方便 預測 大致 ole test cto oop 可執行文件 names

這裏500VIP源碼下載 dsluntan.com 介紹的是通過添加自定義層（RPN層）代替python層，實現c++版的Faster R-CNN，因為去掉python了，所以部署時不會因為牽扯到python庫等其它的莫名其妙的錯誤，使用起來就跟單純的caffe一樣，更簡單方便。 核心代碼，借鑒的是這篇博客，這裏的話，我們不扣具體的代碼細節（比如rpn層是怎麽產出候選框啊，非極大值抑制是具體怎麽實現的等等），有興趣的可以自己查下資料，所以主要是走一個步驟，從而完成c++版Faster R-CNN的配置。

    步入正題，步驟和上面那篇博客大致一樣，但它有一些細節地方直接忽略了，代碼也有幾處小bug，所以我把具體的流程給說下。

  （1） 添加自定義層 rpn_layer.hpp  把它放在 caffe/include/caffe/layers/  目錄下
 

#ifndef CAFFE_RPN_LAYERHPP
#define CAFFE_RPN_LAYERHPP

#include <vector>

#include "caffe/blob.hpp"
#include "caffe/layer.hpp"
#include "caffe/proto/caffe.pb.h"
//#include"opencv2/opencv.hpp"

#define mymax(a,b) ((a)>(b))?(a):(b)
#define mymin(a,b) ((a)>(b))?(b):(a)

namespace caffe {

/**
* @brief implement RPN layer for faster rcnn
*/

template <typename Dtype>
class RPNLayer : public Layer<Dtype> {
public:
    explicit RPNLayer(const LayerParameter& param)
        : Layer<Dtype>(param) {
            m_score_.reset(new Blob<Dtype>());
            m_box_.reset(new Blob<Dtype>());
            local_anchors_.reset(new Blob<Dtype>());
        }
    virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,
        const vector<Blob<Dtype>*>& top);
    virtual void Reshape(const vector<Blob<Dtype>*>& bottom,
        const vector<Blob<Dtype>*>& top){}
    virtual inline const char* type() const { return "RPN"; }

    struct abox{
        Dtype batch_ind;
        Dtype x1;
        Dtype y1;
        Dtype x2;
        Dtype y2;
        Dtype score;
        bool operator <(const abox&tmp) const{
            return score < tmp.score;
        }
    };

protected:
    virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
        const vector<Blob<Dtype>*>& top);
    //virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom,
        //const vector<Blob<Dtype>*>& top);
    virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
        const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom){};

    int feat_stride_;
    int base_size_;
    int min_size_;
    int pre_nms_topN_;
    int post_nms_topN_;
    float nms_thresh_;
    vector<int> anchor_scales_;
    vector<float> ratios_;

    vector<vector<float> > gen_anchors_;
    int *anchors_;
    int anchors_nums_;
    int src_height_;
    int src_width_;
    float src_scale_;
    int map_width_;
    int map_height_;

    shared_ptr<Blob<Dtype> > m_score_;
    shared_ptr<Blob<Dtype> > m_box_;
    shared_ptr<Blob<Dtype> >local_anchors_;
    void generate_anchors();
    vector<vector<float> > ratio_enum(vector<float>);
    vector<float> whctrs(vector<float>);
    vector<float> mkanchor(float w,float h,float x_ctr,float y_ctr);
    vector<vector<float> > scale_enum(vector<float>);

    //cv::Mat proposal_local_anchor(int width, int height);
    void proposal_local_anchor();
    void bbox_tranform_inv();
    cv::Mat bbox_tranform_inv(cv::Mat local_anchors, cv::Mat boxs_delta);
    void nms(std::vector<abox> &input_boxes, float nms_thresh);
    void filter_boxs(cv::Mat& pre_box, cv::Mat& score, vector<abox>& aboxes);
    void filter_boxs(vector<abox>& aboxes);
};
 

} // namespace caffe

#endif // CAFFE_RPN_LAYERHPP
然後是源文件 rpn_layer.cpp 放在 caffe/src/caffe/layers/ 目錄下
#include <algorithm>
#include <vector>

#include "caffe/layers/rpn_layer.hpp"
#include "caffe/util/math_functions.hpp"
#include <opencv2/opencv.hpp>

int debug = 0;
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 }
};
namespace caffe {

template <typename Dtype>
void RPNLayer<Dtype>::LayerSetUp(
    const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
    anchor_scales_.clear();
    ratios_.clear();
    feat_stride_ = this->layer_param_.rpn_param().feat_stride();
    base_size_ = this->layer_param_.rpn_param().basesize();
    min_size_ = this->layer_param_.rpn_param().boxminsize();
    pre_nms_topN_ = this->layer_param_.rpn_param().per_nms_topn();
    post_nms_topN_ = this->layer_param_.rpn_param().post_nms_topn();
    nms_thresh_ = this->layer_param_.rpn_param().nms_thresh();
    int scales_num = this->layer_param_.rpn_param().scale_size();
    for (int i = 0; i < scales_num; ++i)
    {
        anchor_scales_.push_back(this->layer_param_.rpn_param().scale(i));
    }
    int ratios_num = this->layer_param_.rpn_param().ratio_size();
    for (int i = 0; i < ratios_num; ++i)
    {
        ratios_.push_back(this->layer_param_.rpn_param().ratio(i));
    }

    //anchors_nums_ = 9;
    //anchors_ = new int[anchors_nums_ * 4];
    //memcpy(anchors_, tmp, 9 * 4 * sizeof(int));

    generate_anchors();

    anchors_nums_ = gen_anchors_.size();
    anchors_ = new int[anchors_nums_ * 4];
    for (int i = 0; i<gen_anchors_.size(); ++i)
    {
        for (int j = 0; j<gen_anchors_[i].size(); ++j)
        {
            anchors_[i*4+j] = gen_anchors_[i][j];
        }
    }
    top[0]->Reshape(1, 5, 1, 1);
    if (top.size() > 1)
    {
        top[1]->Reshape(1, 1, 1, 1);
    }
}

template <typename Dtype>
void RPNLayer<Dtype>::generate_anchors(){
    //generate base anchor
    vector<float> base_anchor;
    base_anchor.push_back(0);
    base_anchor.push_back(0);
    base_anchor.push_back(base_size_ - 1);
    base_anchor.push_back(base_size_ - 1);
    //enum ratio anchors
    vector<vector<float> >ratio_anchors = ratio_enum(base_anchor);
    for (int i = 0; i < ratio_anchors.size(); ++i)
    {
        vector<vector<float> > tmp = scale_enum(ratio_anchors[i]);
        gen_anchors_.insert(gen_anchors_.end(), tmp.begin(), tmp.end());
    }
}

template <typename Dtype>
vector<vector<float> > RPNLayer<Dtype>::scale_enum(vector<float> anchor){
    vector<vector<float> > result;
    vector<float> reform_anchor = whctrs(anchor);
    float x_ctr = reform_anchor[2];
    float y_ctr = reform_anchor[3];
    float w = reform_anchor[0];
    float h = reform_anchor[1];
    for (int i = 0; i < anchor_scales_.size(); ++i)
    {
        float ws = w * anchor_scales_[i];
        float hs = h *  anchor_scales_[i];
        vector<float> tmp = mkanchor(ws, hs, x_ctr, y_ctr);
        result.push_back(tmp);
    }
    return result;
}

template <typename Dtype>
vector<vector<float> > RPNLayer<Dtype>::ratio_enum(vector<float> anchor){
    vector<vector<float> > result;
    vector<float> reform_anchor = whctrs(anchor);
    float x_ctr = reform_anchor[2];
    float y_ctr = reform_anchor[3];
    float size = reform_anchor[0] * reform_anchor[1];
    for (int i = 0; i < ratios_.size(); ++i)
    {
        float size_ratios = size / ratios_[i];
        float ws = round(sqrt(size_ratios));
        float hs = round(ws*ratios_[i]);
        vector<float> tmp = mkanchor(ws, hs, x_ctr, y_ctr);
        result.push_back(tmp);
    }
    return result;
}

template <typename Dtype>
vector<float> RPNLayer<Dtype>::mkanchor(float w, float h, float x_ctr, float y_ctr){
    vector<float> tmp;
    tmp.push_back(x_ctr - 0.5*(w - 1));
    tmp.push_back(y_ctr - 0.5*(h - 1));
    tmp.push_back(x_ctr + 0.5*(w - 1));
    tmp.push_back(y_ctr + 0.5*(h - 1));
    return tmp;
}
template <typename Dtype>
vector<float> RPNLayer<Dtype>::whctrs(vector<float> anchor){
    vector<float> result;
    result.push_back(anchor[2] - anchor[0] + 1); //w
    result.push_back(anchor[3] - anchor[1] + 1); //h
    result.push_back((anchor[2] + anchor[0]) / 2); //ctrx
    result.push_back((anchor[3] + anchor[1]) / 2); //ctry
    return result;
}

/*template <typename Dtype>
cv::Mat RPNLayer<Dtype>::proposal_local_anchor(int width, int height)
{
    Blob<float> shift;
    cv::Mat shitf_x(height, width, CV_32SC1);
    cv::Mat shitf_y(height, width, CV_32SC1);
    for (size_t i = 0; i < width; i++)
    {
        for (size_t j = 0; j < height; j++)
        {
            shitf_x.at<int>(j, i) = i * feat_stride_;
            shitf_y.at<int>(j, i) = j * feat_stride_;
        }
    }
    shift.Reshape(anchors_nums_, width*height, 4,  1);
    float *p = shift.mutable_cpu_diff(), *a = shift.mutable_cpu_data();
    for (int i = 0; i < height*width; i++)
    {
        for (int j = 0; j < anchors_nums_; j++)
        {
            size_t num = i * 4 + j * 4 * height*width;
            p[num + 0] = -shitf_x.at<int>(i / shitf_x.cols, i % shitf_x.cols);
            p[num + 2] = -shitf_x.at<int>(i / shitf_x.cols, i % shitf_x.cols);
            p[num + 1] = -shitf_y.at<int>(i / shitf_y.cols, i % shitf_y.cols);
            p[num + 3] = -shitf_y.at<int>(i / shitf_y.cols, i % shitf_y.cols);
            a[num + 0] = anchors_[j * 4 + 0];
            a[num + 1] = anchors_[j * 4 + 1];
            a[num + 2] = anchors_[j * 4 + 2];
            a[num + 3] = anchors_[j * 4 + 3];
        }
    }
    shift.Update();
    cv::Mat loacl_anchors(anchors_nums_ * height*width, 4, CV_32FC1);
    size_t num = 0;
    for (int i = 0; i < height; ++i)
    {
        for (int j = 0; j < width; ++j)
        {
            for (int c = 0; c < anchors_nums_; ++c)
            {
                for (int k = 0; k < 4; ++k)
                {
                    loacl_anchors.at<float>((i*width + j)*anchors_nums_+c, k)= shift.data_at(c, i*width + j, k, 0);
                }
            }
        }
    }
    return loacl_anchors;
}*/

template <typename Dtype>
void RPNLayer<Dtype>::proposal_local_anchor(){
    int length = mymax(map_width_, map_height_);
    int step = map_width_*map_height_;
    int *map_m = new int[length];
    for (int i = 0; i < length; ++i)
    {
        map_m[i] = i*feat_stride_;
    }
    Dtype *shift_x = new Dtype[step];
    Dtype *shift_y = new Dtype[step];
    for (int i = 0; i < map_height_; ++i)
    {
        for (int j = 0; j < map_width_; ++j)
        {
            shift_x[i*map_width_ + j] = map_m[j];
            shift_y[i*map_width_ + j] = map_m[i];
        }
    }
    local_anchors_->Reshape(1, anchors_nums_ * 4, map_height_, map_width_);
    Dtype *a = local_anchors_->mutable_cpu_data();
    for (int i = 0; i < anchors_nums_; ++i)
    {
        caffe_set(step, Dtype(anchors_[i * 4 + 0]), a + (i * 4 + 0) *step);
        caffe_set(step, Dtype(anchors_[i * 4 + 1]), a + (i * 4 + 1) *step);
        caffe_set(step, Dtype(anchors_[i * 4 + 2]), a + (i * 4 + 2) *step);
        caffe_set(step, Dtype(anchors_[i * 4 + 3]), a + (i * 4 + 3) *step);
        caffe_axpy(step, Dtype(1), shift_x, a + (i * 4 + 0)*step);
        caffe_axpy(step, Dtype(1), shift_x, a + (i * 4 + 2)*step);
        caffe_axpy(step, Dtype(1), shift_y, a + (i * 4 + 1)*step);
        caffe_axpy(step, Dtype(1), shift_y, a + (i * 4 + 3)*step);
    }
}

template<typename Dtype>
void RPNLayer<Dtype>::filter_boxs(cv::Mat& pre_box, cv::Mat& score, vector<abox>& aboxes)
{
    float localMinSize=min_size_*src_scale_;
    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 >= localMinSize || heights >= localMinSize)
        {
            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);
        }
    }
}

template<typename Dtype>
void RPNLayer<Dtype>::filter_boxs(vector<abox>& aboxes)
{
    float localMinSize = min_size_*src_scale_;
    aboxes.clear();
    int map_width = m_box_->width();
    int map_height = m_box_->height();
    int map_channel = m_box_->channels();
    const Dtype *box = m_box_->cpu_data();
    const Dtype *score = m_score_->cpu_data();

    int step = 4 * map_height*map_width;
    int one_step = map_height*map_width;
    int offset_w, offset_h, offset_x, offset_y, offset_s;

    for (int h = 0; h < map_height; ++h)
    {
        for (int w = 0; w < map_width; ++w)
        {
            offset_x = h*map_width + w;
            offset_y = offset_x + one_step;
            offset_w = offset_y + one_step;
            offset_h = offset_w + one_step;
            offset_s = one_step*anchors_nums_+h*map_width + w;
            for (int c = 0; c < map_channel / 4; ++c)
            {
                Dtype width = box[offset_w], height = box[offset_h];
                if (width < localMinSize || height < localMinSize)
                {
                }
                else
                {
                    abox tmp;
                    tmp.batch_ind = 0;
                    tmp.x1 = box[offset_x] - 0.5*width;
                    tmp.y1 = box[offset_y] - 0.5*height;
                    tmp.x2 = box[offset_x] + 0.5*width;
                    tmp.y2 = box[offset_y] + 0.5*height;
                    tmp.x1 = mymin(mymax(tmp.x1, 0), src_width_);
                    tmp.y1 = mymin(mymax(tmp.y1, 0), src_height_);
                    tmp.x2 = mymin(mymax(tmp.x2, 0), src_width_);
                    tmp.y2 = mymin(mymax(tmp.y2, 0), src_height_);
                    tmp.score = score[offset_s];
                    aboxes.push_back(tmp);
                }
                offset_x += step;
                offset_y += step;
                offset_w += step;
                offset_h += step;
                offset_s += one_step;
            }
        }
    }
}

template<typename Dtype>
void RPNLayer<Dtype>::bbox_tranform_inv(){
    int channel = m_box_->channels();
    int height = m_box_->height();
    int width = m_box_->width();
    int step = height*width;
    Dtype * a = m_box_->mutable_cpu_data();
    Dtype * b = local_anchors_->mutable_cpu_data();
    for (int i = 0; i < channel / 4; ++i)
    {
        caffe_axpy(2*step, Dtype(-1), b + (i * 4 + 0)*step, b + (i * 4 + 2)*step);
        caffe_add_scalar(2 * step, Dtype(1), b + (i * 4 + 2)*step);
        caffe_axpy(2*step, Dtype(0.5), b + (i * 4 + 2)*step, b + (i * 4 + 0)*step);

        caffe_mul(2 * step, b + (i * 4 + 2)*step, a + (i * 4 + 0)*step, a + (i * 4 + 0)*step);
        caffe_add(2 * step, b + (i * 4 + 0)*step, a + (i * 4 + 0)*step, a + (i * 4 + 0)*step);

        caffe_exp(2*step, a + (i * 4 + 2)*step, a + (i * 4 + 2)*step);
        caffe_mul(2 * step, b + (i * 4 + 2)*step, a + (i * 4 + 2)*step, a + (i * 4 + 2)*step);
    }
}

template<typename Dtype>
void RPNLayer<Dtype>::nms(std::vector<abox> &input_boxes, float nms_thresh){
    std::vector<float>vArea(input_boxes.size());
    for (int i = 0; i < input_boxes.size(); ++i)
    {
        vArea[i] = (input_boxes.at(i).x2 - input_boxes.at(i).x1 + 1)
            * (input_boxes.at(i).y2 - input_boxes.at(i).y1 + 1);
    }
    for (int i = 0; i < input_boxes.size(); ++i)
    {
        for (int j = i + 1; j < input_boxes.size();)
        {
            float xx1 = std::max(input_boxes[i].x1, input_boxes[j].x1);
            float yy1 = std::max(input_boxes[i].y1, input_boxes[j].y1);
            float xx2 = std::min(input_boxes[i].x2, input_boxes[j].x2);
            float yy2 = std::min(input_boxes[i].y2, input_boxes[j].y2);
            float w = std::max(float(0), xx2 - xx1 + 1);
            float   h = std::max(float(0), yy2 - yy1 + 1);
            float   inter = w * h;
            float ovr = inter / (vArea[i] + vArea[j] - inter);
            if (ovr >= nms_thresh)
            {
                input_boxes.erase(input_boxes.begin() + j);
                vArea.erase(vArea.begin() + j);
            }
            else
            {
                j++;
            }
        }
    }
}

template <typename Dtype>
void RPNLayer<Dtype>::Forward_cpu(
    const vector<Blob<Dtype>*>& bottom,
    const vector<Blob<Dtype>*>& top) {

    map_width_ = bottom[1]->width();
    map_height_ = bottom[1]->height();
    //int channels = bottom[1]->channels();

    //get boxs_delta,向右。
    m_box_->CopyFrom(*(bottom[1]), false, true);
    /*cv::Mat boxs_delta(height*width*anchors_nums_, 4, CV_32FC1);
    for (int i = 0; i < height; ++i)
    {
        for (int j = 0; j < width; ++j)
        {
            for (int k = 0; k < anchors_nums_; ++k)
            {
                for (int c = 0; c < 4; ++c)
                {
                    boxs_delta.at<float>((i*width + j)*anchors_nums_ + k, c) = bottom[1]->data_at(0, k*4 + c, i, j);
                }
            }
        }
    }*/

    //get sores 向右，前面anchors_nums_個位bg的得分，後面anchors_nums_為fg得分，我們需要的是後面的。
    m_score_->CopyFrom(*(bottom[0]),false,true);

    /*cv::Mat scores(height*width*anchors_nums_, 1, CV_32FC1);
    for (int i = 0; i < height; ++i)
    {
        for (int j = 0; j < width; ++j)
        {
            for (int k = 0; k < anchors_nums_; ++k)
            {
                scores.at<float>((i*width + j)*anchors_nums_+k, 0) = bottom[0]->data_at(0, k + anchors_nums_, i, j);
            }
        }
    }*/

    //get im_info

    src_height_ = bottom[2]->data_at(0, 0,0,0);
    src_width_ = bottom[2]->data_at(0, 1,0,0);
    src_scale_ = bottom[2]->data_at(0, 2, 0, 0);

    //gen local anchors 向右

    proposal_local_anchor();
    //cv::Mat local_anchors = proposal_local_anchor(width, height);

    //Convert anchors into proposals via bbox transformations

    bbox_tranform_inv();

    /*for (int i = 0; i < pre_box.rows; ++i)
    {
        if (pre_box.at<float>(i, 0) < 0)    pre_box.at<float>(i, 0) = 0;
        if (pre_box.at<float>(i, 0) > (src_width_ - 1)) pre_box.at<float>(i, 0) = src_width_ - 1;
        if (pre_box.at<float>(i, 2) < 0)    pre_box.at<float>(i, 2) = 0;
        if (pre_box.at<float>(i, 2) > (src_width_ - 1)) pre_box.at<float>(i, 2) = src_width_ - 1;
        if (pre_box.at<float>(i, 1) < 0)    pre_box.at<float>(i, 1) = 0;
        if (pre_box.at<float>(i, 1) > (src_height_ - 1))    pre_box.at<float>(i, 1) = src_height_ - 1;
        if (pre_box.at<float>(i, 3) < 0)    pre_box.at<float>(i, 3) = 0;
        if (pre_box.at<float>(i, 3) > (src_height_ - 1))    pre_box.at<float>(i, 3) = src_height_ - 1;
    }*/
    vector<abox>aboxes;

    filter_boxs(aboxes);

    //clock_t start, end;
    //start = clock();
    std::sort(aboxes.rbegin(), aboxes.rend()); //降序
    if (pre_nms_topN_ > 0)
    {
        int tmp = mymin(pre_nms_topN_, aboxes.size());
        aboxes.erase(aboxes.begin() + tmp, aboxes.end());
    }

    nms(aboxes,nms_thresh_);
    //end = clock();
    //std::cout << "sort nms:" << (double)(end - start) / CLOCKS_PER_SEC << std::endl;
    if (post_nms_topN_ > 0)
    {
        int tmp = mymin(post_nms_topN_, aboxes.size());
        aboxes.erase(aboxes.begin() + tmp, aboxes.end());
    }
    top[0]->Reshape(aboxes.size(),5,1,1);
    Dtype *top0 = top[0]->mutable_cpu_data();
    for (int i = 0; i < aboxes.size(); ++i)
    {
        //caffe_copy(aboxes.size() * 5, (Dtype*)aboxes.data(), top0);
        top0[0] = aboxes[i].batch_ind;
        top0[1] = aboxes[i].x1;
        top0[2] = aboxes[i].y1; 
        top0[3] = aboxes[i].x2;
        top0[4] = aboxes[i].y2;
        top0 += top[0]->offset(1);
    }
    if (top.size()>1)
    {
        top[1]->Reshape(aboxes.size(), 1,1,1);
        Dtype *top1 = top[1]->mutable_cpu_data();
        for (int i = 0; i < aboxes.size(); ++i)
        {
            top1[0] = aboxes[i].score;
            top1 += top[1]->offset(1);
        }
    }   
}

#ifdef CPU_ONLY
STUB_GPU(RPNLayer);
#endif

INSTANTIATE_CLASS(RPNLayer);
REGISTER_LAYER_CLASS(RPN);

} // namespace caffe

（2） 添加自定義層 roi_pooling_layer.hpp 把它放在 caffe/include/caffe/layers/ 目錄下

#ifndef CAFFE_ROI_POOLING_LAYERHPP
#define CAFFE_ROI_POOLING_LAYERHPP

#include <vector>

#include "caffe/blob.hpp"
#include "caffe/common.hpp"
#include "caffe/layer.hpp"
#include "caffe/proto/caffe.pb.h"

namespace caffe {

/**

• @brief Perform max pooling on regions of interest specified by input, takes
• as input N feature maps and a list of R regions of interest.
• ROIPoolingLayer takes 2 inputs and produces 1 output. bottom[0] is
• [N x C x H x W] feature maps on which pooling is performed. bottom[1] is
• [R x 5] containing a list R ROI tuples with batch index and coordinates of
• regions of interest. Each row in bottom[1] is a ROI tuple in format
• [batch_index x1 y1 x2 y2], where batch_index corresponds to the index of
• instance in the first input and x1 y1 x2 y2 are 0-indexed coordinates
• of ROI rectangle (including its boundaries).
• For each of the R ROIs, max-pooling is performed over pooled_h x pooled_w
• output bins (specified in roi_pooling_param). The pooling bin sizes are
• adaptively set such that they tile ROI rectangle in the indexed feature
• map. The pooling region of vertical bin ph in [0, pooled_h) is computed as
• start_ph (included) = y1 + floor(ph * (y2 - y1 + 1) / pooled_h)
• end_ph (excluded) = y1 + ceil((ph + 1) * (y2 - y1 + 1) / pooled_h)
• and similar horizontal bins.
• @param param provides ROIPoolingParameter roi_pooling_param,
• with ROIPoolingLayer options:
• • pooled_h. The pooled output height.
• • pooled_w. The pooled output width
• • spatial_scale. Multiplicative spatial scale factor to translate ROI
• coordinates from their input scale to the scale used when pooling.
• Fast R-CNN
• Written by Ross Girshick
  */

template <typename Dtype>
class ROIPoolingLayer : public Layer<Dtype> {
public:
explicit ROIPoolingLayer(const LayerParameter& param)
: Layer<Dtype>(param) {}
virtual void LayerSetUp(const vector<Blob<Dtype>>& bottom,
const vector<Blob<Dtype>>& top);
virtual void Reshape(const vector<Blob<Dtype>>& bottom,
const vector<Blob<Dtype>>& top);

virtual inline const char* type() const { return "ROIPooling"; }

virtual inline int MinBottomBlobs() const { return 2; }
virtual inline int MaxBottomBlobs() const { return 2; }
virtual inline int MinTopBlobs() const { return 1; }
virtual inline int MaxTopBlobs() const { return 1; }

protected:
virtual void Forward_cpu(const vector<Blob<Dtype>>& bottom,
const vector<Blob<Dtype>>& top);
virtual void Forward_gpu(const vector<Blob<Dtype>>& bottom,
const vector<Blob<Dtype>>& top);
virtual void Backward_cpu(const vector<Blob<Dtype>>& top,
const vector<bool>& propagate_down, const vector<Blob<Dtype>>& bottom);
virtual void Backward_gpu(const vector<Blob<Dtype>>& top,
const vector<bool>& propagate_down, const vector<Blob<Dtype>>& bottom);

int channels;
int height;
int width_;
int pooledheight;
int pooledwidth;
Dtype spatialscale;
Blob<int> maxidx;
};

} // namespace caffe

#endif // CAFFE_ROI_POOLING_LAYERHPP
然後是源文件 roi_pooling_layer.cpp 以及cuda版的roi_pooling_layer.cu 放在 caffe/src/caffe/layers/ 目錄下
#include <algorithm>
#include <cfloat>
#include <vector>

#include "caffe/layers/roi_pooling_layer.hpp"

using std::max;
using std::min;
using std::floor;
using std::ceil;

namespace caffe {

template <typename Dtype>
void ROIPoolingLayer<Dtype>::LayerSetUp(const vector<Blob<Dtype>>& bottom,
const vector<Blob<Dtype>>& top) {
ROIPoolingParameter roi_pool_param = this->layerparam.roi_pooling_param();
CHECK_GT(roi_pool_param.pooled_h(), 0)
<< "pooled_h must be > 0";
CHECK_GT(roi_pool_param.pooled_w(), 0)
<< "pooled_w must be > 0";
pooledheight = roi_pool_param.pooled_h();
pooledwidth = roi_pool_param.pooled_w();
spatialscale = roi_pool_param.spatial_scale();
LOG(INFO) << "Spatial scale: " << spatialscale;
}

template <typename Dtype>
void ROIPoolingLayer<Dtype>::Reshape(const vector<Blob<Dtype>>& bottom,
const vector<Blob<Dtype>>& top) {
channels = bottom[0]->channels();
height = bottom[0]->height();
width = bottom[0]->width();
top[0]->Reshape(bottom[1]->num(), channels, pooledheight,
pooledwidth);
maxidx.Reshape(bottom[1]->num(), channels_, pooledheight,
pooledwidth);
}

template <typename Dtype>
void ROIPoolingLayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>>& bottom,
const vector<Blob<Dtype>>& top) {
const Dtype bottom_data = bottom[0]->cpu_data();
const Dtype bottom_rois = bottom[1]->cpu_data();
// Number of ROIs
int num_rois = bottom[1]->num();
int batch_size = bottom[0]->num();
int top_count = top[0]->count();
Dtype top_data = top[0]->mutable_cpu_data();
caffe_set(top_count, Dtype(-FLT_MAX), top_data);
int argmax_data = maxidx.mutable_cpu_data();
caffe_set(top_count, -1, argmax_data);

// For each ROI R = [batch_index x1 y1 x2 y2]: max pool over R
for (int n = 0; n < num_rois; ++n) {
int roi_batch_ind = bottom_rois[0];
int roi_start_w = round(bottom_rois[1] spatialscale);
int roi_start_h = round(bottom_rois[2] spatialscale);
int roi_end_w = round(bottom_rois[3] spatialscale);
int roi_end_h = round(bottom_rois[4] spatialscale);
CHECK_GE(roi_batch_ind, 0);
CHECK_LT(roi_batch_ind, batch_size);

int roi_height = max(roi_end_h - roi_start_h + 1, 1);
int roi_width = max(roi_end_w - roi_start_w + 1, 1);
const Dtype bin_size_h = static_cast<Dtype>(roi_height)
                         / static_cast<Dtype>(pooled_height_);
const Dtype bin_size_w = static_cast<Dtype>(roi_width)
                         / static_cast<Dtype>(pooled_width_);

const Dtype* batch_data = bottom_data + bottom[0]->offset(roi_batch_ind);

for (int c = 0; c < channels_; ++c) {
  for (int ph = 0; ph < pooled_height_; ++ph) {
    for (int pw = 0; pw < pooled_width_; ++pw) {
      // Compute pooling region for this output unit:
      //  start (included) = floor(ph * roi_height / pooled_height_)
      //  end (excluded) = ceil((ph + 1) * roi_height / pooled_height_)
      int hstart = static_cast<int>(floor(static_cast<Dtype>(ph)
                                          * bin_size_h));
      int wstart = static_cast<int>(floor(static_cast<Dtype>(pw)
                                          * bin_size_w));
      int hend = static_cast<int>(ceil(static_cast<Dtype>(ph + 1)
                                       * bin_size_h));
      int wend = static_cast<int>(ceil(static_cast<Dtype>(pw + 1)
                                       * bin_size_w));

      hstart = min(max(hstart + roi_start_h, 0), height_);
      hend = min(max(hend + roi_start_h, 0), height_);
      wstart = min(max(wstart + roi_start_w, 0), width_);
      wend = min(max(wend + roi_start_w, 0), width_);

      bool is_empty = (hend <= hstart) || (wend <= wstart);

      const int pool_index = ph * pooled_width_ + pw;
      if (is_empty) {
        top_data[pool_index] = 0;
        argmax_data[pool_index] = -1;
      }

      for (int h = hstart; h < hend; ++h) {
        for (int w = wstart; w < wend; ++w) {
          const int index = h * width_ + w;
          if (batch_data[index] > top_data[pool_index]) {
            top_data[pool_index] = batch_data[index];
            argmax_data[pool_index] = index;
          }
        }
      }
    }
  }
  // Increment all data pointers by one channel
  batch_data += bottom[0]->offset(0, 1);
  top_data += top[0]->offset(0, 1);
  argmax_data += max_idx_.offset(0, 1);
}
// Increment ROI data pointer
bottom_rois += bottom[1]->offset(1);

}
}

template <typename Dtype>
void ROIPoolingLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>>& top,
const vector<bool>& propagate_down, const vector<Blob<Dtype>>& bottom) {
if (propagate_down[1]) {
LOG(FATAL) << this->type()
<< " Layer cannot backpropagate to roi inputs.";
}
if (!propagate_down[0]) {
return;
}
const Dtype bottom_rois = bottom[1]->cpu_data();
const Dtype top_diff = top[0]->cpu_diff();
Dtype bottom_diff = bottom[0]->mutable_cpu_diff();
caffe_set(bottom[0]->count(), Dtype(0.), bottom_diff);
const int argmax_data = maxidx.cpu_data();
const int num_rois = top[0]->num();

// Accumulate gradient over all ROIs
for (int roi_n = 0; roi_n < num_rois; ++roi_n) {
int roi_batch_ind = bottom_rois[roin * 5];
// Accumulate gradients over each bin in this ROI
for (int c = 0; c < channels; ++c) {
for (int ph = 0; ph < pooledheight; ++ph) {
for (int pw = 0; pw < pooledwidth; ++pw) {
int offset_top = ((roin * channels + c) * pooledheight + ph)

• pooledwidth + pw;
  int argmax_index = argmax_data[offset_top];
  if (argmax_index >= 0) {
  int offset_bottom = (roi_batchind * channels + c) * height_
  • width_ + argmax_index;
    bottom_diff[offset_bottom] += top_diff[offset_top];
    }
    }
    }
    }
    }
    }

#ifdef CPU_ONLY
STUB_GPU(ROIPoolingLayer);
#endif

INSTANTIATE_CLASS(ROIPoolingLayer);
REGISTER_LAYER_CLASS(ROIPooling);

} // namespace caffe

#include <algorithm>
#include <cfloat>
#include <vector>

#include "caffe/layers/roi_pooling_layer.hpp"

using std::max;
using std::min;

namespace caffe {

template <typename Dtype>
global void ROIPoolForward(const int nthreads, const Dtype bottom_data,
const Dtype spatial_scale, const int channels, const int height,
const int width, const int pooled_height, const int pooled_width,
const Dtype bottom_rois, Dtype top_data, int argmax_data) {
CUDA_KERNEL_LOOP(index, nthreads) {
// (n, c, ph, pw) is an element in the pooled output
int pw = index % pooled_width;
int ph = (index / pooled_width) % pooled_height;
int c = (index / pooled_width / pooled_height) % channels;
int n = index / pooled_width / pooled_height / channels;

bottom_rois += n * 5;
int roi_batch_ind = bottom_rois[0];
int roi_start_w = round(bottom_rois[1] * spatial_scale);
int roi_start_h = round(bottom_rois[2] * spatial_scale);
int roi_end_w = round(bottom_rois[3] * spatial_scale);
int roi_end_h = round(bottom_rois[4] * spatial_scale);

// Force malformed ROIs to be 1x1
int roi_width = max(roi_end_w - roi_start_w + 1, 1);
int roi_height = max(roi_end_h - roi_start_h + 1, 1);
Dtype bin_size_h = static_cast<Dtype>(roi_height)
                   / static_cast<Dtype>(pooled_height);
Dtype bin_size_w = static_cast<Dtype>(roi_width)
                   / static_cast<Dtype>(pooled_width);

int hstart = static_cast<int>(floor(static_cast<Dtype>(ph)
                                    * bin_size_h));
int wstart = static_cast<int>(floor(static_cast<Dtype>(pw)
                                    * bin_size_w));
int hend = static_cast<int>(ceil(static_cast<Dtype>(ph + 1)
                                 * bin_size_h));
int wend = static_cast<int>(ceil(static_cast<Dtype>(pw + 1)
                                 * bin_size_w));

// Add roi offsets and clip to input boundaries
hstart = min(max(hstart + roi_start_h, 0), height);
hend = min(max(hend + roi_start_h, 0), height);
wstart = min(max(wstart + roi_start_w, 0), width);
wend = min(max(wend + roi_start_w, 0), width);
bool is_empty = (hend <= hstart) || (wend <= wstart);

// Define an empty pooling region to be zero
Dtype maxval = is_empty ? 0 : -FLT_MAX;
// If nothing is pooled, argmax = -1 causes nothing to be backprop‘d
int maxidx = -1;
bottom_data += (roi_batch_ind * channels + c) * height * width;
for (int h = hstart; h < hend; ++h) {
  for (int w = wstart; w < wend; ++w) {
    int bottom_index = h * width + w;
    if (bottom_data[bottom_index] > maxval) {
      maxval = bottom_data[bottom_index];
      maxidx = bottom_index;
    }
  }
}
top_data[index] = maxval;
argmax_data[index] = maxidx;

}
}

template <typename Dtype>
void ROIPoolingLayer<Dtype>::Forward_gpu(const vector<Blob<Dtype>>& bottom,
const vector<Blob<Dtype>>& top) {
const Dtype bottom_data = bottom[0]->gpu_data();
const Dtype bottom_rois = bottom[1]->gpu_data();
Dtype top_data = top[0]->mutable_gpu_data();
int argmax_data = maxidx.mutable_gpu_data();
int count = top[0]->count();
// NOLINT_NEXT_LINE(whitespace/operators)
ROIPoolForward<Dtype><<<CAFFE_GET_BLOCKS(count), CAFFE_CUDA_NUM_THREADS>>>(
count, bottom_data, spatialscale, channels, height, width_,
pooledheight, pooledwidth, bottom_rois, top_data, argmax_data);
CUDA_POST_KERNEL_CHECK;
}

template <typename Dtype>
global void ROIPoolBackward(const int nthreads, const Dtype top_diff,
const int argmax_data, const int num_rois, const Dtype spatial_scale,
const int channels, const int height, const int width,
const int pooled_height, const int pooled_width, Dtype bottom_diff,
const Dtype bottom_rois) {
CUDA_KERNEL_LOOP(index, nthreads) {
// (n, c, h, w) coords in bottom data
int w = index % width;
int h = (index / width) % height;
int c = (index / width / height) % channels;
int n = index / width / height / channels;

Dtype gradient = 0;
// Accumulate gradient over all ROIs that pooled this element
for (int roi_n = 0; roi_n < num_rois; ++roi_n) {
  const Dtype* offset_bottom_rois = bottom_rois + roi_n * 5;
  int roi_batch_ind = offset_bottom_rois[0];
  // Skip if ROI‘s batch index doesn‘t match n
  if (n != roi_batch_ind) {
    continue;
  }

  int roi_start_w = round(offset_bottom_rois[1] * spatial_scale);
  int roi_start_h = round(offset_bottom_rois[2] * spatial_scale);
  int roi_end_w = round(offset_bottom_rois[3] * spatial_scale);
  int roi_end_h = round(offset_bottom_rois[4] * spatial_scale);

  // Skip if ROI doesn‘t include (h, w)
  const bool in_roi = (w >= roi_start_w && w <= roi_end_w &&
                       h >= roi_start_h && h <= roi_end_h);
  if (!in_roi) {
    continue;
  }

  int offset = (roi_n * channels + c) * pooled_height * pooled_width;
  const Dtype* offset_top_diff = top_diff + offset;
  const int* offset_argmax_data = argmax_data + offset;

  // Compute feasible set of pooled units that could have pooled
  // this bottom unit

  // Force malformed ROIs to be 1x1
  int roi_width = max(roi_end_w - roi_start_w + 1, 1);
  int roi_height = max(roi_end_h - roi_start_h + 1, 1);

  Dtype bin_size_h = static_cast<Dtype>(roi_height)
                     / static_cast<Dtype>(pooled_height);
  Dtype bin_size_w = static_cast<Dtype>(roi_width)
                     / static_cast<Dtype>(pooled_width);

  int phstart = floor(static_cast<Dtype>(h - roi_start_h) / bin_size_h);
  int phend = ceil(static_cast<Dtype>(h - roi_start_h + 1) / bin_size_h);
  int pwstart = floor(static_cast<Dtype>(w - roi_start_w) / bin_size_w);
  int pwend = ceil(static_cast<Dtype>(w - roi_start_w + 1) / bin_size_w);

  phstart = min(max(phstart, 0), pooled_height);
  phend = min(max(phend, 0), pooled_height);
  pwstart = min(max(pwstart, 0), pooled_width);
  pwend = min(max(pwend, 0), pooled_width);

  for (int ph = phstart; ph < phend; ++ph) {
    for (int pw = pwstart; pw < pwend; ++pw) {
      if (offset_argmax_data[ph * pooled_width + pw] == (h * width + w)) {
        gradient += offset_top_diff[ph * pooled_width + pw];
      }
    }
  }
}
bottom_diff[index] = gradient;

}
}

template <typename Dtype>
void ROIPoolingLayer<Dtype>::Backward_gpu(const vector<Blob<Dtype>>& top,
const vector<bool>& propagate_down, const vector<Blob<Dtype>>& bottom) {
if (!propagate_down[0]) {
return;
}
const Dtype bottom_rois = bottom[1]->gpu_data();
const Dtype top_diff = top[0]->gpu_diff();
Dtype bottom_diff = bottom[0]->mutable_gpu_diff();
const int count = bottom[0]->count();
caffe_gpu_set(count, Dtype(0.), bottom_diff);
const int argmax_data = maxidx.gpu_data();
// NOLINT_NEXT_LINE(whitespace/operators)
ROIPoolBackward<Dtype><<<CAFFE_GET_BLOCKS(count), CAFFE_CUDA_NUM_THREADS>>>(
count, top_diff, argmax_data, top[0]->num(), spatialscale, channels,
height, width_, pooledheight, pooledwidth, bottom_diff, bottom_rois);
CUDA_POST_KERNEL_CHECK;
}

INSTANTIATE_LAYER_GPU_FUNCS(ROIPoolingLayer);

} // namespace caffe

（3） 好了，代碼添加完畢，現在在caffe/src/caffe/proto/caffe.proto 中聲明這兩個類
根據你自己的可用ID 在message Layer中添加這兩個類，我的已經添加了，大概是這樣的，千萬記住大小寫！

// NOTE
// Update the next available ID when you add a new LayerParameter field.
// LayerParameter next available layer-specific ID: 152 (last added: rpn_param roi_pooling_param)
optional RPNParameter rpn_param = 150; //
optional ROIPoolingParameter roi_pooling_param = 151; // roi pooling Faster-Rcnn
這裏寫好後，因為這兩個層都有內置的參數，還得在這個文件的最末尾，定義具體的參數
message ROIPoolingParameter {
optional uint32 pooled_h = 1 [default = 0];
optional uint32 pooled_w = 2 [default = 0];
optional float spatial_scale = 3 [default = 1];
}
message RPNParameter {
optional uint32 feat_stride = 1;
optional uint32 basesize = 2;
repeated uint32 scale = 3;
repeated float ratio = 4;
optional uint32 boxminsize =5;
optional uint32 per_nms_topn = 9;
optional uint32 post_nms_topn = 11;
optional float nms_thresh = 8;
}

（4） 因為自定義層使用了RPN層，為了以後程序中各處都能使用該層，所以得在common.hpp和common.cpp文件的最末尾，添加對應的代碼，註意這裏的namespace RPN是和namespace caffe同一級的
頭文件common.hpp裏添加

namespace RPN{
struct abox
{
float x1;
float y1;
float x2;
float y2;
float score;
bool operator <(const abox&tmp) const{
return score < tmp.score;
}
};
void nms(std::vector<abox>& input_boxes,float nms_thresh);
cv::Mat bbox_tranform_inv(cv::Mat, cv::Mat);
} // namespace RPN
源文件common.cpp裏，為了防止說找不到cv::Mat類型的錯誤，添加opencv頭文件

#include<opencv2/opencv.hpp>

using namespace cv;

namespace RPN{
cv::Mat bbox_tranform_inv(cv::Mat local_anchors, cv::Mat boxs_delta){
cv::Mat pre_box(local_anchors.rows, local_anchors.cols, CV_32FC1);
for (int i = 0; i < local_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 = local_anchors.at<float>(i, 2) - local_anchors.at<float>(i, 0) + 1;
src_h = local_anchors.at<float>(i, 3) - local_anchors.at<float>(i, 1) + 1;
src_ctr_x = local_anchors.at<float>(i, 0) + 0.5 src_w;
src_ctr_y = local_anchors.at<float>(i, 1) + 0.5 src_h;

        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;
        pre_box.at<float>(i, 1) = pred_ctr_y - 0.5*pred_h;
        pre_box.at<float>(i, 2) = pred_ctr_x + 0.5*pred_w;
        pre_box.at<float>(i, 3) = pred_ctr_y + 0.5*pred_h;
    }
    return pre_box;
}
void nms(std::vector<abox> &input_boxes, float nms_thresh){
    std::vector<float>vArea(input_boxes.size());
    for (int i = 0; i < input_boxes.size(); ++i)
    {
        vArea[i] = (input_boxes.at(i).x2 - input_boxes.at(i).x1 + 1)
            * (input_boxes.at(i).y2 - input_boxes.at(i).y1 + 1);
    }
    for (int i = 0; i < input_boxes.size(); ++i)
    {
        for (int j = i + 1; j < input_boxes.size();)
        {
            float xx1 = std::max(input_boxes[i].x1, input_boxes[j].x1);
            float yy1 = std::max(input_boxes[i].y1, input_boxes[j].y1);
            float xx2 = std::min(input_boxes[i].x2, input_boxes[j].x2);
            float yy2 = std::min(input_boxes[i].y2, input_boxes[j].y2);
            float w = std::max(float(0), xx2 - xx1 + 1);
            float   h = std::max(float(0), yy2 - yy1 + 1);
            float   inter = w * h;
            float ovr = inter / (vArea[i] + vArea[j] - inter);
            if (ovr >= nms_thresh)
            {
                input_boxes.erase(input_boxes.begin() + j);
                vArea.erase(vArea.begin() + j);
            }
            else
            {
                j++;
            }
        }
    }
}

}

（5）好了，配置弄完了，回到caffe根目錄下，

make clean

make all -j

開始編譯吧！

可能會出現什麽找不到pb.h文件什麽的，那就繼續執行 make -j5 可能是因為編譯的線程太多導致先後順序什麽的。 我也是猜的，反正我是這麽解決的。

（6）環境已經配置好了，現在我們再加個類，用來對圖片進行檢測吧！編寫頭文件ObjectDetector.hpp

#ifndef OBJECTDETECTOR_H
#define OBJECTDETECTOR_H

#define INPUT_SIZE_NARROW 600
#define INPUT_SIZE_LONG 1000

#include <string>
#include <caffe/net.hpp>
#include <caffe/common.hpp>
#include <opencv2/core/core.hpp>
#include <iostream>
#include <memory>
#include <map>

using namespace std;

class ObjectDetector
{
public:

  ObjectDetector(const std::string &model_file, const std::string &weights_file);  //構造函數
//對一張圖片，進行檢測，將結果保存進map數據結構裏,分別表示每個類別對應的目標框，如果需要分數信息，則計算分數
  map<int,vector<cv::Rect> > detect(const cv::Mat& image, map<int,vector<float> >* score=NULL);   

private:
boost::sharedptr< caffe::Net<float> > net;
int classnum; //類別數+1 ,官方給的demo 是20+1類
};

#endif
源文件ObjectDetector.cpp
#include "ObjectDetector.hpp"
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <vector>
#include <fstream>

using std::string;
using std::vector;
using namespace caffe;
using std::max;
using std::min;

ObjectDetector::ObjectDetector(const std::string &model_file,const std::string &weights_file){
#ifdef CPU_ONLY
Caffe::set_mode(Caffe::CPU);
#else
Caffe::setmode(Caffe::GPU);
#endif
net.reset(new Net<float>(modelfile, TEST));
net->CopyTrainedLayersFrom(weights_file);
this->classnum = net_->blob_by_name("cls_prob")->channels(); //求得類別數+1
}

//對一張圖片，進行檢測，將結果保存進map數據結構裏,分別表示每個類別對應的目標框，如果需要分數信息，則計算分數
map<int,vector<cv::Rect> > ObjectDetector::detect(const cv::Mat& image,map<int,vector<float> >* objectScore){

if(objectScore!=NULL)   //如果需要保存置信度
    objectScore->clear();

float CONF_THRESH = 0.8;  //置信度閾值
float NMS_THRESH = 0.3;   //非極大值抑制閾值
int max_side = max(image.rows, image.cols);   //分別求出圖片寬和高的較大者
int min_side = min(image.rows, image.cols);
float max_side_scale = float(max_side) / float(INPUT_SIZE_LONG);    //分別求出縮放因子
float min_side_scale = float(min_side) / float(INPUT_SIZE_NARROW);
float max_scale = max(max_side_scale, min_side_scale);

float img_scale = float(1) / max_scale;
int height = int(image.rows * img_scale);
int width = int(image.cols * img_scale);

int num_out;
cv::Mat cv_resized;
image.convertTo(cv_resized, CV_32FC3);
cv::resize(cv_resized, cv_resized, cv::Size(width, height)); 
cv::Mat mean(height, width, cv_resized.type(), cv::Scalar(102.9801, 115.9465, 122.7717));
cv::Mat normalized;
subtract(cv_resized, mean, normalized);

float im_info[3];
im_info[0] = height;
im_info[1] = width;
im_info[2] = img_scale;
shared_ptr<Blob<float> > input_layer = net_->blob_by_name("data");
input_layer->Reshape(1, normalized.channels(), height, width);
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(height, width, CV_32FC1, input_data);
    input_channels.push_back(channel);
    input_data += height * width;
}
cv::split(normalized, input_channels);
net_->blob_by_name("im_info")->set_cpu_data(im_info);
net_->Forward();                                       //進行網絡前向傳播

int num = net_->blob_by_name("rois")->num();    //產生的 ROI 個數,比如為 13949個ROI
const float *rois_data = net_->blob_by_name("rois")->cpu_data();    //維度比如為：13949*5*1*1
int num1 = net_->blob_by_name("bbox_pred")->num();   //預測的矩形框 維度為 13949*84
cv::Mat rois_box(num, 4, CV_32FC1);
for (int i = 0; i < num; ++i)
{
    rois_box.at<float>(i, 0) = rois_data[i * 5 + 1] / img_scale;
    rois_box.at<float>(i, 1) = rois_data[i * 5 + 2] / img_scale;
    rois_box.at<float>(i, 2) = rois_data[i * 5 + 3] / img_scale;
    rois_box.at<float>(i, 3) = rois_data[i * 5 + 4] / img_scale;
}

shared_ptr<Blob<float> > bbox_delt_data = net_->blob_by_name("bbox_pred");   // 13949*84
shared_ptr<Blob<float> > score = net_->blob_by_name("cls_prob");             // 3949*21

map<int,vector<cv::Rect> > label_objs;    //每個類別，對應的檢測目標框
for (int i = 1; i < class_num_; ++i){     //對每個類，進行遍歷
    cv::Mat bbox_delt(num, 4, CV_32FC1);
    for (int j = 0; j < num; ++j){
        bbox_delt.at<float>(j, 0) = bbox_delt_data->data_at(j, i * 4 + 0, 0, 0);
        bbox_delt.at<float>(j, 1) = bbox_delt_data->data_at(j, i * 4 + 1, 0, 0);
        bbox_delt.at<float>(j, 2) = bbox_delt_data->data_at(j, i * 4 + 2, 0, 0);
        bbox_delt.at<float>(j, 3) = bbox_delt_data->data_at(j, i * 4 + 3, 0, 0);
    }
    cv::Mat box_class = RPN::bbox_tranform_inv(rois_box, bbox_delt);

    vector<RPN::abox> aboxes;   //對於 類別i，檢測出的矩形框保存在這
    for (int j = 0; j < box_class.rows; ++j){
        if (box_class.at<float>(j, 0) < 0)  box_class.at<float>(j, 0) = 0;
        if (box_class.at<float>(j, 0) > (image.cols - 1))   box_class.at<float>(j, 0) = image.cols - 1;
        if (box_class.at<float>(j, 2) < 0)  box_class.at<float>(j, 2) = 0;
        if (box_class.at<float>(j, 2) > (image.cols - 1))   box_class.at<float>(j, 2) = image.cols - 1;

        if (box_class.at<float>(j, 1) < 0)  box_class.at<float>(j, 1) = 0;
        if (box_class.at<float>(j, 1) > (image.rows - 1))   box_class.at<float>(j, 1) = image.rows - 1;
        if (box_class.at<float>(j, 3) < 0)  box_class.at<float>(j, 3) = 0;
        if (box_class.at<float>(j, 3) > (image.rows - 1))   box_class.at<float>(j, 3) = image.rows - 1;
        RPN::abox tmp;
        tmp.x1 = box_class.at<float>(j, 0);
        tmp.y1 = box_class.at<float>(j, 1);
        tmp.x2 = box_class.at<float>(j, 2);
        tmp.y2 = box_class.at<float>(j, 3);
        tmp.score = score->data_at(j, i, 0, 0);
        aboxes.push_back(tmp);
    }
    std::sort(aboxes.rbegin(), aboxes.rend());
    RPN::nms(aboxes, NMS_THRESH);  //與非極大值抑制消除對於的矩形框
    for (int k = 0; k < aboxes.size();){
        if (aboxes[k].score < CONF_THRESH)
            aboxes.erase(aboxes.begin() + k);
        else
            k++;
    }
    //################ 將類別i的所有檢測框，保存
    vector<cv::Rect> rect(aboxes.size());    //對於類別i，檢測出的矩形框
    for(int ii=0;ii<aboxes.size();++ii)
        rect[ii]=cv::Rect(cv::Point(aboxes[ii].x1,aboxes[ii].y1),cv::Point(aboxes[ii].x2,aboxes[ii].y2));
    label_objs[i]=rect;   
    //################ 將類別i的所有檢測框的打分，保存
    if(objectScore!=NULL){           //################ 將類別i的所有檢測框的打分，保存
        vector<float> tmp(aboxes.size());       //對於 類別i，檢測出的矩形框的得分
        for(int ii=0;ii<aboxes.size();++ii)
            tmp[ii]=aboxes[ii].score;
        objectScore->insert(pair<int,vector<float> >(i,tmp));
    }
}
return label_objs;

}

這裏的代碼，是在參考博客中的代碼，我改了下，加了自己的需求。這裏的函數返回的是一個map對象，每一個鍵（類別label），對應一個矩形框向量。比如，一個20類檢測任務，而一張圖片裏有3個人（標簽是1），和2輛車（標簽是5），那函數會返回一個map，其中有兩個鍵值對，鍵1對應的值是一個3維的矩形框向量，分別代表著3個人的矩形框；鍵5對應的值是一個2維的矩形框向量，分別代表的是2輛車的矩形框。同時，函數還接受一個可選參數，可以返回每個矩形框各自對應的置信度。
Ok，現在我們寫個主函數，測試下效果吧，我們建個文件夾，首先把網絡描述文件test.prototxt拷貝過來，這裏我用的是VGG16的，end2end的網絡，路徑是py-faster-rcnn/models/pascal_voc/VGG16/faster_rcnn_end2end/test.prototxt，Ok，拷貝過來，因為我們不需要python層了，那我們打開這個文件，定位到 Python層，

layer {
name: ‘proposal‘
type: ‘Python‘
bottom: ‘rpn_cls_prob_reshape‘
bottom: ‘rpn_bbox_pred‘
bottom: ‘im_info‘
top: ‘rois‘
python_param {
module: ‘rpn.proposal_layer‘
layer: ‘ProposalLayer‘
param_str: "‘feat_stride‘: 16"
}
}
把它修改為
layer {
name: "proposal"
type: "RPN"
bottom: "rpn_cls_prob_reshape"
bottom: "rpn_bbox_pred"
bottom: "im_info"
top: "rois"
rpn_param {
feat_stride : 16
basesize : 16
scale : 8
scale : 16
scale : 32
ratio : 0.5
ratio : 1
ratio : 2
boxminsize :16
per_nms_topn : 0;
post_nms_topn : 0;
nms_thresh : 0.3
}
}
是的，這裏的一系列參數，可以自己設置的，大家可以嘗試下
然後，我們需要一個已經訓練好的檢測caffemodel，這裏我直接拿示例的20類demo的caffemodel，也把它拷貝到我們的文件夾下，萬事俱備，只欠東風了！ 趕緊編寫個主函數進行測試吧，我的示例如下：

#include "ObjectDetector.hpp"
#include<opencv2/opencv.hpp>
#include<iostream>
#include<sstream>
using namespace cv;
using namespace std;
string num2str(float i){
stringstream ss;
ss<<i;
return ss.str();
}

int main(int argc,char **argv){
::google::InitGoogleLogging(argv[0]);
#ifdef CPU_ONLY
cout<<"Use CPU\n";
#else
cout<<"Use GPU\n";
#endif

ObjectDetector detect("test.prototxt","1.caffemodel");

Mat img=imread("1.jpg");
map<int,vector<float> > score;
map<int,vector<Rect> > label_objs=detect.detect(img,&score); //目標檢測,同時保存每個框的置信度

for(map<int,vector<Rect> >::iterator it=label_objs.begin();it!=label_objs.end();it++){
int label=it->first; //標簽
vector<Rect> rects=it->second; //檢測框
for(int j=0;j<rects.size();j++){
rectangle(img,rects[j],Scalar(0,0,255),2); //畫出矩形框
string txt=num2str(label)+" : "+num2str(score[label][j]);
putText(img,txt,Point(rects[j].x,rects[j].y),CV_FONT_HERSHEY_SIMPLEX,0.5,Scalar(0,255,0)); //標記 類別：置信度
}
}
imshow("", img);
waitKey();
return 0;
}

好了，這裏網絡描述文件是 test.prototxt，調用的是caffemodel是官方示例的model，我這為了簡單，改名1.caffemodel了， 對圖片1.jpg進行測試， 現在編譯main.cpp 文件，命令如下：
app.bin: main.cpp ObjectDetector.cpp
g++ -o app.bin main.cpp ObjectDetector.cpp -I /home//caffe/include/ -I /home//caffe/.build_release/src/ -I /usr/local/cuda-8.0/include/ pkg-config --libs --cflags opencv -L /home/****/caffe/build/lib/ -lcaffe -lglog -lboost_system -lprotobuf
具體路徑參照自己的就好，生成app.bin可執行文件，運行，我們對一張圖片進行測試，原圖如下

檢測後，如下：

這裏為了方便，我直接輸出的標簽號以及對應的置信度了。可以看出 ，飛機的的label為1，船的label是4，我們從python版的demo.py中可以證實這點：

CLASSES = (‘background‘,
‘aeroplane‘, ‘bicycle‘, ‘bird‘, ‘boat‘,
‘bottle‘, ‘bus‘, ‘car‘, ‘cat‘, ‘chair‘,
‘cow‘, ‘diningtable‘, ‘dog‘, ‘horse‘,
‘motorbike‘, ‘person‘, ‘pottedplant‘,
‘sheep‘, ‘sofa‘, ‘train‘, ‘tvmonitor‘)

OK，大功告成啦~~~

純C++版500VIP源碼下載的Faster R-CNN（通過caffe自定義RPN層實現）