test10.cpp

test10.cpp

// Sample of using Halide backend in OpenCV deep learning module.
// Based on caffe_googlenet.cpp.

#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
using namespace cv;
using namespace cv::dnn;
using namespace std;

#include <fstream>
#include <iostream>
#include <cstdlib>

int main(int argc, char **argv)
{
    std::string model = "test10.pb";
    std::string imageFile = (argc > 1) ? argv[1] : "1.bmp";

    //! [Read and initialize network]
    Net net = dnn::readNetFromTensorflow(model);
    //! [Read and initialize network]

    //! [Prepare blob]
    Mat img = imread(imageFile);
    if (img.empty())
    {
        std::cerr << "Can't read image from the file: " << imageFile << std::endl;
        exit(-1);
    }
    if (img.channels() != 3)
    {
        std::cerr << "Image " << imageFile << " isn't 3-channel" << std::endl;
        exit(-1);
    }

    resize(img, img, Size(256, 256));
    Mat inputBlob = blobFromImage(img, 1.0, Size(), Scalar(), false);  // Convert Mat to 4-dimensional batch.
    //! [Prepare blob]

    //! [Set input blob]
    net.setInput(inputBlob);                         // Set the network input.
    //! [Set input blob]

    //! [Make forward pass]
    Mat prob = net.forward("dense_2");                  // Compute output.
    //! [Make forward pass]

    // debug code to print out layers
    MatShape ms1 { inputBlob.size[0], inputBlob.size[1] , inputBlob.size[2], inputBlob.size[3] };
    size_t nlayers = net.getLayerNames().size() + 1;        // one off for the hidden input layer
    for (size_t i=0; i<nlayers; i++) {
        Ptr<Layer> lyr = net.getLayer((unsigned)i);
        std::vector<MatShape> in,out;
        net.getLayerShapes(ms1,i,in,out);
        int id = net.getLayerId(lyr->name);
        cout << format("%-3d%-38s %-13s ", id, (i==0?"data":lyr->name.c_str()), (i==0?"Input":lyr->type.c_str()));
        for (auto j:in)  cout << "i" << Mat(j).t() << "  "; // input(s) size
        for (auto j:out) cout << "o" << Mat(j).t() << "  "; // output(s) size
        for (auto b:lyr->blobs) {                           // what the net trains on, e.g. weights and bias
            cout << "b[" << b.size[0];
            for (size_t d=1; d<b.dims; d++) cout << ", " << b.size[d];
            cout << "]  ";
        }
        if (id>=0) {
            cout << "ci ";
            std::vector<Ptr<Layer> > inp = net.getLayerInputs(id);
            for (auto k:inp) cout <<  net.getLayerId(k->name) << " ";
        }
        cout << endl;
    }


    return 0;
} //main