ssd_detected.cpp代码 head.h代码
ssd_detection.cpp代码
#include "head.h"
#include <caffe/caffe.hpp>
#ifdef USE_OPENCV
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#endif // USE_OPENCV
#include <algorithm>
#include <iomanip>
#include <iosfwd>
#include <memory>
#include <string>
#include <utility>
#include <vector>#ifdef USE_OPENCV
using namespace caffe; // NOLINT(build/namespaces)class Detector {
public:Detector(const string& model_file,const string& weights_file,const string& mean_file,const string& mean_value);std::vector<vector<float> > Detect(const cv::Mat& img);private:void SetMean(const string& mean_file, const string& mean_value);void WrapInputLayer(std::vector<cv::Mat>* input_channels);void Preprocess(const cv::Mat& img,std::vector<cv::Mat>* input_channels);private:shared_ptr<Net<float> > net_;cv::Size input_geometry_;int num_channels_;cv::Mat mean_;
};Detector::Detector(const string& model_file,const string& weights_file,const string& mean_file,const string& mean_value) {
#ifdef CPU_ONLYCaffe::set_mode(Caffe::CPU);
#elseCaffe::set_mode(Caffe::GPU);
#endif/* Load the network. */net_.reset(new Net<float>(model_file, TEST));net_->CopyTrainedLayersFrom(weights_file);CHECK_EQ(net_->num_inputs(), 1) << "Network should have exactly one input.";CHECK_EQ(net_->num_outputs(), 1) << "Network should have exactly one output.";Blob<float>* input_layer = net_->input_blobs()[0];num_channels_ = input_layer->channels();CHECK(num_channels_ == 3 || num_channels_ == 1)<< "Input layer should have 1 or 3 channels.";input_geometry_ = cv::Size(input_layer->width(), input_layer->height());/* Load the binaryproto mean file. */SetMean(mean_file, mean_value);
}std::vector<vector<float> > Detector::Detect(const cv::Mat& img) {Blob<float>* input_layer = net_->input_blobs()[0];input_layer->Reshape(1, num_channels_,input_geometry_.height, input_geometry_.width);/* Forward dimension change to all layers. */net_->Reshape();std::vector<cv::Mat> input_channels;WrapInputLayer(&input_channels);Preprocess(img, &input_channels);net_->Forward();/* Copy the output layer to a std::vector */Blob<float>* result_blob = net_->output_blobs()[0];const float* result = result_blob->cpu_data();const int num_det = result_blob->height();vector<vector<float> > detections;for (int k = 0; k < num_det; ++k) {if (result[0] == -1) {// Skip invalid detection.result += 7;continue;}vector<float> detection(result, result + 7);detections.push_back(detection);result += 7;}return detections;
}/* Load the mean file in binaryproto format. */
void Detector::SetMean(const string& mean_file, const string& mean_value) {cv::Scalar channel_mean;if (!mean_file.empty()) {CHECK(mean_value.empty()) <<"Cannot specify mean_file and mean_value at the same time";BlobProto blob_proto;ReadProtoFromBinaryFileOrDie(mean_file.c_str(), &blob_proto);/* Convert from BlobProto to Blob<float> */Blob<float> mean_blob;mean_blob.FromProto(blob_proto);CHECK_EQ(mean_blob.channels(), num_channels_)<< "Number of channels of mean file doesn't match input layer.";/* The format of the mean file is planar 32-bit float BGR or grayscale. */std::vector<cv::Mat> channels;float* data = mean_blob.mutable_cpu_data();for (int i = 0; i < num_channels_; ++i) {/* Extract an individual channel. */cv::Mat channel(mean_blob.height(), mean_blob.width(), CV_32FC1, data);channels.push_back(channel);data += mean_blob.height() * mean_blob.width();}/* Merge the separate channels into a single image. */cv::Mat mean;cv::merge(channels, mean);/* Compute the global mean pixel value and create a mean image* filled with this value. */channel_mean = cv::mean(mean);mean_ = cv::Mat(input_geometry_, mean.type(), channel_mean);}if (!mean_value.empty()) {CHECK(mean_file.empty()) <<"Cannot specify mean_file and mean_value at the same time";stringstream ss(mean_value);vector<float> values;string item;while (getline(ss, item, ',')) {float value = std::atof(item.c_str());values.push_back(value);}CHECK(values.size() == 1 || values.size() == num_channels_) <<"Specify either 1 mean_value or as many as channels: " << num_channels_;std::vector<cv::Mat> channels;for (int i = 0; i < num_channels_; ++i) {/* Extract an individual channel. */cv::Mat channel(input_geometry_.height, input_geometry_.width, CV_32FC1,cv::Scalar(values[i]));channels.push_back(channel);}cv::merge(channels, mean_);}
}void Detector::WrapInputLayer(std::vector<cv::Mat>* input_channels) {Blob<float>* input_layer = net_->input_blobs()[0];int width = input_layer->width();int height = input_layer->height();float* input_data = input_layer->mutable_cpu_data();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 += width * height;}
}void Detector::Preprocess(const cv::Mat& img,std::vector<cv::Mat>* input_channels) {/* Convert the input image to the input image format of the network. */cv::Mat sample;if (img.channels() == 3 && num_channels_ == 1)cv::cvtColor(img, sample, cv::COLOR_BGR2GRAY);else if (img.channels() == 4 && num_channels_ == 1)cv::cvtColor(img, sample, cv::COLOR_BGRA2GRAY);else if (img.channels() == 4 && num_channels_ == 3)cv::cvtColor(img, sample, cv::COLOR_BGRA2BGR);else if (img.channels() == 1 && num_channels_ == 3)cv::cvtColor(img, sample, cv::COLOR_GRAY2BGR);elsesample = img;cv::Mat sample_resized;if (sample.size() != input_geometry_)cv::resize(sample, sample_resized, input_geometry_);elsesample_resized = sample;cv::Mat sample_float;if (num_channels_ == 3)sample_resized.convertTo(sample_float, CV_32FC3);elsesample_resized.convertTo(sample_float, CV_32FC1);cv::Mat sample_normalized;cv::subtract(sample_float, mean_, sample_normalized);/* This operation will write the separate BGR planes directly to the* input layer of the network because it is wrapped by the cv::Mat* objects in input_channels. */cv::split(sample_normalized, *input_channels);CHECK(reinterpret_cast<float*>(input_channels->at(0).data)== net_->input_blobs()[0]->cpu_data())<< "Input channels are not wrapping the input layer of the network.";
}DEFINE_string(mean_file, "","The mean file used to subtract from the input image.");
DEFINE_string(mean_value, "104,117,123","If specified, can be one value or can be same as image channels"" - would subtract from the corresponding channel). Separated by ','.""Either mean_file or mean_value should be provided, not both.");
DEFINE_string(file_type, "image","The file type in the list_file. Currently support image and video.");
DEFINE_string(out_file, "","If provided, store the detection results in the out_file.");
DEFINE_double(confidence_threshold, 0.01,"Only store detections with score higher than the threshold.");//string num2label(int num)
//{// string labels[25]{"", "airplane", "bicycle", "bird", "boat", "bottle", "bus", "car",
// "cat", "chair", "cow", "table", "dog", "horse", "motobike",
// "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"};
// return labels[num];
//}string num2label(int num)
{string labels[2]{"", "car"};return labels[num];
}
cv::Point pt1;
cv::Point pt2;/*********************************************************//*********************************************************/
/*********************************************************//*********************************************************/int main(int argc, char** argv)
{::google::InitGoogleLogging(argv[0]);// Print output to stderr (while still logging)FLAGS_alsologtostderr = 1;#ifndef GFLAGS_GFLAGS_H_namespace gflags = google;
#endifconst string& model_file("deploy.prototxt"); //prototxt文件const string& weights_file("VGG_VOC0712_SSD_300x300_iter_15000.caffemodel");; //caffemodel文件const string& mean_file = FLAGS_mean_file;const string& mean_value = FLAGS_mean_value;const float confidence_threshold = FLAGS_confidence_threshold;// 加载网络Detector detector(model_file, weights_file, mean_file, mean_value);//cvNamedWindow("SSD", 0);cv::VideoCapture cap("2.mp4");if (!cap.isOpened()){LOG(FATAL) << "Failed to open video: ";}cv::Mat img;int frame_count = 0;while (true){bool success = cap.read(img);if (!success){LOG(INFO) << "Process " << frame_count << " frames from ";break;}CHECK(!img.empty()) << "Error when read frame";std::vector<vector<float> > detections = detector.Detect(img);/* Print the detection results. */for (int i = 0; i < detections.size(); ++i){const vector<float>& d = detections[i];// Detection format: d[image_id, label, score, xmin, ymin, xmax, ymax].CHECK_EQ(d.size(), 7);const float score = d[2];if (score >= 0.6) //【置信度】{//pt1.x = d[3] * img.cols;//pt1.y = d[4] * img.rows;//pt2.x = d[5] * img.cols;//pt2.y = d[6] * img.rows;//rectangle(img, pt1, pt2, cv::Scalar(0, 0, 255), 3, 8, 0);int posx = static_cast<int>(d[3] * img.cols);int posy = static_cast<int>(d[4] * img.rows);int posw = static_cast<int>(d[5] * img.cols) - posx;int posh = static_cast<int>(d[6] * img.rows) - posy;cv::Rect pos(posx, posy, posw, posh);cv::rectangle(img, pos, cv::Scalar(0, static_cast<int>(d[1]) / 21.0 * 255, 255)); //细、橙色框char buffer[50];_gcvt(score, 2, buffer);std::string words = std::string(buffer);words = num2label(static_cast<int>(d[1])) + " : " + words;cv::putText(img, words, cv::Point(posx, posy), CV_FONT_HERSHEY_COMPLEX, 0.4, cv::Scalar(0, static_cast<int>(d[1]) / 21.0 * 255, 255));}}cv::imshow("SSD", img);cv::waitKey(24);++frame_count;}//if (cap.isOpened()) //释放相机cap{cap.release();}return 0;
}
#else
int main(int argc, char** argv) {LOG(FATAL) << "This example requires OpenCV; compile with USE_OPENCV.";
}
#endif // USE_OPENCV
head.h代码
#ifndef CAFFE_REG_H
#define CAFFE_REG_H
#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/pooling_layer.hpp"
#include "caffe/layers/lrn_layer.hpp"
#include "caffe/layers/softmax_layer.hpp"
#include "caffe/layers/normalize_layer.hpp"
#include "caffe/layers/permute_layer.hpp"
#include "caffe/layers/flatten_layer.hpp"
#include "caffe/layers/prior_box_layer.hpp"
#include "caffe/layers/concat_layer.hpp"
#include "caffe/layers/reshape_layer.hpp"
#include "caffe/layers/softmax_layer.hpp"
#include "caffe/layers/detection_output_layer.hpp"
namespace caffe
{extern INSTANTIATE_CLASS(InputLayer);extern INSTANTIATE_CLASS(ConvolutionLayer);REGISTER_LAYER_CLASS(Convolution);extern INSTANTIATE_CLASS(InnerProductLayer);extern INSTANTIATE_CLASS(DropoutLayer);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(NormalizeLayer);//REGISTER_LAYER_CLASS(Normalize); extern INSTANTIATE_CLASS(PermuteLayer);//REGISTER_LAYER_CLASS(Permute); extern INSTANTIATE_CLASS(FlattenLayer);extern INSTANTIATE_CLASS(PriorBoxLayer);extern INSTANTIATE_CLASS(ConcatLayer);extern INSTANTIATE_CLASS(ReshapeLayer);extern INSTANTIATE_CLASS(SoftmaxLayer);REGISTER_LAYER_CLASS(Softmax);extern INSTANTIATE_CLASS(DetectionOutputLayer);
}
#endif
ssd_detected.cpp代码 head.h代码相关推荐
- SLAM十四讲 ch7 orb_self.cpp中402行代码:cv::DMatch m{i1, 0, 256}报错
orb_self.cpp中402行代码:cv::DMatch m{i, 0, 256}; 报错:warning: narrowing conversion of 'i' from 'size_t {a ...
- 【C/C++16】_public.h,_public.cpp,_cmpublic.h
文章目录 1._public.h 2._public.cpp 3._cmpublic.h 1._public.h #ifndef _PUBLIC_H #define _PUBLIC_H 1 #incl ...
- 【C/C++11】天气APP:txt/xml文件处理入库(psurfdata.cpp,_shqx.h),数据结构设计(PowerDesigner)
文章目录 1.txt/xml文件入表/自身调度:结构体内容 2.分区/表空间/网络/主键/错误优化:chown -R 用户 3.历史文件/表数据清理:生成测试数据后去采集,采集后未删除文件,因为数据不 ...
- 在C代码调用C++代码
由于历史原因,以及不同开发人员的技术偏好,C语言和C++语言都有一些独有的非常有价值的项目,因而两种语言的互操作,充分利用前人造的轮子是一件非常有价值的事情. C++代码调用C代码很简单,只要分别在包 ...
- 让C++代码与C#代码一起生成一个单一的Assembly
本文提供了一个方法,让C++源码和C#源码一起编译链接成一个单一的Assembly. 由于M$的C++/CLI提供了IJW方法,允许将旧有C++代码也编译成托管代码,因此这篇小文可以用极小的工作量来彻 ...
- 最全的基于c++的serialport.cpp与serialport.h类文件(解析版)
最全的基于c++的serialport.cpp与serialport.h类文件(解析版) 备注 参考原文件为:serialport.cpp与serialport.h类文件源代码 作者:c344935 ...
- python好看的流星雨代码,python流星雨代码解释
用C语言编写流星雨程序 数字流星雨代码://流星雨.cpp:Defines the entry point for the console application.///程序名称:数字流星雨//最后修 ...
- 向代码节添加代码编程实现
原理 分析PE结构,找到第一个节,假设它是代码节(后面的实验都是基于这个前提),获取其内存偏移 VirtualAddress,计算它最后一条指令的偏移的下一个字节,作为代码插入点.插入调用Messag ...
- php图片变成代码怎么解决,一段图片处理代码PHP代码转C#代码,该怎么解决
一段图片处理代码PHP代码转C#代码 把下面代码转换成 C#代码 $res = json_decode(stripslashes($_POST['jsondata']), true); /* get ...
最新文章
- R可视化多元线性回归模型
- PostgreSQL — Overview
- 创业故事:腾讯的创始人们
- linux安装字体时找不到mkfontscale、mkfontdir
- ‘ping‘ 不是内部或外部命令,也不是可运行的程序或批处理文件。
- .NET Core 的过去、现在和未来
- ctf 改变图片高度_CTF中.htaccess文件的利用
- Toml :设置策略配置文件
- tomcat内存溢出:PermGen space解决方法
- Invest模型问题答疑--产水模块、土壤保持模块、供需平衡分析、生态系统服务、生物多样性生境质量
- 怎么使用计算机唱歌,声卡怎么用手机唱歌
- python pandas的read_html方法爬取网页表格
- mac下展示隐藏文件
- 基于单片机MAX30100血氧、心率检测系统设计-整套资料
- 专家教你用!!!google .
- 智慧城市与智能网联汽车如何协同发展?
- 7.2影像云阅片【斯纳克PACS医学影像云平台用户手册】
- CFDA《药品数据管理规范》疑难点解读
- 【Python安装配置教程】
- 智能制造中的名词释义
热门文章
- mac或linux下JDBC的简单实现,图文介绍(附测试源码)
- 分布式服务化系统一致性的“最佳实干”--转
- Java泛型总结--转
- ConcurrentHashMap实现原理--转载
- 使用Java API创建(create),查看(describe),列举(list),删除(delete)Kafka主题(Topic)--转载...
- MySQL——基于CASE WHEN的常用查询
- 数模学习笔记——微分方程(传染病模型)
- 设置Network id: 5777 in MetaMask
- 从0到1建立一张评分卡之数据预处理
- Java 高并发_JAVA并发编程与高并发解决方案 JAVA高并发项目实战课程 没有项目经验的朋友不要错过!...