caffe textboxes++测试(c++版本)-boxDe

这里是c++测试版本的boxDetect.cpp，来源应该是SSD

// This is a demo code for using a SSD model to do detection.
// The code is modified from examples/cpp_classification/classification.cpp.
// Usage:
//    ssd_detect [FLAGS] model_file weights_file list_file
//
// where model_file is the .prototxt file defining the network architecture, and
// weights_file is the .caffemodel file containing the network parameters, and
// list_file contains a list of image files with the format as follows:
//    folder/img1.JPEG
//    folder/img2.JPEG
// list_file can also contain a list of video files with the format as follows:
//    folder/video1.mp4
//    folder/video2.mp4
//
#include <stdio.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>
#include "caffe/boxDetect.h"

#ifdef USE_OPENCV
using namespace caffe;  // NOLINT(build/namespaces)
using namespace std;
Detector::Detector(const string& model_file,
  const string& weights_file,
  const string& mean_file,
  const string& mean_value) {
#ifdef CPU_ONLY
  Caffe::set_mode(Caffe::CPU);
#else
  Caffe::set_mode(Caffe::GPU);
#endif

  /* Load the network. */
  net_.reset(new Net<float>(model_file, TEST));//重新构建网络，调用Net的构造方法
  net_->CopyTrainedLayersFrom(weights_file);//载入模型参数

  CHECK_EQ(net_->num_inputs(), 1) << "Network should have exactly one input.";
  CHECK_EQ(net_->num_outputs(), 1) << "Network should have exactly one output.";
  //输入层
  Blob<float>* input_layer = net_->input_blobs()[0];
  num_channels_ = input_layer->channels();
  //输入层一般是彩色图像、或灰度图像，因此需要进行判断
  CHECK(num_channels_ == 3 || num_channels_ == 1)
  << "Input layer should have 1 or 3 channels.";
  //输入图像的尺寸
  input_geometry_.push_back(cv::Size(768, 768));

  /* Load the binaryproto mean file. */
  SetMean(mean_file, mean_value);
}

std::vector<vector<float> > Detector::Detect(const cv::Mat& img) {

  vector<vector<float> > detections;

  for(int i=0;i< input_geometry_.size();i++)
  {
    int img_height = input_geometry_[i].height;
    int img_width =  input_geometry_[i].width;
    Blob<float>* input_layer = net_->input_blobs()[0];
    input_layer->Reshape(1, num_channels_,
      img_height, img_width);
    /* Forward dimension change to all layers. */
    net_->Reshape();

    std::vector<cv::Mat> input_channels;
    WrapInputLayer(&input_channels, i);

    Preprocess(img, &input_channels, i);

    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;
    
    int j=0;
    //get datas for textboxes++
    while(true)
    {
      if(result[j]==0&&result[j+1]==0&&result[j+2]==0)
      {
        break;
      }
      vector<float> detection;
      detection.push_back(result[j+2]);
      detection.push_back(result[j+7]);
      detection.push_back(result[j+8]);
      detection.push_back(result[j+9]);
      detection.push_back(result[j+10]);
      detection.push_back(result[j+11]);
      detection.push_back(result[j+12]);
      detection.push_back(result[j+13]);
      detection.push_back(result[j+14]);
      detections.push_back(detection);
      j=j+15;
    }
  }
  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);
  // }
  for (int m = 0; m < input_geometry_.size(); ++m)
  {
    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;
      cv::Mat mean;
      for (int i = 0; i < num_channels_; ++i) {
          /* Extract an individual channel. */
        cv::Mat channel(input_geometry_[m].height, input_geometry_[m].width, CV_32FC1,
          cv::Scalar(values[i]));
        channels.push_back(channel);
      }
      cv::merge(channels, mean);
      mean_.push_back(mean);
    }
  }

}

/* Wrap the input layer of the network in separate cv::Mat objects
 * (one per channel). This way we save one memcpy operation and we
 * don't need to rely on cudaMemcpy2D. The last preprocessing
 * operation will write the separate channels directly to the input
 * layer. */

/* 这个其实是为了获得net_网络的输入层数据的指针，然后后面我们直接把输入图片数据拷贝到这个指针里面*/
void Detector::WrapInputLayer(std::vector<cv::Mat>* input_channels, int n) {
  Blob<float>* input_layer = net_->input_blobs()[0];

  int width = input_geometry_[n].width;
  int height = input_geometry_[n].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;
  }
}

//图片预处理函数，包括图片缩放、归一化、3通道图片分开存储
//对于三通道输入CNN，经过该函数返回的是std::vector<cv::Mat>因为是三通道数据，索引用了vector
void Detector::Preprocess(const cv::Mat& img,
  std::vector<cv::Mat>* input_channels, int n) {
  /* Convert the input image to the input image format of the network. */
  cv::Mat sample;
  //如果输入图片是一张彩色图片，但是CNN的输入是一张灰度图像，那么我们需要把彩色图片转换成灰度图片
  
  //如果输入图片是灰度图片，或者是4通道图片，而CNN的输入要求是彩色图片，因此我们也需要把它转化成三通道彩色图片
  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);
  else
    sample = img;

  /*2、缩放处理，因为我们输入的一张图片如果是任意大小的图片，那么我们就应该把它缩放到227×227*/
  cv::Mat sample_resized;
  if (sample.size() != input_geometry_[n])
    cv::resize(sample, sample_resized, input_geometry_[n]);
  else
    sample_resized = sample;
  
  /*3、数据类型处理，因为我们的图片是uchar类型，我们需要把数据转换成float类型*/
  cv::Mat sample_float;
  if (num_channels_ == 3)
    sample_resized.convertTo(sample_float, CV_32FC3);
  else
    sample_resized.convertTo(sample_float, CV_32FC1);

  //均值归一化，为什么没有大小归一化？
  cv::Mat sample_normalized;
  cv::subtract(sample_float, mean_[n], 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. */
  /* 3通道数据分开存储 */
  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.");

#endif  // USE_OPENCV