windows下实现c++版faster-rcnn

本文主要参考:http://blog.csdn.net/oYangZi12/article/details/53290426?locationNum=5&fps=1 
1.下载微软提供的caffe(https://github.com/Microsoft/caffe)并编译,Pre-Build Steps 
Copy .\windows\CommonSettings.props.example to .\windows\CommonSettings.props 选择cpu或者gpu模式。 
2.在caffe-master中libcaffe的相应位置加入roi-pooling层对应的cpp,hpp,cu文件重新编译caffe)。因roi-pooling层已经在微软版本的caffe中存在,只需要找到并添加到libcaffe模块下。caffe-master\include\caffe\layers\roi_pooling_layer.hpp,caffe-master\include\caffe\layers\smooth_l1_loss_layer.hpp添加至caffe-master\include\caffe\layers路径下,将caffe-master\src\caffe\layers\roi_pooling_layer.cpp,caffe-master\src\caffe\layers\smooth_l1_loss_layer添加至caffe-master\src\caffe\layers路径下。 
3.重新build(生成各模块),并对整个caffe工程进行build.build成功则roi_pooling_layer层添加成功。 
4.caffe-master工程下添加Faster_rcnn模块,这里直接将Classification模块中classification.cpp替换掉,Classification重命名成Detect,添加Faster_rcnn.h,Faster_rcnn.cpp和Detect.cpp,添加路径为..\caffe-master\examples\cpp_classification\ 
5.Faster_rcnn.h代码如下:

#pragma once
#include <gflags\gflags.h>
#include <glog\logging.h>
#include <cstring>
#include <map>
#include <string>
#include <vector>
#include "boost\algorithm\string.hpp"
#include "caffe\caffe.hpp"
#include "caffe\util\signal_handler.h"
#include <opencv2\opencv.hpp>
using namespace cv;
using caffe::Blob;
using caffe::Caffe;
using caffe::Net;
using caffe::Layer;
using caffe::Solver;
using caffe::shared_ptr;
using caffe::string;
using caffe::Timer;
using caffe::vector;
using std::ostringstream;
struct config{
    int maxsize;
    int target_size;
    int feat_stride;
    int anchor[9][4];
    int test_min_box_size;
    int per_nms_topN;
    int after_nms_topN;
    float overlap;
    config(){
        maxsize = 1000;
        target_size = 600;
        feat_stride = 16;
        int tmp[9][4] = {
            {-83,-39,100,56},
            {-175,-87,192,104},
            {-359,-183,376,200},
            {-55,-55,72,72},
            {-119,-119,136,136},
            {-247,-247,264,264},
            {-35,-79,52,96},
            {-79,-167,96,184},
            {-167,-343,184,360}
        };
        memcpy(anchor, tmp, 9 * 4 * sizeof(int));
        test_min_box_size = 16;
        per_nms_topN = 6000;
        after_nms_topN = 300;
        overlap = 0.7;
    }
};
struct abox
{
    float x1;
    float y1;
    float x2;
    float y2;
    float score;
};
class Faster_rcnn
{
public:
    Faster_rcnn(Mat);
    ~Faster_rcnn();
    bool init();
    Mat gettarget(Mat);
public:
    config conf;


private:
    Mat im, m_src;
    Size input_geometry_;
    shared_ptr<Net<float> > rpn_net, faster_rcnn_net;
    double im_scale;
    Size feature_map_size;
private:
    bool loadnet();
    bool imgtoblob();
    vector<abox> forward();
    bool rpn_converttoboxs();
    void prep_im_size();
    Mat proposal_local_anchor();
    Mat bbox_tranform_inv(Mat, Mat, string);
    Mat get_rpn_score(Blob<float>*, int w, int h);
    void m_sort(Mat&, Mat&);
    void boxes_filter(vector<abox>&, int, vector<abox>, vector<int>);
    void filter_boxs(Mat&, Mat&, vector<abox>&);
    void nms(vector<abox>, double overlap, vector<int>& vPick, int &nPick);
    void testdetection(vector<abox>&);


};
 
 
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 7
  • 8
  • 9
  • 10
  • 11
  • 12
  • 13
  • 14
  • 15
  • 16
  • 17
  • 18
  • 19
  • 20
  • 21
  • 22
  • 23
  • 24
  • 25
  • 26
  • 27
  • 28
  • 29
  • 30
  • 31
  • 32
  • 33
  • 34
  • 35
  • 36
  • 37
  • 38
  • 39
  • 40
  • 41
  • 42
  • 43
  • 44
  • 45
  • 46
  • 47
  • 48
  • 49
  • 50
  • 51
  • 52
  • 53
  • 54
  • 55
  • 56
  • 57
  • 58
  • 59
  • 60
  • 61
  • 62
  • 63
  • 64
  • 65
  • 66
  • 67
  • 68
  • 69
  • 70
  • 71
  • 72
  • 73
  • 74
  • 75
  • 76
  • 77
  • 78
  • 79
  • 80
  • 81
  • 82
  • 83
  • 84
  • 85
  • 86
  • 87
  • 88
  • 89
  • 90
  • 91
  • 92
  • 93
  • 94
  • 95
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 7
  • 8
  • 9
  • 10
  • 11
  • 12
  • 13
  • 14
  • 15
  • 16
  • 17
  • 18
  • 19
  • 20
  • 21
  • 22
  • 23
  • 24
  • 25
  • 26
  • 27
  • 28
  • 29
  • 30
  • 31
  • 32
  • 33
  • 34
  • 35
  • 36
  • 37
  • 38
  • 39
  • 40
  • 41
  • 42
  • 43
  • 44
  • 45
  • 46
  • 47
  • 48
  • 49
  • 50
  • 51
  • 52
  • 53
  • 54
  • 55
  • 56
  • 57
  • 58
  • 59
  • 60
  • 61
  • 62
  • 63
  • 64
  • 65
  • 66
  • 67
  • 68
  • 69
  • 70
  • 71
  • 72
  • 73
  • 74
  • 75
  • 76
  • 77
  • 78
  • 79
  • 80
  • 81
  • 82
  • 83
  • 84
  • 85
  • 86
  • 87
  • 88
  • 89
  • 90
  • 91
  • 92
  • 93
  • 94
  • 95

Faster_rcnn.cpp代码如下:

#include "Faster_rcnn.h"
#include <opencv2\opencv.hpp>

#include <algorithm>
#include "caffe\common.hpp"
#include "caffe\layers\input_layer.hpp"
#include "caffe\layers\inner_product_layer.hpp"
#include "caffe\layers\dropout_layer.hpp"
#include "caffe\layers\conv_layer.hpp"
#include "caffe\layers\relu_layer.hpp"
#include "caffe\layers\reshape_layer.hpp"
#include "caffe\layers\pooling_layer.hpp"
#include "caffe\layers\lrn_layer.hpp"
#include "caffe\layers\softmax_layer.hpp"
#include "caffe\layers\roi_pooling_layer.hpp"
//
//namespace caffe
//{
//  extern INSTANTIATE_CLASS(InputLayer);
//  extern INSTANTIATE_CLASS(InnerProductLayer);
//  extern INSTANTIATE_CLASS(DropoutLayer);
//  extern INSTANTIATE_CLASS(ConvolutionLayer);
//  extern INSTANTIATE_CLASS(ROIPoolingLayer);
//  REGISTER_LAYER_CLASS(Convolution);
//  extern INSTANTIATE_CLASS(ReLULayer);
//  REGISTER_LAYER_CLASS(ReLU);
//  extern INSTANTIATE_CLASS(PoolingLayer);
//  REGISTER_LAYER_CLASS(Pooling);
//  extern INSTANTIATE_CLASS(LRNLayer);
//  REGISTER_LAYER_CLASS(LRN);
//  extern INSTANTIATE_CLASS(SoftmaxLayer);
//  REGISTER_LAYER_CLASS(Softmax);
//  extern INSTANTIATE_CLASS(ReshapeLayer);
//
//}





cv::Scalar colortable[20] = { cv::Scalar(0, 0, 0), cv::Scalar(0, 0, 125),
cv::Scalar(0, 125, 125), cv::Scalar(125, 125, 125), cv::Scalar(125, 0, 0), cv::Scalar(125, 125, 0), cv::Scalar(0, 125, 0), cv::Scalar(125, 0, 125),
cv::Scalar(0, 0, 255), cv::Scalar(0, 255, 255), cv::Scalar(255, 255, 255), cv::Scalar(255, 0, 0), cv::Scalar(255, 255, 0), cv::Scalar(0, 255, 0),
cv::Scalar(255, 0, 255), cv::Scalar(0, 255, 100), cv::Scalar(0, 0, 100),
cv::Scalar(255, 0, 100), cv::Scalar(255, 255, 100), cv::Scalar(100, 100, 100) };
string classname[20] = { "aeroplane", "bike", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog",
"horse", "motobike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor" };
Faster_rcnn::Faster_rcnn(Mat src)
{
    m_src = src;
}
Faster_rcnn::~Faster_rcnn()
{
    //if (boxs != NULL) delete boxs;
}
bool Faster_rcnn::init()
{
    //init
    Caffe::set_mode(Caffe::CPU);
    loadnet();
    return true;
}
bool Faster_rcnn::loadnet()
{
    //load net
    rpn_net.reset(new Net<float>("F:\\fast rcnn\\fasterrcnn_vs2013_beta\\fasterrcnn_vs2013\\faster_rcnn_VOC0712_ZF\\proposal_test.prototxt", caffe::TEST));
    rpn_net->CopyTrainedLayersFrom("F:\\fast rcnn\\fasterrcnn_vs2013_beta\\fasterrcnn_vs2013\\faster_rcnn_VOC0712_ZF\\proposal_final");
    faster_rcnn_net.reset(new Net<float>("F:\\fast rcnn\\fasterrcnn_vs2013_beta\\fasterrcnn_vs2013\\faster_rcnn_VOC0712_ZF\\detection_test.prototxt", caffe::TEST));
    faster_rcnn_net->CopyTrainedLayersFrom("F:\\fast rcnn\\fasterrcnn_vs2013_beta\\fasterrcnn_vs2013\\faster_rcnn_VOC0712_ZF\\detection_final");
    /*rpn_net.reset(new Net<float>("faster_rcnn_VOC0712_ZF\\proposal_test.prototxt", caffe::TEST));
    rpn_net->CopyTrainedLayersFrom("faster_rcnn_VOC0712_ZF\\proposal_final");
    faster_rcnn_net.reset(new Net<float>("faster_rcnn_VOC0712_ZF\\detection_test.prototxt", caffe::TEST));
    faster_rcnn_net->CopyTrainedLayersFrom("faster_rcnn_VOC0712_ZF\\detection_final");*/
    return true;
}
bool Faster_rcnn::imgtoblob()
{
    Mat sample_float;
    m_src.convertTo(sample_float, CV_32FC3);
    cv::Scalar channel_mean = cv::mean(sample_float);
    Mat mean = cv::Mat(m_src.rows, m_src.cols, sample_float.type(), channel_mean);

    Mat sample_normalized;
    subtract(sample_float, mean, sample_normalized);
    prep_im_size();
    resize(sample_normalized, sample_normalized, input_geometry_);
    Blob<float>* input_layer = rpn_net->input_blobs()[0];
    input_layer->Reshape(1, sample_normalized.channels(), sample_normalized.rows, sample_normalized.cols);
    rpn_net->Reshape();
    float* input_data = input_layer->mutable_cpu_data();
    vector<cv::Mat> input_channels;
    for (int i = 0; i < input_layer->channels(); ++i)
    {
        cv::Mat channel(sample_normalized.rows, sample_normalized.cols, CV_32FC1, input_data);
        input_channels.push_back(channel);
        input_data += sample_normalized.rows * sample_normalized.cols;
    }
    cv::split(sample_normalized, input_channels);
    CHECK(reinterpret_cast<float*>(input_channels.at(0).data) == rpn_net->input_blobs()[0]->cpu_data()) << "Input channels are not wrapping the input layer of the network.";

    return true;
}
bool aboxcomp(abox& b1, abox& b2)
{
    return b1.score > b2.score;
}
vector<abox> Faster_rcnn::forward()
{
    //forward
    const vector<Blob<float>*>& result = rpn_net->Forward();
    Blob<float>* resule0 = result[0];
    Blob<float>* resule1 = result[1];
    Mat boxs_delta(resule0->num()*resule0->channels()*resule0->width()*resule0->height() / 4, 4, CV_32FC1);
    float* p = resule0->mutable_cpu_data();
    int num = 0;
    for (int i = 0; i < resule0->num()*resule0->channels()*resule0->width()*resule0->height() / 4; i++)
    {
        for (int j = 0; j < 4; j++)
        {
            boxs_delta.at<float>(i, j) = resule0->data_at(0, num%resule0->channels(),
                (num - num / resule0->channels() / resule0->height() * resule0->channels() * resule0->height()) / resule0->height(),
                num / resule0->channels() / resule0->height());
            num++;
            //int order = j + i * 4;
            //boxs_delta.at<float>(i, j) = resule0->data_at(0, (order % (resule0->height()*resule0->channels())) % resule0->channels(), (order % (resule0->height()*resule0->channels())) / resule0->channels(), order / (resule0->height()*resule0->channels()));
        }
    }
    //create anchors
    feature_map_size = Size(resule0->width(), resule0->height());
    //prep_im_size();
    Mat anchors = proposal_local_anchor();
    Mat pre_box = bbox_tranform_inv(anchors, boxs_delta, "rpn");
    //Mat score(resule0->width(), resule0->height(), CV_32FC1);
    Mat score = get_rpn_score(resule1, resule0->width(), resule0->height());
    vector<abox> aboxes;
    filter_boxs(pre_box, score, aboxes);
    std::sort(aboxes.begin(), aboxes.end(), aboxcomp);
    //m_sort(pre_box,score);
    vector<int> vPick(aboxes.size());
    int nPick;
    /有cuda版,待加入,此处为cpu版///
    nms(aboxes, conf.overlap, vPick, nPick);
    vector<abox> aboxes_;
    boxes_filter(aboxes_, nPick, aboxes, vPick);
    return aboxes_;
}
void Faster_rcnn::nms(vector<abox> input_boxes, double overlap, vector<int> &vPick, int &nPick)
{
    int nSample = min(int(input_boxes.size()), conf.per_nms_topN);

    vector<double> vArea(nSample);
    for (int i = 0; i < nSample; ++i)
    {
        vArea[i] = double(input_boxes.at(i).x2 - input_boxes.at(i).x1 + 1)
            * (input_boxes.at(i).y2 - input_boxes.at(i).y1 + 1);
    }

    std::multimap<double, int> scores;
    for (int i = 0; i < nSample; ++i)
        scores.insert(std::pair<double, int>(input_boxes.at(i).score, i));

    nPick = 0;

    do
    {
        int last = scores.rbegin()->second;
        vPick[nPick] = last;
        nPick += 1;

        for (std::multimap<double, int>::iterator it = scores.begin(); it != scores.end();)
        {
            int it_idx = it->second;
            double xx1 = max(input_boxes.at(last).x1, input_boxes.at(it_idx).x1);
            double yy1 = max(input_boxes.at(last).y1, input_boxes.at(it_idx).y1);
            double xx2 = min(input_boxes.at(last).x2, input_boxes.at(it_idx).x2);
            double yy2 = min(input_boxes.at(last).y2, input_boxes.at(it_idx).y2);

            double w = max(double(0.0), xx2 - xx1 + 1), h = max(double(0.0), yy2 - yy1 + 1);

            double ov = w*h / (vArea[last] + vArea[it_idx] - w*h);

            if (ov > overlap)
            {
                it = scores.erase(it);
            }
            else
            {
                it++;
            }
        }

    } while (scores.size() != 0);
}
void Faster_rcnn::boxes_filter(vector<abox>& aboxes, int nPick, vector<abox> row, vector<int> vPick)
{
    int n = min(nPick, conf.after_nms_topN);
    for (int i = 0; i < n; i++)
    {
        aboxes.push_back(row[vPick[i]]);
    }
}
void Faster_rcnn::filter_boxs(Mat& pre_box, Mat& score, vector<abox>& aboxes)
{
    aboxes.clear();
    for (int i = 0; i < pre_box.rows; i++)
    {
        int widths = pre_box.at<float>(i, 2) - pre_box.at<float>(i, 0) + 1;
        int heights = pre_box.at<float>(i, 3) - pre_box.at<float>(i, 1) + 1;
        if (widths < conf.test_min_box_size || heights < conf.test_min_box_size)
        {
            pre_box.at<float>(i, 0) = 0;
            pre_box.at<float>(i, 1) = 0;
            pre_box.at<float>(i, 2) = 0;
            pre_box.at<float>(i, 3) = 0;
            score.at<float>(i, 0) = 0;
        }
        abox tmp;
        tmp.x1 = pre_box.at<float>(i, 0);
        tmp.y1 = pre_box.at<float>(i, 1);
        tmp.x2 = pre_box.at<float>(i, 2);
        tmp.y2 = pre_box.at<float>(i, 3);
        tmp.score = score.at<float>(i, 0);
        aboxes.push_back(tmp);
    }
}
void Faster_rcnn::m_sort(Mat& pre_box, Mat& score)
{
    for (int i = 0; i < pre_box.rows - 1; i++)
    {
        for (int j = i + 1; j < pre_box.rows; j++)
        {
            if (score.at<float>(i, 0) < score.at<float>(j, 0))
            {
                float tmp = score.at<float>(j, 0);
                score.at<float>(j, 0) = score.at<float>(i, 0);
                score.at<float>(i, 0) = tmp;

                float tmp0 = pre_box.at<float>(j, 0);
                float tmp1 = pre_box.at<float>(j, 1);
                float tmp2 = pre_box.at<float>(j, 2);
                float tmp3 = pre_box.at<float>(j, 3);
                pre_box.at<float>(j, 0) = pre_box.at<float>(i, 0);
                pre_box.at<float>(j, 1) = pre_box.at<float>(i, 1);
                pre_box.at<float>(j, 2) = pre_box.at<float>(i, 2);
                pre_box.at<float>(j, 3) = pre_box.at<float>(i, 3);
                pre_box.at<float>(i, 0) = tmp0;
                pre_box.at<float>(i, 1) = tmp1;
                pre_box.at<float>(i, 2) = tmp2;
                pre_box.at<float>(i, 3) = tmp3;
            }

        }
    }
}
Mat Faster_rcnn::get_rpn_score(Blob<float>* resule1, int w, int h)
{
    //Blob<float> tmp;
    int channel = resule1->width()*resule1->height() / (w * h);
    Mat score(resule1->width()*resule1->height(), 1, CV_32FC1);
    //tmp.Reshape(1, resule1->width()*resule1->height() / (w * h),h,w);
    //float* p = tmp.mutable_cpu_data;
    int num = 0;
    for (int i = 0; i < w; i++)
    {
        for (int j = 0; j < h; j++)
        {
            for (int k = 0; k < channel; k++)
            {
                score.at<float>(num, 0) = resule1->data_at(0, 1, h*k + j, i);
                num++;
            }
        }
    }
    return score;
}
Mat Faster_rcnn::bbox_tranform_inv(Mat anchors, Mat boxs_delta, string type)
{
    if (type == "rpn")
    {
        Mat pre_box(anchors.rows, anchors.cols, CV_32FC1);
        for (int i = 0; i < anchors.rows; i++)
        {
            double pred_ctr_x, pred_ctr_y, src_ctr_x, src_ctr_y;
            double dst_ctr_x, dst_ctr_y, dst_scl_x, dst_scl_y;
            double src_w, src_h, pred_w, pred_h;
            src_w = anchors.at<float>(i, 2) - anchors.at<float>(i, 0) + 1;
            src_h = anchors.at<float>(i, 3) - anchors.at<float>(i, 1) + 1;
            src_ctr_x = anchors.at<float>(i, 0) + 0.5 * (src_w - 1);
            src_ctr_y = anchors.at<float>(i, 1) + 0.5 * (src_h - 1);

            dst_ctr_x = boxs_delta.at<float>(i, 0);
            dst_ctr_y = boxs_delta.at<float>(i, 1);
            dst_scl_x = boxs_delta.at<float>(i, 2);
            dst_scl_y = boxs_delta.at<float>(i, 3);
            pred_ctr_x = dst_ctr_x*src_w + src_ctr_x;
            pred_ctr_y = dst_ctr_y*src_h + src_ctr_y;
            pred_w = exp(dst_scl_x) * src_w;
            pred_h = exp(dst_scl_y) * src_h;

            pre_box.at<float>(i, 0) = ((pred_ctr_x - 0.5*(pred_w - 1)) - 1) * (float)(m_src.cols) / (im.cols - 1) + 1;
            pre_box.at<float>(i, 1) = ((pred_ctr_y - 0.5*(pred_h - 1)) - 1) * (float)(m_src.rows) / (im.rows - 1) + 1;
            pre_box.at<float>(i, 2) = ((pred_ctr_x + 0.5*(pred_w - 1)) - 1) * (float)(m_src.cols) / (im.cols - 1) + 1;
            pre_box.at<float>(i, 3) = ((pred_ctr_y + 0.5*(pred_h - 1)) - 1) * (float)(m_src.rows) / (im.rows - 1) + 1;
            if (pre_box.at<float>(i, 0) < 0)    pre_box.at<float>(i, 0) = 0;
            if (pre_box.at<float>(i, 0) > (m_src.cols - 1)) pre_box.at<float>(i, 0) = m_src.cols - 1;
            if (pre_box.at<float>(i, 2) < 0)    pre_box.at<float>(i, 2) = 0;
            if (pre_box.at<float>(i, 2) > (m_src.cols - 1)) pre_box.at<float>(i, 2) = m_src.cols - 1;

            if (pre_box.at<float>(i, 1) < 0)    pre_box.at<float>(i, 1) = 0;
            if (pre_box.at<float>(i, 1) > (m_src.rows - 1)) pre_box.at<float>(i, 1) = m_src.rows - 1;
            if (pre_box.at<float>(i, 3) < 0)    pre_box.at<float>(i, 3) = 0;
            if (pre_box.at<float>(i, 3) > (m_src.rows - 1)) pre_box.at<float>(i, 3) = m_src.rows - 1;
        }
        return pre_box;
    }
    if (type == "rcnn")
    {
        Mat pre_box(boxs_delta.rows, boxs_delta.cols, CV_32FC1);
        for (int i = 0; i < boxs_delta.rows; i++)
        {
            for (int j = 1; j < boxs_delta.cols / 4; j++)
            {
                double pred_ctr_x, pred_ctr_y, src_ctr_x, src_ctr_y;
                double dst_ctr_x, dst_ctr_y, dst_scl_x, dst_scl_y;
                double src_w, src_h, pred_w, pred_h;
                src_w = anchors.at<float>(i, 2) - anchors.at<float>(i, 0) + 1;
                src_h = anchors.at<float>(i, 3) - anchors.at<float>(i, 1) + 1;
                src_ctr_x = anchors.at<float>(i, 0) + 0.5 * (src_w - 1);
                src_ctr_y = anchors.at<float>(i, 1) + 0.5 * (src_h - 1);

                dst_ctr_x = boxs_delta.at<float>(i, 4 * j + 0);
                dst_ctr_y = boxs_delta.at<float>(i, 4 * j + 1);
                dst_scl_x = boxs_delta.at<float>(i, 4 * j + 2);
                dst_scl_y = boxs_delta.at<float>(i, 4 * j + 3);
                pred_ctr_x = dst_ctr_x*src_w + src_ctr_x;
                pred_ctr_y = dst_ctr_y*src_h + src_ctr_y;
                pred_w = exp(dst_scl_x) * src_w;
                pred_h = exp(dst_scl_y) * src_h;

                pre_box.at<float>(i, 4 * (j - 1) + 0) = ((pred_ctr_x - 0.5*(pred_w - 1)) - 1);
                pre_box.at<float>(i, 4 * (j - 1) + 1) = ((pred_ctr_y - 0.5*(pred_h - 1)) - 1);
                pre_box.at<float>(i, 4 * (j - 1) + 2) = ((pred_ctr_x + 0.5*(pred_w - 1)) - 1);
                pre_box.at<float>(i, 4 * (j - 1) + 3) = ((pred_ctr_y + 0.5*(pred_h - 1)) - 1);
                if (pre_box.at<float>(i, 4 * (j - 1) + 0) < 0)  pre_box.at<float>(i, 4 * (j - 1) + 0) = 0;
                if (pre_box.at<float>(i, 4 * (j - 1) + 0) > (m_src.cols - 1))   pre_box.at<float>(i, 4 * (j - 1) + 0) = m_src.cols - 1;
                if (pre_box.at<float>(i, 4 * (j - 1) + 2) < 0)  pre_box.at<float>(i, 4 * (j - 1) + 2) = 0;
                if (pre_box.at<float>(i, 4 * (j - 1) + 2) > (m_src.cols - 1))   pre_box.at<float>(i, 4 * (j - 1) + 2) = m_src.cols - 1;

                if (pre_box.at<float>(i, 4 * (j - 1) + 1) < 0)  pre_box.at<float>(i, 4 * (j - 1) + 1) = 0;
                if (pre_box.at<float>(i, 4 * (j - 1) + 1) > (m_src.rows - 1))   pre_box.at<float>(i, 4 * (j - 1) + 1) = m_src.rows - 1;
                if (pre_box.at<float>(i, 4 * (j - 1) + 3) < 0)  pre_box.at<float>(i, 4 * (j - 1) + 3) = 0;
                if (pre_box.at<float>(i, 4 * (j - 1) + 3) > (m_src.rows - 1))   pre_box.at<float>(i, 4 * (j - 1) + 3) = m_src.rows - 1;
            }

        }
        return pre_box;
    }


}
Mat Faster_rcnn::proposal_local_anchor()
{
    Blob<float> shift;
    Mat shitf_x(feature_map_size.height, feature_map_size.width, CV_32SC1);
    Mat shitf_y(feature_map_size.height, feature_map_size.width, CV_32SC1);
    for (size_t i = 0; i < feature_map_size.width; i++)
    {
        for (size_t j = 0; j < feature_map_size.height; j++)
        {
            shitf_x.at<int>(j, i) = i * conf.feat_stride;
            shitf_y.at<int>(j, i) = j * conf.feat_stride;
        }
    }
    shift.Reshape(9, feature_map_size.width*feature_map_size.height, 4, 1);
    float *p = shift.mutable_cpu_diff(), *a = shift.mutable_cpu_data();
    for (int i = 0; i < feature_map_size.width*feature_map_size.height; i++)
    {
        for (int j = 0; j < 9; j++)
        {
            {
                size_t num = i * 4 + j * 4 * feature_map_size.width*feature_map_size.height;
                p[num + 0] = -shitf_x.at<int>(i % shitf_x.rows, i / shitf_x.rows);
                p[num + 2] = -shitf_x.at<int>(i % shitf_x.rows, i / shitf_x.rows);
                p[num + 1] = -shitf_y.at<int>(i % shitf_y.rows, i / shitf_y.rows);
                p[num + 3] = -shitf_y.at<int>(i % shitf_y.rows, i / shitf_y.rows);
                a[num + 0] = conf.anchor[j][0];
                a[num + 1] = conf.anchor[j][1];
                a[num + 2] = conf.anchor[j][2];
                a[num + 3] = conf.anchor[j][3];
            }
        }
    }
    shift.Update();
    Mat anchors(9 * feature_map_size.width*feature_map_size.height, 4, CV_32FC1);
    size_t num = 0;
    for (int i = 0; i < anchors.cols; i++)
    {
        for (int j = 0; j < anchors.rows; j++)
        {
            anchors.at<float>(j, i) = shift.data_at(num%shift.num(),
                (num - num / (shift.num() * shift.channels())*shift.num() * shift.channels()) / shift.num(),
                num / (shift.num() * shift.channels()), 0);
            num++;
        }
    }
    /*for (int i = 0; i < 4; i++)
    {
    for (int k = 0; k < feature_map_size.width*feature_map_size.height; k++)
    {
    for (int j = 0; j < 9; j++)
    {
    anchors.at<float>(num%anchors.rows, num / anchors.rows) = shift.data_at(j, k, i, 0);
    num++;
    }
    }
    }*/
    return anchors;
}
void Faster_rcnn::prep_im_size()
{
    int im_size_min = min(m_src.cols, m_src.rows);
    int im_size_max = max(m_src.cols, m_src.rows);
    im_scale = double(conf.target_size) / im_size_min;
    if (round(im_scale*im_size_max) > conf.maxsize)
    {
        im_scale = double(conf.maxsize) / im_size_max;
    }
    input_geometry_ = Size(round(m_src.cols * im_scale), round(m_src.rows * im_scale));
    resize(m_src, im, input_geometry_);
}
bool Faster_rcnn::rpn_converttoboxs()
{
    return true;
}
Mat Faster_rcnn::gettarget(Mat src)
{
    m_src = src;
    //img=>blob
    imgtoblob();
    vector<abox> abox = forward();
    testdetection(abox);
    return m_src;
}
void Faster_rcnn::testdetection(vector<abox>& aboxes)
{
    float scales = im_scale;
    Mat anchors(aboxes.size(), 4, CV_32FC1);
    //int a= faster_rcnn_net->blob_by_name("data")->count();
    //vector<string> a = rpn_net->blob_names();
    //  int b = rpn_net->blob_by_name("conv5")->count();
    faster_rcnn_net->blob_by_name("data")->CopyFrom(*rpn_net->blob_by_name("conv5").get(), false, true);
    Blob<float>* input_layer = faster_rcnn_net->input_blobs()[1];
    int sub_blob_num = aboxes.size();
    input_layer->Reshape(sub_blob_num, 5, 1, 1);
    float* input_data = input_layer->mutable_cpu_data();
    int num = 0;
    for (auto ite = aboxes.begin(); ite != aboxes.end(); ite++)
    {
        anchors.at<float>(num, 0) = ite->x1;
        anchors.at<float>(num, 1) = ite->y1;
        anchors.at<float>(num, 2) = ite->x2;
        anchors.at<float>(num, 3) = ite->y2;
        ite->score = 0;
        ite->x1 = (ite->x1 - 1) * scales + 1 - 1;
        ite->y1 = (ite->y1 - 1) * scales + 1 - 1;
        ite->x2 = (ite->x2 - 1) * scales + 1 - 1;
        ite->y2 = (ite->y2 - 1) * scales + 1 - 1;
        input_data[num * 5 + 0] = ite->score;
        input_data[num * 5 + 1] = ite->x1;
        input_data[num * 5 + 2] = ite->y1;
        input_data[num * 5 + 3] = ite->x2;
        input_data[num * 5 + 4] = ite->y2;
        num++;
    }
    const vector<Blob<float>*>& result = faster_rcnn_net->Forward();
    Blob<float>* scores = result[1];
    Blob<float>* box_deltas = result[0];
    box_deltas->data_at(0, 3, 0, 0);
    Mat boxs_delta(box_deltas->num(), box_deltas->channels(), CV_32FC1);
    for (int i = 0; i < box_deltas->num(); i++)
    {
        for (int j = 0; j < box_deltas->channels(); j++)
        {
            boxs_delta.at<float>(i, j) = box_deltas->data_at(i, j, 0, 0);
        }
    }
    Mat score(scores->num(), scores->channels() - 1, CV_32FC1);
    for (int i = 0; i < scores->num(); i++)
    {
        for (int j = 0 + 1; j < scores->channels(); j++)
        {
            score.at<float>(i, j - 1) = scores->data_at(i, j, 0, 0);
        }
    }
    Mat pred_boxes = bbox_tranform_inv(anchors, boxs_delta, "rcnn");
    std::map<int, vector<Rect>> classer;
    20为类别数///
    for (int i = 0; i < 20; i++)
    {
        vector<Rect> r;
        vector<abox> aboxes;
        for (int j = 0; j < pred_boxes.rows; j++)
        {
            abox tmp;
            tmp.x1 = pred_boxes.at<float>(j, i * 4);
            tmp.y1 = pred_boxes.at<float>(j, i * 4 + 1);
            tmp.x2 = pred_boxes.at<float>(j, i * 4 + 2);
            tmp.y2 = pred_boxes.at<float>(j, i * 4 + 3);
            tmp.score = score.at<float>(j, i);
            aboxes.push_back(tmp);
        }
        vector<int> vPick(aboxes.size());
        int nPick;
        nms(aboxes, 0.3, vPick, nPick);
        for (int i = 0; i < nPick; i++)
        {
            if (aboxes[vPick[i]].score > 0.6)
            {
                Rect rt;
                rt.x = aboxes[vPick[i]].x1;
                rt.y = aboxes[vPick[i]].y1;
                rt.width = aboxes[vPick[i]].x2 - aboxes[vPick[i]].x1 + 1;
                rt.height = aboxes[vPick[i]].y2 - aboxes[vPick[i]].y1 + 1;
                r.push_back(rt);
            }
        }
        classer.insert(std::pair<int, vector<Rect>>(i, r));
    }
    for (int i = 0; i < 20; i++)
    {
        if (!classer[i].empty())
        {
            //printf("%d\t%d\n", i, classer[i].size());
            for (auto ite = classer[i].begin(); ite != classer[i].end(); ite++)
            {
                rectangle(m_src, *ite, colortable[i]);
                putText(m_src, classname[i], Point(ite->x, ite->y), CV_FONT_HERSHEY_SIMPLEX, 0.5, colortable[i], 2, 2);
            }
        }
    }
}

 
 
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 7
  • 8
  • 9
  • 10
  • 11
  • 12
  • 13
  • 14
  • 15
  • 16
  • 17
  • 18
  • 19
  • 20
  • 21
  • 22
  • 23
  • 24
  • 25
  • 26
  • 27
  • 28
  • 29
  • 30
  • 31
  • 32
  • 33
  • 34
  • 35
  • 36
  • 37
  • 38
  • 39
  • 40
  • 41
  • 42
  • 43
  • 44
  • 45
  • 46
  • 47
  • 48
  • 49
  • 50
  • 51
  • 52
  • 53
  • 54
  • 55
  • 56
  • 57
  • 58
  • 59
  • 60
  • 61
  • 62
  • 63
  • 64
  • 65
  • 66
  • 67
  • 68
  • 69
  • 70
  • 71
  • 72
  • 73
  • 74
  • 75
  • 76
  • 77
  • 78
  • 79
  • 80
  • 81
  • 82
  • 83
  • 84
  • 85
  • 86
  • 87
  • 88
  • 89
  • 90
  • 91
  • 92
  • 93
  • 94
  • 95
  • 96
  • 97
  • 98
  • 99
  • 100
  • 101
  • 102
  • 103
  • 104
  • 105
  • 106
  • 107
  • 108
  • 109
  • 110
  • 111
  • 112
  • 113
  • 114
  • 115
  • 116
  • 117
  • 118
  • 119
  • 120
  • 121
  • 122
  • 123
  • 124
  • 125
  • 126
  • 127
  • 128
  • 129
  • 130
  • 131
  • 132
  • 133
  • 134
  • 135
  • 136
  • 137
  • 138
  • 139
  • 140
  • 141
  • 142
  • 143
  • 144
  • 145
  • 146
  • 147
  • 148
  • 149
  • 150
  • 151
  • 152
  • 153
  • 154
  • 155
  • 156
  • 157
  • 158
  • 159
  • 160
  • 161
  • 162
  • 163
  • 164
  • 165
  • 166
  • 167
  • 168
  • 169
  • 170
  • 171
  • 172
  • 173
  • 174
  • 175
  • 176
  • 177
  • 178
  • 179
  • 180
  • 181
  • 182
  • 183
  • 184
  • 185
  • 186
  • 187
  • 188
  • 189
  • 190
  • 191
  • 192
  • 193
  • 194
  • 195
  • 196
  • 197
  • 198
  • 199
  • 200
  • 201
  • 202
  • 203
  • 204
  • 205
  • 206
  • 207
  • 208
  • 209
  • 210
  • 211
  • 212
  • 213
  • 214
  • 215
  • 216
  • 217
  • 218
  • 219
  • 220
  • 221
  • 222
  • 223
  • 224
  • 225
  • 226
  • 227
  • 228
  • 229
  • 230
  • 231
  • 232
  • 233
  • 234
  • 235
  • 236
  • 237
  • 238
  • 239
  • 240
  • 241
  • 242
  • 243
  • 244
  • 245
  • 246
  • 247
  • 248
  • 249
  • 250
  • 251
  • 252
  • 253
  • 254
  • 255
  • 256
  • 257
  • 258
  • 259
  • 260
  • 261
  • 262
  • 263
  • 264
  • 265
  • 266
  • 267
  • 268
  • 269
  • 270
  • 271
  • 272
  • 273
  • 274
  • 275
  • 276
  • 277
  • 278
  • 279
  • 280
  • 281
  • 282
  • 283
  • 284
  • 285
  • 286
  • 287
  • 288
  • 289
  • 290
  • 291
  • 292
  • 293
  • 294
  • 295
  • 296
  • 297
  • 298
  • 299
  • 300
  • 301
  • 302
  • 303
  • 304
  • 305
  • 306
  • 307
  • 308
  • 309
  • 310
  • 311
  • 312
  • 313
  • 314
  • 315
  • 316
  • 317
  • 318
  • 319
  • 320
  • 321
  • 322
  • 323
  • 324
  • 325
  • 326
  • 327
  • 328
  • 329
  • 330
  • 331
  • 332
  • 333
  • 334
  • 335
  • 336
  • 337
  • 338
  • 339
  • 340
  • 341
  • 342
  • 343
  • 344
  • 345
  • 346
  • 347
  • 348
  • 349
  • 350
  • 351
  • 352
  • 353
  • 354
  • 355
  • 356
  • 357
  • 358
  • 359
  • 360
  • 361
  • 362
  • 363
  • 364
  • 365
  • 366
  • 367
  • 368
  • 369
  • 370
  • 371
  • 372
  • 373
  • 374
  • 375
  • 376
  • 377
  • 378
  • 379
  • 380
  • 381
  • 382
  • 383
  • 384
  • 385
  • 386
  • 387
  • 388
  • 389
  • 390
  • 391
  • 392
  • 393
  • 394
  • 395
  • 396
  • 397
  • 398
  • 399
  • 400
  • 401
  • 402
  • 403
  • 404
  • 405
  • 406
  • 407
  • 408
  • 409
  • 410
  • 411
  • 412
  • 413
  • 414
  • 415
  • 416
  • 417
  • 418
  • 419
  • 420
  • 421
  • 422
  • 423
  • 424
  • 425
  • 426
  • 427
  • 428
  • 429
  • 430
  • 431
  • 432
  • 433
  • 434
  • 435
  • 436
  • 437
  • 438
  • 439
  • 440
  • 441
  • 442
  • 443
  • 444
  • 445
  • 446
  • 447
  • 448
  • 449
  • 450
  • 451
  • 452
  • 453
  • 454
  • 455
  • 456
  • 457
  • 458
  • 459
  • 460
  • 461
  • 462
  • 463
  • 464
  • 465
  • 466
  • 467
  • 468
  • 469
  • 470
  • 471
  • 472
  • 473
  • 474
  • 475
  • 476
  • 477
  • 478
  • 479
  • 480
  • 481
  • 482
  • 483
  • 484
  • 485
  • 486
  • 487
  • 488
  • 489
  • 490
  • 491
  • 492
  • 493
  • 494
  • 495
  • 496
  • 497
  • 498
  • 499
  • 500
  • 501
  • 502
  • 503
  • 504
  • 505
  • 506
  • 507
  • 508
  • 509
  • 510
  • 511
  • 512
  • 513
  • 514
  • 515
  • 516
  • 517
  • 518
  • 519
  • 520
  • 521
  • 522
  • 523
  • 524
  • 525
  • 526
  • 527
  • 528
  • 529
  • 530
  • 531
  • 532
  • 533
  • 534
  • 535
  • 536
  • 537
  • 538
  • 539
  • 540
  • 541
  • 542
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 7
  • 8
  • 9
  • 10
  • 11
  • 12
  • 13
  • 14
  • 15
  • 16
  • 17
  • 18
  • 19
  • 20
  • 21
  • 22
  • 23
  • 24
  • 25
  • 26
  • 27
  • 28
  • 29
  • 30
  • 31
  • 32
  • 33
  • 34
  • 35
  • 36
  • 37
  • 38
  • 39
  • 40
  • 41
  • 42
  • 43
  • 44
  • 45
  • 46
  • 47
  • 48
  • 49
  • 50
  • 51
  • 52
  • 53
  • 54
  • 55
  • 56
  • 57
  • 58
  • 59
  • 60
  • 61
  • 62
  • 63
  • 64
  • 65
  • 66
  • 67
  • 68
  • 69
  • 70
  • 71
  • 72
  • 73
  • 74
  • 75
  • 76
  • 77
  • 78
  • 79
  • 80
  • 81
  • 82
  • 83
  • 84
  • 85
  • 86
  • 87
  • 88
  • 89
  • 90
  • 91
  • 92
  • 93
  • 94
  • 95
  • 96
  • 97
  • 98
  • 99
  • 100
  • 101
  • 102
  • 103
  • 104
  • 105
  • 106
  • 107
  • 108
  • 109
  • 110
  • 111
  • 112
  • 113
  • 114
  • 115
  • 116
  • 117
  • 118
  • 119
  • 120
  • 121
  • 122
  • 123
  • 124
  • 125
  • 126
  • 127
  • 128
  • 129
  • 130
  • 131
  • 132
  • 133
  • 134
  • 135
  • 136
  • 137
  • 138
  • 139
  • 140
  • 141
  • 142
  • 143
  • 144
  • 145
  • 146
  • 147
  • 148
  • 149
  • 150
  • 151
  • 152
  • 153
  • 154
  • 155
  • 156
  • 157
  • 158
  • 159
  • 160
  • 161
  • 162
  • 163
  • 164
  • 165
  • 166
  • 167
  • 168
  • 169
  • 170
  • 171
  • 172
  • 173
  • 174
  • 175
  • 176
  • 177
  • 178
  • 179
  • 180
  • 181
  • 182
  • 183
  • 184
  • 185
  • 186
  • 187
  • 188
  • 189
  • 190
  • 191
  • 192
  • 193
  • 194
  • 195
  • 196
  • 197
  • 198
  • 199
  • 200
  • 201
  • 202
  • 203
  • 204
  • 205
  • 206
  • 207
  • 208
  • 209
  • 210
  • 211
  • 212
  • 213
  • 214
  • 215
  • 216
  • 217
  • 218
  • 219
  • 220
  • 221
  • 222
  • 223
  • 224
  • 225
  • 226
  • 227
  • 228
  • 229
  • 230
  • 231
  • 232
  • 233
  • 234
  • 235
  • 236
  • 237
  • 238
  • 239
  • 240
  • 241
  • 242
  • 243
  • 244
  • 245
  • 246
  • 247
  • 248
  • 249
  • 250
  • 251
  • 252
  • 253
  • 254
  • 255
  • 256
  • 257
  • 258
  • 259
  • 260
  • 261
  • 262
  • 263
  • 264
  • 265
  • 266
  • 267
  • 268
  • 269
  • 270
  • 271
  • 272
  • 273
  • 274
  • 275
  • 276
  • 277
  • 278
  • 279
  • 280
  • 281
  • 282
  • 283
  • 284
  • 285
  • 286
  • 287
  • 288
  • 289
  • 290
  • 291
  • 292
  • 293
  • 294
  • 295
  • 296
  • 297
  • 298
  • 299
  • 300
  • 301
  • 302
  • 303
  • 304
  • 305
  • 306
  • 307
  • 308
  • 309
  • 310
  • 311
  • 312
  • 313
  • 314
  • 315
  • 316
  • 317
  • 318
  • 319
  • 320
  • 321
  • 322
  • 323
  • 324
  • 325
  • 326
  • 327
  • 328
  • 329
  • 330
  • 331
  • 332
  • 333
  • 334
  • 335
  • 336
  • 337
  • 338
  • 339
  • 340
  • 341
  • 342
  • 343
  • 344
  • 345
  • 346
  • 347
  • 348
  • 349
  • 350
  • 351
  • 352
  • 353
  • 354
  • 355
  • 356
  • 357
  • 358
  • 359
  • 360
  • 361
  • 362
  • 363
  • 364
  • 365
  • 366
  • 367
  • 368
  • 369
  • 370
  • 371
  • 372
  • 373
  • 374
  • 375
  • 376
  • 377
  • 378
  • 379
  • 380
  • 381
  • 382
  • 383
  • 384
  • 385
  • 386
  • 387
  • 388
  • 389
  • 390
  • 391
  • 392
  • 393
  • 394
  • 395
  • 396
  • 397
  • 398
  • 399
  • 400
  • 401
  • 402
  • 403
  • 404
  • 405
  • 406
  • 407
  • 408
  • 409
  • 410
  • 411
  • 412
  • 413
  • 414
  • 415
  • 416
  • 417
  • 418
  • 419
  • 420
  • 421
  • 422
  • 423
  • 424
  • 425
  • 426
  • 427
  • 428
  • 429
  • 430
  • 431
  • 432
  • 433
  • 434
  • 435
  • 436
  • 437
  • 438
  • 439
  • 440
  • 441
  • 442
  • 443
  • 444
  • 445
  • 446
  • 447
  • 448
  • 449
  • 450
  • 451
  • 452
  • 453
  • 454
  • 455
  • 456
  • 457
  • 458
  • 459
  • 460
  • 461
  • 462
  • 463
  • 464
  • 465
  • 466
  • 467
  • 468
  • 469
  • 470
  • 471
  • 472
  • 473
  • 474
  • 475
  • 476
  • 477
  • 478
  • 479
  • 480
  • 481
  • 482
  • 483
  • 484
  • 485
  • 486
  • 487
  • 488
  • 489
  • 490
  • 491
  • 492
  • 493
  • 494
  • 495
  • 496
  • 497
  • 498
  • 499
  • 500
  • 501
  • 502
  • 503
  • 504
  • 505
  • 506
  • 507
  • 508
  • 509
  • 510
  • 511
  • 512
  • 513
  • 514
  • 515
  • 516
  • 517
  • 518
  • 519
  • 520
  • 521
  • 522
  • 523
  • 524
  • 525
  • 526
  • 527
  • 528
  • 529
  • 530
  • 531
  • 532
  • 533
  • 534
  • 535
  • 536
  • 537
  • 538
  • 539
  • 540
  • 541
  • 542

Detect.cpp代码如下:

#include "Faster_rcnn.h"
//#include <opencv2\opencv.hpp>

int main()
{
    Mat im = imread("D:\\fast-rcnn-master\\data\\demo\\001551.jpg");
    Faster_rcnn detect(im);
    detect.init();
    while (1)
    {
        Mat img = detect.gettarget(im);
        imshow("img", img);
        cvWaitKey(20);

    }

    return 0;
}
 
 
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 7
  • 8
  • 9
  • 10
  • 11
  • 12
  • 13
  • 14
  • 15
  • 16
  • 17
  • 18
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 7
  • 8
  • 9
  • 10
  • 11
  • 12
  • 13
  • 14
  • 15
  • 16
  • 17
  • 18

6.将matlab版faster-rcnn的ZF网络模型文件放到工程faster_rcnn_VOC0712_ZF文件夹下。https://github.com/ShaoqingRen/faster_rcnn 最后几行给出了下载地址,下载地址为:https://pan.baidu.com/s/1hsFKmeK,下载完成放在自己的路径下,并在Faster_rcnn.cpp文件bool Faster_rcnn::loadnet()函数中正确添加所需的模型文件路径。 
7. build(生成)Detect模块,如果是Debug模式,则可以在….\caffe-master\Build\x64\Debug\路径下找到Detect.exe, 
cmd进入到….\caffe-master\Build\x64\Debug\路径,执行 
..\x64\Debug>Detect.exe 
8.出来检测结果: 
因图片大小问题不能上传成功。

  • 0
    点赞
  • 4
    收藏
    觉得还不错? 一键收藏
  • 2
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值