SSD MyDetect记录
来源：互联网 发布：大麦盒子安装软件 编辑：程序博客网 时间：2024/06/01 10:49
最近学习了SSD，想自己实现SSD后面检测的过程（虽然SSD已经有提供代码，但是自己练练手）。
SSD怎么由先验框得到bounding box的框：
//prior_data_mean表示的是先验框的位置的均值，prior_data_std表示先验框的位置的方差，loc_pre表示预测 prior_w = prior_data_mean[i*4+2] - prior_data_mean[0+i*4];//先验的宽 prior_h = prior_data_mean[i*4+3] - prior_data_mean[1+i*4];//先验的高 prior_x = (prior_data_mean[i*4+2] + prior_data_mean[0+i*4])/2;//先验的中心位置x坐标 prior_y = (prior_data_mean[i*4+1] + prior_data_mean[3+i*4])/2;//先验的中心位置y坐标 bb_x = prior_data_std[i*4+0]*loc_pre[i*4+0]*prior_w + prior_x; bb_y = prior_data_std[i*4+1]*loc_pre[i*4+1]*prior_h + prior_y; bb_w = exp(prior_data_std[i*4+2]*loc_pre[i*4+2])*prior_w; bb_h = exp(prior_data_std[i*4+3]*loc_pre[i*4+3])*prior_h;自己添加的层MyDetect（功能是对于输入进来的prior bounding box， location predict， confidence predict进行处理，输出top[0]维度是1×1×num×6（num表示的是输出目标框的个数，这个是层进行forward的时候回进行调整的，后面维度6分别表示一个框的xmin，ymin，xmax，ymax，class，confidence）
#ifndef CAFFE_MY_DETECT_LAYER_HPP_#define CAFFE_MY_DETECT_LAYER_HPP_#include "caffe/blob.hpp"#include "caffe/layer.hpp"#include "caffe/proto/caffe.pb.h"#include <vector>#include <string>namespace caffe{template <typename Dtype>class MyDetectLayer : public Layer<Dtype>{public: explicit MyDetectLayer(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 "MyDetect";} virtual inline int ExactNumBottomBlobs() const { return 3; } virtual inline int ExactNumTopBlobs() const { return 1; }protected: virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top); virtual void Backward_cpu(const vector<Blob<Dtype>*>& bottom, const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& top); int prior_num;};}#endif#include "caffe/layers/mydetect.hpp"#include <vector>namespace caffe{template<typename Dtype>Dtype lap(Dtype x1_min,Dtype x1_max,Dtype x2_min,Dtype x2_max){ if(x1_min < x2_min){ if(x1_max < x2_min){ return 0; }else{ if(x1_max > x2_min){ if(x1_max < x2_max){ return x1_max - x2_min; }else{ return x2_max - x2_min; } }else{ return 0; } } }else{ if(x1_min < x2_max){ if(x1_max < x2_max) return x1_max-x1_min; else return x2_max-x1_min; }else{ return 0; } }}template<typename Dtype>Dtype jaccard(vector<Dtype> x1, vector<Dtype>x2){ Dtype lap1 = lap<Dtype>(x1[0],x1[2],x2[0],x2[2]); Dtype lap2 = lap<Dtype>(x1[1],x1[3],x2[1],x2[3]); if(lap1 < Dtype(0.00000001) || lap2 < Dtype(0.00000001)) return Dtype(0); else return lap1*lap2/((x1[2]-x1[0])*(x1[3]-x1[1])+(x2[2]-x2[0])*(x2[3]-x2[1])-lap1*lap2);}template<typename Dtype>void MyDetectLayer<Dtype>::LayerSetUp(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top){ CHECK_EQ(bottom.size(), 3); CHECK_EQ(top.size(), 1); prior_num = bottom[2]->height()/4; CHECK_EQ(prior_num*4, bottom[0]->channels()) << "Number of priors must match number of location predictions."; CHECK_EQ(prior_num*21, bottom[1]->channels()) << "Number of priors must match number of confidence predictions.";}template<typename Dtype>void MyDetectLayer<Dtype>::Reshape(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top){ vector<int> shape; shape.push_back(1); shape.push_back(1); shape.push_back(1); shape.push_back(6); top[0]->Reshape(shape);}template<typename Dtype>void MyDetectLayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top){ std::vector<std::pair<std::pair<int,int>,Dtype> > idx_class_conf; const Dtype* conf_data = bottom[1]->cpu_data(); const Dtype* prior_data_mean = bottom[2]->cpu_data(); const Dtype* prior_data_std = bottom[2]->cpu_data()+prior_num*4; const Dtype* loc_pre = bottom[0]->cpu_data(); for(int prior_idx = 0; prior_idx < prior_num; ++prior_idx){ int idx = prior_idx*21; Dtype max = 0; int max_idx = -1; for(int class_idx = 1; class_idx < 21; ++class_idx){//class_idx = 0 is background if(conf_data[idx+class_idx] > max){ max = conf_data[idx+class_idx]; max_idx = class_idx; } } if(max > 0.5){//threshold idx_class_conf.push_back(make_pair(make_pair(prior_idx,max_idx),conf_data[idx+max_idx])); } } vector<vector<Dtype> > bboxes; for(int i = 0; i < prior_num; ++i){ vector<Dtype> temp; Dtype prior_x,prior_y,prior_w,prior_h; prior_w = prior_data_mean[i*4+2] - prior_data_mean[0+i*4]; prior_h = prior_data_mean[i*4+3] - prior_data_mean[1+i*4]; prior_x = (prior_data_mean[i*4+2] + prior_data_mean[0+i*4])/2; prior_y = (prior_data_mean[i*4+1] + prior_data_mean[3+i*4])/2; Dtype bb_x,bb_y,bb_w,bb_h; bb_x = prior_data_std[i*4+0]*loc_pre[i*4+0]*prior_w + prior_x; bb_y = prior_data_std[i*4+1]*loc_pre[i*4+1]*prior_h + prior_y; bb_w = exp(prior_data_std[i*4+2]*loc_pre[i*4+2])*prior_w; bb_h = exp(prior_data_std[i*4+3]*loc_pre[i*4+3])*prior_h; temp.push_back(bb_x-bb_w/2); temp.push_back(bb_y-bb_h/2); temp.push_back(bb_x+bb_w/2); temp.push_back(bb_y+bb_h/2); temp[0] = temp[0] < 0 ? 0:temp[0]; temp[1] = temp[1] < 0 ? 0:temp[1]; temp[2] = temp[2] < 0 ? 0:temp[2]; temp[3] = temp[3] < 0 ? 0:temp[3]; temp[0] = temp[0] > 1 ? 1:temp[0]; temp[1] = temp[1] > 1 ? 1:temp[1]; temp[2] = temp[2] > 1 ? 1:temp[2]; temp[3] = temp[3] > 1 ? 1:temp[3]; bboxes.push_back(temp); } for(int i = 0; i < idx_class_conf.size(); ++i){ for(int j = idx_class_conf.size()-1; j > i; --j){ if(idx_class_conf[i].first.second == idx_class_conf[j].first.second){ //如果iou大于0.5，并且confidence小的删除，如果是第i个小，并且要break，不用进行后面的比较，--i，否这不用。 if(jaccard(bboxes[idx_class_conf[i].first.first],bboxes[idx_class_conf[j].first.first]) > 0.5){ if(idx_class_conf[i].second < idx_class_conf[j].second){ idx_class_conf.erase(idx_class_conf.begin()+i); --i; break; }else{ idx_class_conf.erase(idx_class_conf.begin()+j); } } } } } vector<int> top_shape; top_shape.push_back(1); top_shape.push_back(1); top_shape.push_back(idx_class_conf.size()); top_shape.push_back(6); top[0]->Reshape(top_shape); Dtype* top_data = top[0]->mutable_cpu_data(); int top_idx = 0; for(int i = 0 ; i < idx_class_conf.size(); ++i){ vector<Dtype> bbox = bboxes[idx_class_conf[i].first.first]; top_data[top_idx++] = bbox[0]; top_data[top_idx++] = bbox[1]; top_data[top_idx++] = bbox[2]; top_data[top_idx++] = bbox[3]; top_data[top_idx++] = idx_class_conf[i].first.second; top_data[top_idx++] = idx_class_conf[i].second; }}template<typename Dtype>void MyDetectLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& bottom, const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& top){ NOT_IMPLEMENTED;}template float jaccard(vector<float> x1, vector<float> x2);template double jaccard(vector<double> x1, vector<double> x2);template double lap(double x1_min, double x1_max, double x2_min, double x2_max);template float lap(float x1_min, float x1_max, float x2_min, float x2_max);#ifdef CPU_ONLYSTUB_GPU_FORWARD(MyDetect, Forward);#endifINSTANTIATE_CLASS(MyDetectLayer);REGISTER_LAYER_CLASS(MyDetect);}检测与画框程序
#include <string>#include <vector>#include "boost/algorithm/string.hpp"#include "google/protobuf/text_format.h"#include <opencv2/opencv.hpp>#include "caffe/blob.hpp"#include "caffe/layer.hpp"#include "caffe/common.hpp"#include "caffe/net.hpp"#include "caffe/proto/caffe.pb.h"#include "caffe/util/db.hpp"#include "caffe/util/format.hpp"#include "caffe/util/io.hpp"#include <stdio.h>#include <malloc.h>#include <fstream>#include <boost/progress.hpp>#include <boost/math/special_functions/next.hpp>#include <boost/random.hpp>#include <limits>#include "caffe/common.hpp"#include "caffe/util/math_functions.hpp"#include "caffe/util/rng.hpp"//#include "caffe/util/math_functions.hpp"using caffe::Blob;using caffe::Caffe;using caffe::Datum;using caffe::Net;using caffe::Layer;using std::string;namespace db = caffe::db;void loaddata(boost::shared_ptr<Net<float> >& net, std::string image_path);//int lap(int x1_min,int x1_max,int x2_min,int x2_max);int main(int argc, char** argv){ char *labelname[] = {"aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"}; Caffe::set_mode(Caffe::GPU); boost::shared_ptr<Net<float> > net(new Net<float>(argv[1], caffe::TEST)); net->CopyTrainedLayersFromBinaryProto(argv[2]); loaddata(net,std::string(argv[3])); net->Forward(); Blob<float>* output_layer = net->output_blobs()[0]; const float* begin = output_layer->cpu_data(); const float* end = begin + output_layer->channels()*output_layer->height()*output_layer->width(); std::vector<float> result(begin, end); cv::Mat image = cv::imread(argv[3]); for(int i = 0; i < output_layer->height(); ++i){ cv::Point point1(result[i*6+0]*image.cols, result[i*6+1]*image.rows); cv::Point point2(result[i*6+2]*image.cols, result[i*6+3]*image.rows); cv::rectangle(image, cv::Rect(point1,point2),cv::Scalar(0,result[i*6+4]/20.0*225,255),result[i*6+5]*50/8); char ch[100]; sprintf(ch,"%s %.2f",labelname[int(result[i*6+4]-1)], result[i*6+5]*1.0); std::string temp(ch); cv::putText(image,temp,point1,CV_FONT_HERSHEY_COMPLEX,0.4,cv::Scalar(255,255,255)); } cv::imshow("SSD",image); cv::waitKey(0); return 1;}void loaddata(boost::shared_ptr<Net<float> >& net, std::string image_path){ Blob<float>* input_layer = net->input_blobs()[0]; int width, height; width = input_layer->width(); height = input_layer->height(); int size = width*height; cv::Mat image = cv::imread(image_path,-1); cv::Mat image_resized; cv::resize(image, image_resized, cv::Size(height, width)); float* input_data = input_layer->mutable_cpu_data(); int temp,idx; for(int i = 0; i < height; ++i){ uchar* pdata = image_resized.ptr<uchar>(i); for(int j = 0; j < width; ++j){ temp = 3*j; idx = i*width+j; input_data[idx] = (pdata[temp+2]); input_data[idx+size] = (pdata[temp+1]); input_data[idx+2*size] = (pdata[temp+0]); } } //cv::imshow("image",image_resized);}结果展示： 
1 2
- SSD MyDetect记录
- SSD性能优化记录
- 装SSD记录
- ssd论文阅读记录
- CubieBoard3 安装SSD记录笔记
- SSD MultiBoxLossLayer代码学习记录
- 深度学习SSD学习记录
- 人脸检测SSD 记录
- HHD+SSD重装mac os 10.9记录
- ubuntu14.04 硬盘迁移记录 HHD->SSD
- 工作记录：训练、测试 TF-SSD
- ssd
- SSD
- SSD
- ssd
- SSD
- SSD
- ssd
- c++字符串的讲解
- easyui datagrid 自适应窗口边宽度
- iOS设计模式 ——单例模式详解以及严格单例模式注意点
- PHP判断图片格式的7种方法
- MapReduce编程基础—学习笔记[2]
- SSD MyDetect记录
- Wireshark过滤规则设置
- Tyvj P1288 飘飘乎居士取能量块
- 【安全资讯】中国BAT巨头Web浏览器隐私和安全问题
- Mac下使用brew搭建PHP7+nginx+mysql开发环境
- POJ 2349 Arctic Network（Kruskal求最小生成树第k条边的长度）
- Android大数据、断点续传、耗时下载之DownloadManager开发简介(1)
- CMD 命令行中文件路径有空格怎么办？
- 正则匹配：去除字符串中的空格，获取select下拉选项中的option的文本内容
