(meanValues[0], meanValues[1], meanValues[2]);
-    }
-
     // Open file with classes names.
     if (parser.has("classes"))
     {

samples/dnn/fcn_semsegm.cpp

@@ -1,138 +0,0 @@
-#include <opencv2/dnn.hpp>
-#include <opencv2/imgproc.hpp>
-#include <opencv2/highgui.hpp>
-using namespace cv;
-using namespace cv::dnn;
-
-#include <fstream>
-#include <iostream>
-#include <cstdlib>
-using namespace std;
-
-static const string fcnType = "fcn8s";
-
-static vector<cv::Vec3b> readColors(const string &filename = "pascal-classes.txt")
-{
-    vector<cv::Vec3b> colors;
-
-    ifstream fp(filename.c_str());
-    if (!fp.is_open())
-    {
-        cerr << "File with colors not found: " << filename << endl;
-        exit(-1);
-    }
-
-    string line;
-    while (!fp.eof())
-    {
-        getline(fp, line);
-        if (line.length())
-        {
-            stringstream ss(line);
-
-            string name; ss >> name;
-            int temp;
-            cv::Vec3b color;
-            ss >> temp; color[0] = (uchar)temp;
-            ss >> temp; color[1] = (uchar)temp;
-            ss >> temp; color[2] = (uchar)temp;
-            colors.push_back(color);
-        }
-    }
-
-    fp.close();
-    return colors;
-}
-
-static void colorizeSegmentation(const Mat &score, const vector<cv::Vec3b> &colors, cv::Mat &segm)
-{
-    const int rows = score.size[2];
-    const int cols = score.size[3];
-    const int chns = score.size[1];
-
-    cv::Mat maxCl=cv::Mat::zeros(rows, cols, CV_8UC1);
-    cv::Mat maxVal(rows, cols, CV_32FC1, cv::Scalar(-FLT_MAX));
-    for (int ch = 0; ch < chns; ch++)
-    {
-        for (int row = 0; row < rows; row++)
-        {
-            const float *ptrScore = score.ptr<float>(0, ch, row);
-            uchar *ptrMaxCl = maxCl.ptr<uchar>(row);
-            float *ptrMaxVal = maxVal.ptr<float>(row);
-            for (int col = 0; col < cols; col++)
-            {
-                if (ptrScore[col] > ptrMaxVal[col])
-                {
-                    ptrMaxVal[col] = ptrScore[col];
-                    ptrMaxCl[col] = (uchar)ch;
-                }
-            }
-        }
-    }
-
-    segm.create(rows, cols, CV_8UC3);
-    for (int row = 0; row < rows; row++)
-    {
-        const uchar *ptrMaxCl = maxCl.ptr<uchar>(row);
-        cv::Vec3b *ptrSegm = segm.ptr<cv::Vec3b>(row);
-        for (int col = 0; col < cols; col++)
-        {
-            ptrSegm[col] = colors[ptrMaxCl[col]];
-        }
-    }
-
-}
-
-int main(int argc, char **argv)
-{
-    String modelTxt = fcnType + "-heavy-pascal.prototxt";
-    String modelBin = fcnType + "-heavy-pascal.caffemodel";
-    String imageFile = (argc > 1) ? argv[1] : "rgb.jpg";
-
-    vector<cv::Vec3b> colors = readColors();
-
-    //! [Initialize network]
-    dnn::Net net = readNetFromCaffe(modelTxt, modelBin);
-    //! [Initialize network]
-
-    if (net.empty())
-    {
-        cerr << "Can't load network by using the following files: " << endl;
-        cerr << "prototxt:   " << modelTxt << endl;
-        cerr << "caffemodel: " << modelBin << endl;
-        cerr << fcnType << "-heavy-pascal.caffemodel can be downloaded here:" << endl;
-        cerr << "http://dl.caffe.berkeleyvision.org/" << fcnType << "-heavy-pascal.caffemodel" << endl;
-        exit(-1);
-    }
-
-    //! [Prepare blob]
-    Mat img = imread(imageFile);
-    if (img.empty())
-    {
-        cerr << "Can't read image from the file: " << imageFile << endl;
-        exit(-1);
-    }
-
-    resize(img, img, Size(500, 500), 0, 0, INTER_LINEAR_EXACT);       //FCN accepts 500x500 BGR-images
-    Mat inputBlob = blobFromImage(img, 1, Size(), Scalar(), false);   //Convert Mat to batch of images
-    //! [Prepare blob]
-
-    //! [Set input blob]
-    net.setInput(inputBlob, "data");        //set the network input
-    //! [Set input blob]
-
-    //! [Make forward pass]
-    double t = (double)cv::getTickCount();
-    Mat score = net.forward("score");                          //compute output
-    t = (double)cv::getTickCount() - t;
-    printf("processing time: %.1fms\n", t*1000./getTickFrequency());
-    //! [Make forward pass]
-
-    Mat colorize;
-    colorizeSegmentation(score, colors, colorize);
-    Mat show;
-    addWeighted(img, 0.4, colorize, 0.6, 0.0, show);
-    imshow("show", show);
-    waitKey(0);
-    return 0;
-} //main

samples/dnn/object_detection.cpp

@@ -1,5 +1,4 @@
 #include <fstream>
-#include <iostream>
 #include <sstream>
 
 #include <opencv2/dnn.hpp>
@@ -54,23 +53,11 @@ int main(int argc, char** argv)
 
     confThreshold = parser.get<float>("thr");
     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");
 
-    // Parse mean values.
-    Scalar mean;
-    if (parser.has("mean"))
-    {
-        std::istringstream meanStr(parser.get<String>("mean"));
-        std::vector<float> meanValues;
-        float val;
-        while (meanStr >> val)
-            meanValues.push_back(val);
-        CV_Assert(meanValues.size() == 3);
-        mean = Scalar(meanValues[0], meanValues[1], meanValues[2]);
-    }
-
     // Open file with classes names.
     if (parser.has("classes"))
     {

samples/dnn/segmentation.cpp

@@ -0,0 +1,237 @@
+#include <fstream>
+#include <sstream>
+
+#include <opencv2/dnn.hpp>
+#include <opencv2/imgproc.hpp>
+#include <opencv2/highgui.hpp>
+
+const char* keys =
+    "{ help  h     | | Print help message. }"
+    "{ input i     | | Path to input image or video file. Skip this argument to capture frames from a camera.}"
+    "{ model m     | | Path to a binary file of model contains trained weights. "
+                      "It could be a file with extensions .caffemodel (Caffe), "
+                      ".pb (TensorFlow), .t7 or .net (Torch), .weights (Darknet) }"
+    "{ config c    | | Path to a text file of model contains network configuration. "
+                      "It could be a file with extensions .prototxt (Caffe), .pbtxt (TensorFlow), .cfg (Darknet) }"
+    "{ 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. }"
+    "{ colors      | | Optional path to a text file with colors for an every class. "
+                      "An every color is represented with three values from 0 to 255 in BGR channels order. }"
+    "{ mean        | | Preprocess input image by subtracting mean values. Mean values should be in BGR order and delimited by spaces. }"
+    "{ scale       | 1 | Preprocess input image by multiplying on a scale factor. }"
+    "{ width       |   | Preprocess input image by resizing to a specific width. }"
+    "{ height      |   | Preprocess input image by resizing to a specific height. }"
+    "{ rgb         |   | Indicate that model works with RGB input images instead BGR ones. }"
+    "{ backend     | 0 | Choose one of computation backends: "
+                        "0: default C++ backend, "
+                        "1: Halide language (http://halide-lang.org/), "
+                        "2: Intel's Deep Learning Inference Engine (https://software.seek.intel.com/deep-learning-deployment)}"
+    "{ target      | 0 | Choose one of target computation devices: "
+                        "0: CPU target (by default),"
+                        "1: OpenCL }";
+
+using namespace cv;
+using namespace dnn;
+
+std::vector<std::string> classes;
+std::vector<Vec3b> colors;
+
+void showLegend();
+
+void colorizeSegmentation(const Mat &score, Mat &segm);
+
+int main(int argc, char** argv)
+{
+    CommandLineParser parser(argc, argv, keys);
+    parser.about("Use this script to run semantic segmentation 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");
+    CV_Assert(parser.has("width"), parser.has("height"));
+    int inpWidth = parser.get<int>("width");
+    int inpHeight = parser.get<int>("height");
+    String model = parser.get<String>("model");
+    String config = 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);
+        }
+    }
+
+    // Open file with colors.
+    if (parser.has("colors"))
+    {
+        std::string file = parser.get<String>("colors");
+        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))
+        {
+            std::istringstream colorStr(line.c_str());
+
+            Vec3b color;
+            for (int i = 0; i < 3 && !colorStr.eof(); ++i)
+                colorStr >> color[i];
+            colors.push_back(color);
+        }
+    }
+
+    CV_Assert(parser.has("model"));
+    //! [Read and initialize network]
+    Net net = readNet(model, config, framework);
+    net.setPreferableBackend(backendId);
+    net.setPreferableTarget(targetId);
+    //! [Read and initialize network]
+
+    // Create a window
+    static const std::string kWinName = "Deep learning semantic segmentation in OpenCV";
+    namedWindow(kWinName, WINDOW_NORMAL);
+
+    //! [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);
+    //! [Open a video file or an image file or a camera stream]
+
+    // Process frames.
+    Mat frame, blob;
+    while (waitKey(1) < 0)
+    {
+        cap >> frame;
+        if (frame.empty())
+        {
+            waitKey();
+            break;
+        }
+
+        //! [Create a 4D blob from a frame]
+        blobFromImage(frame, blob, scale, Size(inpWidth, inpHeight), mean, swapRB, false);
+        //! [Create a 4D blob from a frame]
+
+        //! [Set input blob]
+        net.setInput(blob);
+        //! [Set input blob]
+        //! [Make forward pass]
+        Mat score = net.forward();
+        //! [Make forward pass]
+
+        Mat segm;
+        colorizeSegmentation(score, segm);
+
+        resize(segm, segm, frame.size(), 0, 0, INTER_NEAREST);
+        addWeighted(frame, 0.1, segm, 0.9, 0.0, frame);
+
+        // 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));
+
+        imshow(kWinName, frame);
+        if (!classes.empty())
+            showLegend();
+    }
+    return 0;
+}
+
+void colorizeSegmentation(const Mat &score, Mat &segm)
+{
+    const int rows = score.size[2];
+    const int cols = score.size[3];
+    const int chns = score.size[1];
+
+    if (colors.empty())
+    {
+        // Generate colors.
+        colors.push_back(Vec3b());
+        for (int i = 1; i < chns; ++i)
+        {
+            Vec3b color;
+            for (int j = 0; j < 3; ++j)
+                color[j] = (colors[i - 1][j] + rand() % 256) / 2;
+            colors.push_back(color);
+        }
+    }
+    else if (chns != (int)colors.size())
+    {
+        CV_Error(Error::StsError, format("Number of output classes does not match "
+                                         "number of colors (%d != %d)", chns, colors.size()));
+    }
+
+    Mat maxCl = Mat::zeros(rows, cols, CV_8UC1);
+    Mat maxVal(rows, cols, CV_32FC1, score.data);
+    for (int ch = 1; ch < chns; ch++)
+    {
+        for (int row = 0; row < rows; row++)
+        {
+            const float *ptrScore = score.ptr<float>(0, ch, row);
+            uint8_t *ptrMaxCl = maxCl.ptr<uint8_t>(row);
+            float *ptrMaxVal = maxVal.ptr<float>(row);
+            for (int col = 0; col < cols; col++)
+            {
+                if (ptrScore[col] > ptrMaxVal[col])
+                {
+                    ptrMaxVal[col] = ptrScore[col];
+                    ptrMaxCl[col] = (uchar)ch;
+                }
+            }
+        }
+    }
+
+    segm.create(rows, cols, CV_8UC3);
+    for (int row = 0; row < rows; row++)
+    {
+        const uchar *ptrMaxCl = maxCl.ptr<uchar>(row);
+        Vec3b *ptrSegm = segm.ptr<Vec3b>(row);
+        for (int col = 0; col < cols; col++)
+        {
+            ptrSegm[col] = colors[ptrMaxCl[col]];
+        }
+    }
+}
+
+void showLegend()
+{
+    static const int kBlockHeight = 30;
+    static Mat legend;
+    if (legend.empty())
+    {
+        const int numClasses = (int)classes.size();
+        if ((int)colors.size() != numClasses)
+        {
+            CV_Error(Error::StsError, format("Number of output classes does not match "
+                                             "number of labels (%d != %d)", colors.size(), classes.size()));
+        }
+        legend.create(kBlockHeight * numClasses, 200, CV_8UC3);
+        for (int i = 0; i < numClasses; i++)
+        {
+            Mat block = legend.rowRange(i * kBlockHeight, (i + 1) * kBlockHeight);
+            block.setTo(colors[i]);
+            putText(block, classes[i], Point(0, kBlockHeight / 2), FONT_HERSHEY_SIMPLEX, 0.5, Vec3b(255, 255, 255));
+        }
+        namedWindow("Legend", WINDOW_NORMAL);
+        imshow("Legend", legend);
+    }
+}

samples/dnn/segmentation.py

@@ -0,0 +1,125 @@
+import cv2 as cv
+import argparse
+import numpy as np
+import sys
+
+backends = (cv.dnn.DNN_BACKEND_DEFAULT, cv.dnn.DNN_BACKEND_HALIDE, cv.dnn.DNN_BACKEND_INFERENCE_ENGINE)
+targets = (cv.dnn.DNN_TARGET_CPU, cv.dnn.DNN_TARGET_OPENCL)
+
+parser = argparse.ArgumentParser(description='Use this script to run semantic segmentation deep learning networks using OpenCV.')
+parser.add_argument('--input', help='Path to input image or video file. Skip this argument to capture frames from a camera.')
+parser.add_argument('--model', required=True,
+                    help='Path to a binary file of model contains trained weights. '
+                         'It could be a file with extensions .caffemodel (Caffe), '
+                         '.pb (TensorFlow), .t7 or .net (Torch), .weights (Darknet)')
+parser.add_argument('--config',
+                    help='Path to a text file of model contains network configuration. '
+                         'It could be a file with extensions .prototxt (Caffe), .pbtxt (TensorFlow), .cfg (Darknet)')
+parser.add_argument('--framework', choices=['caffe', 'tensorflow', 'torch', 'darknet'],
+                    help='Optional name of an origin framework of the model. '
+                         'Detect it automatically if it does not set.')
+parser.add_argument('--classes', help='Optional path to a text file with names of classes.')
+parser.add_argument('--colors', help='Optional path to a text file with colors for an every class. '
+                                     'An every color is represented with three values from 0 to 255 in BGR channels order.')
+parser.add_argument('--mean', nargs='+', type=float, default=[0, 0, 0],
+                    help='Preprocess input image by subtracting mean values. '
+                         'Mean values should be in BGR order.')
+parser.add_argument('--scale', type=float, default=1.0,
+                    help='Preprocess input image by multiplying on a scale factor.')
+parser.add_argument('--width', type=int, required=True,
+                    help='Preprocess input image by resizing to a specific width.')
+parser.add_argument('--height', type=int, required=True,
+                    help='Preprocess input image by resizing to a specific height.')
+parser.add_argument('--rgb', action='store_true',
+                    help='Indicate that model works with RGB input images instead BGR ones.')
+parser.add_argument('--backend', choices=backends, default=cv.dnn.DNN_BACKEND_DEFAULT, type=int,
+                    help="Choose one of computation backends: "
+                         "%d: default C++ backend, "
+                         "%d: Halide language (http://halide-lang.org/), "
+                         "%d: Intel's Deep Learning Inference Engine (https://software.seek.intel.com/deep-learning-deployment)" % backends)
+parser.add_argument('--target', choices=targets, default=cv.dnn.DNN_TARGET_CPU, type=int,
+                    help='Choose one of target computation devices: '
+                         '%d: CPU target (by default), '
+                         '%d: OpenCL' % targets)
+args = parser.parse_args()
+
+np.random.seed(324)
+
+# Load names of classes
+classes = None
+if args.classes:
+    with open(args.classes, 'rt') as f:
+        classes = f.read().rstrip('\n').split('\n')
+
+# Load colors
+colors = None
+if args.colors:
+    with open(args.colors, 'rt') as f:
+        colors = [np.array(color.split(' '), np.uint8) for color in f.read().rstrip('\n').split('\n')]
+
+legend = None
+def showLegend(classes):
+    global legend
+    if not classes is None and legend is None:
+        blockHeight = 30
+        assert(len(classes) == len(colors))
+
+        legend = np.zeros((blockHeight * len(colors), 200, 3), np.uint8)
+        for i in range(len(classes)):
+            block = legend[i * blockHeight:(i + 1) * blockHeight]
+            block[:,:] = colors[i]
+            cv.putText(block, classes[i], (0, blockHeight/2), cv.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255))
+
+        cv.namedWindow('Legend', cv.WINDOW_NORMAL)
+        cv.imshow('Legend', legend)
+        classes = None
+
+# Load a network
+net = cv.dnn.readNet(args.model, args.config, args.framework)
+net.setPreferableBackend(args.backend)
+net.setPreferableTarget(args.target)
+
+winName = 'Deep learning image classification in OpenCV'
+cv.namedWindow(winName, cv.WINDOW_NORMAL)
+
+cap = cv.VideoCapture(args.input if args.input else 0)
+legend = None
+while cv.waitKey(1) < 0:
+    hasFrame, frame = cap.read()
+    if not hasFrame:
+        cv.waitKey()
+        break
+
+    # Create a 4D blob from a frame.
+    blob = cv.dnn.blobFromImage(frame, args.scale, (args.width, args.height), args.mean, args.rgb, crop=False)
+
+    # Run a model
+    net.setInput(blob)
+    score = net.forward()
+
+    numClasses = score.shape[1]
+    height = score.shape[2]
+    width = score.shape[3]
+
+    # Draw segmentation
+    if not colors:
+        # Generate colors
+        colors = [np.array([0, 0, 0], np.uint8)]
+        for i in range(1, numClasses):
+            colors.append((colors[i - 1] + np.random.randint(0, 256, [3], np.uint8)) / 2)
+
+    classIds = np.argmax(score[0], axis=0)
+    segm = np.stack([colors[idx] for idx in classIds.flatten()])
+    segm = segm.reshape(height, width, 3)
+
+    segm = cv.resize(segm, (frame.shape[1], frame.shape[0]), interpolation=cv.INTER_NEAREST)
+    frame = (0.1 * frame + 0.9 * segm).astype(np.uint8)
+
+    # Put efficiency information.
+    t, _ = net.getPerfProfile()
+    label = 'Inference time: %.2f ms' % (t * 1000.0 / cv.getTickFrequency())
+    cv.putText(frame, label, (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0))
+
+    showLegend(classes)
+
+    cv.imshow(winName, frame)

samples/dnn/torch_enet.cpp

@@ -1,175 +0,0 @@
-/*
-Sample of using OpenCV dnn module with Torch ENet model.
-*/
-
-#include <opencv2/dnn.hpp>
-#include <opencv2/imgproc.hpp>
-#include <opencv2/highgui.hpp>
-using namespace cv;
-using namespace cv::dnn;
-
-#include <fstream>
-#include <iostream>
-#include <cstdlib>
-#include <sstream>
-using namespace std;
-
-const String keys =
-        "{help h    || Sample app for loading ENet Torch model. "
-                       "The model and class names list can be downloaded here: "
-                       "https://www.dropbox.com/sh/dywzk3gyb12hpe5/AAD5YkUa8XgMpHs2gCRgmCVCa }"
-        "{model m   || path to Torch .net model file (model_best.net) }"
-        "{image i   || path to image file }"
-        "{result r  || path to save output blob (optional, binary format, NCHW order) }"
-        "{show s    || whether to show all output channels or not}"
-        "{o_blob    || output blob's name. If empty, last blob's name in net is used}";
-
-static const int kNumClasses = 20;
-
-static const String classes[] = {
-    "Background", "Road", "Sidewalk", "Building", "Wall", "Fence", "Pole",
-    "TrafficLight", "TrafficSign", "Vegetation", "Terrain", "Sky", "Person",
-    "Rider", "Car", "Truck", "Bus", "Train", "Motorcycle", "Bicycle"
-};
-
-static const Vec3b colors[] = {
-    Vec3b(0, 0, 0), Vec3b(244, 126, 205), Vec3b(254, 83, 132), Vec3b(192, 200, 189),
-    Vec3b(50, 56, 251), Vec3b(65, 199, 228), Vec3b(240, 178, 193), Vec3b(201, 67, 188),
-    Vec3b(85, 32, 33), Vec3b(116, 25, 18), Vec3b(162, 33, 72), Vec3b(101, 150, 210),
-    Vec3b(237, 19, 16), Vec3b(149, 197, 72), Vec3b(80, 182, 21), Vec3b(141, 5, 207),
-    Vec3b(189, 156, 39), Vec3b(235, 170, 186), Vec3b(133, 109, 144), Vec3b(231, 160, 96)
-};
-
-static void showLegend();
-
-static void colorizeSegmentation(const Mat &score, Mat &segm);
-
-int main(int argc, char **argv)
-{
-    CommandLineParser parser(argc, argv, keys);
-
-    if (parser.has("help") || argc == 1)
-    {
-        parser.printMessage();
-        return 0;
-    }
-
-    String modelFile = parser.get<String>("model");
-    String imageFile = parser.get<String>("image");
-
-    if (!parser.check())
-    {
-        parser.printErrors();
-        return 0;
-    }
-
-    String resultFile = parser.get<String>("result");
-
-    //! [Read model and initialize network]
-    dnn::Net net = dnn::readNetFromTorch(modelFile);
-
-    //! [Prepare blob]
-    Mat img = imread(imageFile), input;
-    if (img.empty())
-    {
-        std::cerr << "Can't read image from the file: " << imageFile << std::endl;
-        exit(-1);
-    }
-
-    Mat inputBlob = blobFromImage(img, 1./255, Size(1024, 512), Scalar(), true, false);   //Convert Mat to batch of images
-    //! [Prepare blob]
-
-    //! [Set input blob]
-    net.setInput(inputBlob);        //set the network input
-    //! [Set input blob]
-
-    TickMeter tm;
-
-    String oBlob = net.getLayerNames().back();
-    if (!parser.get<String>("o_blob").empty())
-    {
-        oBlob = parser.get<String>("o_blob");
-    }
-
-    //! [Make forward pass]
-    tm.start();
-    Mat result = net.forward(oBlob);
-    tm.stop();
-
-    if (!resultFile.empty()) {
-        CV_Assert(result.isContinuous());
-
-        ofstream fout(resultFile.c_str(), ios::out | ios::binary);
-        fout.write((char*)result.data, result.total() * sizeof(float));
-        fout.close();
-    }
-
-    std::cout << "Output blob: " << result.size[0] << " x " << result.size[1] << " x " << result.size[2] << " x " << result.size[3] << "\n";
-    std::cout << "Inference time, ms: " << tm.getTimeMilli()  << std::endl;
-
-    if (parser.has("show"))
-    {
-        Mat segm, show;
-        colorizeSegmentation(result, segm);
-        showLegend();
-
-        cv::resize(segm, segm, img.size(), 0, 0, cv::INTER_NEAREST);
-        addWeighted(img, 0.1, segm, 0.9, 0.0, show);
-
-        imshow("Result", show);
-        waitKey();
-    }
-    return 0;
-} //main
-
-static void showLegend()
-{
-    static const int kBlockHeight = 30;
-
-    cv::Mat legend(kBlockHeight * kNumClasses, 200, CV_8UC3);
-    for(int i = 0; i < kNumClasses; i++)
-    {
-        cv::Mat block = legend.rowRange(i * kBlockHeight, (i + 1) * kBlockHeight);
-        block.setTo(colors[i]);
-        putText(block, classes[i], Point(0, kBlockHeight / 2), FONT_HERSHEY_SIMPLEX, 0.5, Vec3b(255, 255, 255));
-    }
-    imshow("Legend", legend);
-}
-
-static void colorizeSegmentation(const Mat &score, Mat &segm)
-{
-    const int rows = score.size[2];
-    const int cols = score.size[3];
-    const int chns = score.size[1];
-
-    Mat maxCl = Mat::zeros(rows, cols, CV_8UC1);
-    Mat maxVal(rows, cols, CV_32FC1, score.data);
-    for (int ch = 1; ch < chns; ch++)
-    {
-        for (int row = 0; row < rows; row++)
-        {
-            const float *ptrScore = score.ptr<float>(0, ch, row);
-            uint8_t *ptrMaxCl = maxCl.ptr<uint8_t>(row);
-            float *ptrMaxVal = maxVal.ptr<float>(row);
-            for (int col = 0; col < cols; col++)
-            {
-                if (ptrScore[col] > ptrMaxVal[col])
-                {
-                    ptrMaxVal[col] = ptrScore[col];
-                    ptrMaxCl[col] = (uchar)ch;
-                }
-            }
-        }
-    }
-
-    segm.create(rows, cols, CV_8UC3);
-    for (int row = 0; row < rows; row++)
-    {
-        const uchar *ptrMaxCl = maxCl.ptr<uchar>(row);
-        Vec3b *ptrSegm = segm.ptr<Vec3b>(row);
-        for (int col = 0; col < cols; col++)
-        {
-            ptrSegm[col] = colors[ptrMaxCl[col]];
-        }
-    }
-}