ghimiredhikura/imagenet-evaluation-raspberrypi3-4

ilsvrc2012 ImageNet Top-1, Top-5 Accuracy Benchmarking on 10K Validation Images

Hi there 👋

• 🔭 I’m currently working as a Research Professor in Soongsil University, South Korea.
• 👯 I’m looking to collaborate on lightweight deep learning (model compression) based research.

---

Languages and tools 💬

---

---

You can also reach me on 📫

---

imagenet-evaluation-raspberrypi3-4's Issues

opencv_4.1.1 IE, Mobilenet_V2_1.0_224_caffe model, top-1: 62.32%, top-5: 84.04%

we used following script for image classification and to get dump file in 10K imagenet 2012 validation images. In order to get exact result as reported in paper, I think we need to figure out what is missing in this script.

#include <time.h>
#include <sys/time.h>

#include <algorithm>
#include <string>
#include <cstdlib>
#include <stdio.h>
#include "float.h"
#include <cmath>
#include <stdlib.h>
#include <fstream>
#include <sstream>
#include <iostream>
#include <iomanip>
#include <unistd.h>

#include "opencv2/opencv.hpp"
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>

#include <vector>

using namespace cv;
using namespace dnn;
using namespace std;

const char* keys =
	"{ help  h     | | Print help message. }"
	"{ input i     | | Path to input test image file. }"
	"{ model m     | | Path to a binary file of model contains trained weights. }"
	"{ config c    | | Path to a text file of model contains network configuration.}"
	"{ scale       | | scale factor. }"
    "{ mean        | | mean rgb values. }"
    "{ width       | | input width. }"
    "{ height      | | input height. }"
    "{ classes     | | Optional path to a text file with names of classes. }"
	"{ backend     |  0 | Choose one of computation backends: "
						"0: automatically (by default, only this option is available now, to use other backend you have to rebuild opencv), "
						"1: Halide language (http://halide-lang.org/), "
						"2: Intel's Deep Learning Inference Engine (https://software.intel.com/openvino-toolkit), "
						"3: OpenCV implementation }"
	"{ target      | 0 | Choose one of target computation devices: "
						"0: CPU target (by default, only this option is available now, to use other backend you have to rebuild opencv), "
						"1: OpenCL, "
						"2: OpenCL fp16 (half-float precision), "
						"3: VPU }";

double what_time_is_it_now()
{
    struct timeval time;
    if (gettimeofday(&time,NULL)){
        return 0;
    }
    return (double)time.tv_sec + (double)time.tv_usec * .000001;
}

void findAndReplaceAll(std::string & data, std::string toSearch, std::string replaceStr)
{
	// Get the first occurrence
	size_t pos = data.find(toSearch);
 
	// Repeat till end is reached
	while( pos != std::string::npos)
	{
		// Replace this occurrence of Sub String
		data.replace(pos, toSearch.size(), replaceStr);
		// Get the next occurrence from the current position
		pos =data.find(toSearch, pos + replaceStr.size());
	}
}

float get_temp()
{
    remove( "temp.txt" );
    system("/usr/bin/vcgencmd measure_temp >> temp.txt");
    ifstream readFrom("temp.txt");
	std::string line;
	getline(readFrom, line);
    findAndReplaceAll(line, "temp=", "");
    findAndReplaceAll(line, "'C", "");

    return atof(line.c_str());
}

std::string get_file_name_from_path(std::string path_name)
{
    std::string base_filename = path_name.substr(path_name.find_last_of("/\\") + 1);
    std::string::size_type const p(base_filename.find_last_of('.'));
    std::string file_without_extension = base_filename.substr(0, p);
    return file_without_extension;
}

std::vector<std::string> classes;

int main(int argc, char **argv)
{
	CommandLineParser parser(argc, argv, keys);
	parser.about("Use this script to run object detection deep learning networks using OpenCV.");
	if (argc == 1 || parser.has("help"))
	{
		parser.printMessage();
		return 0;
	}

    cout << "OpenCV version : " << CV_VERSION << endl;

	String model = parser.get<String>("model");
	String config = parser.get<String>("config");

	float scale = parser.get<float>("scale");
    Scalar mean = parser.get<Scalar>("mean");

    //cout << scale << mean << endl;

	int backendId = parser.get<int>("backend");
	int targetId = parser.get<int>("target");

	Net net = readNet(model, config);
	net.setPreferableBackend(backendId);
	net.setPreferableTarget(targetId);

	String image_dir = parser.get<String>("input");

    int inpWidth = parser.get<int>("width");
    int inpHeight = parser.get<int>("height");

    // 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);
        }
    }

    // Create a 4D blob from a frame.
    Size inpSize(inpWidth, inpHeight);

    std::vector<cv::String> imagenames;
	cv::glob(image_dir, imagenames);

    // dump predictions in file
    std::string file_without_extension = get_file_name_from_path(model);
    std::string filename = file_without_extension + "_imagenet.txt";
    ofstream myfile(filename.c_str(), std::ios_base::out);

	Mat frame_org, blob;
	for(int i=0; i<imagenames.size(); i++)
    //for(int i=0; i<10; i++)
    {
        if(i%50 == 0 && get_temp() > 55.0) sleep(5);

        frame_org = cv::imread(imagenames[i]);
        imagenames[i] = get_file_name_from_path(imagenames[i]);

        blobFromImage(frame_org, blob, scale, inpSize, Scalar(127.5, 127.5, 127.5), true, false);

        // run a model.
        net.setInput(blob);
        Mat out = net.forward().reshape(1, 1);

        /*Point classIdPoint;
        double confidence;
        minMaxLoc(out, 0, &confidence, 0, &classIdPoint);
        int classId = classIdPoint.x;
        imagenames[i] = get_file_name_from_path(imagenames[i]);
        std::string label = format("%s: %s, %.4f", imagenames[i].c_str(), (classes.empty() ? format("Class #%d", classId).c_str() : classes[classId].c_str()), confidence);
        // print top 1 result
        cout << label << endl;
        */

        myfile << imagenames[i] << " : ";
        float *data = (float*)out.data;
        for (int i = 0; i < out.size().width; i++) {
            myfile << data[i] << " ";
        }
        myfile << endl;

        if((i+1)%100==0) cout << "Completed: " << i+1 << "/" << imagenames.size() << endl;
    }

    myfile.close();

    return 0;
}