JAVA高级面试进阶训练营视频教程

admin

本来SSD做测试的Python接口用起来也是比较方便的，但是如果部署集成的话，肯定要用c++环境，于是动手鼓捣了一下。

编译用的cmake，写的CMakeList.txt，期间碰到一些小问题，简单记录一下问题以及解决方法。

当然前提是你本地的caffe环境没啥问题。各种依赖都安好了。。

1.error: ‘AnnotatedDatum’ has not been declared    AnnotatedDatum* anno_datum);

/home/jiawenhao/ssd/caffe/include/caffe/util/io.hpp:192:40: error: ‘AnnotatedDatum_AnnotationType’ does not name a type
     const std::string& encoding, const AnnotatedDatum_AnnotationType type,
                                        ^
/home/jiawenhao/ssd/caffe/include/caffe/util/io.hpp:194:5: error: ‘AnnotatedDatum’ has not been declared
     AnnotatedDatum* anno_datum);
     ^
/home/jiawenhao/ssd/caffe/include/caffe/util/io.hpp:199:11: error: ‘AnnotatedDatum_AnnotationType’ does not name a type
     const AnnotatedDatum_AnnotationType type, const string& labeltype,
           ^
/home/jiawenhao/ssd/caffe/include/caffe/util/io.hpp:200:49: error: ‘AnnotatedDatum’ has not been declared
     const std::map<string, int>& name_to_label, AnnotatedDatum* anno_datum) {
                                                 ^
/home/jiawenhao/ssd/caffe/include/caffe/util/io.hpp:208:5: error: ‘AnnotatedDatum’ has not been declared
     AnnotatedDatum* anno_datum);
     ^
/home/jiawenhao/ssd/caffe/include/caffe/util/io.hpp:212:5: error: ‘AnnotatedDatum’ has not been declared
     AnnotatedDatum* anno_datum);
     ^
/home/jiawenhao/ssd/caffe/include/caffe/util/io.hpp:215:22: error: ‘AnnotatedDatum’ has not been declared
     const int width, AnnotatedDatum* anno_datum);
                      ^
/home/jiawenhao/ssd/caffe/include/caffe/util/io.hpp:218:30: error: ‘LabelMap’ has not been declared
     const string& delimiter, LabelMap* map);
                              ^
/home/jiawenhao/ssd/caffe/include/caffe/util/io.hpp:221:32: error: ‘LabelMap’ has not been declared
       bool include_background, LabelMap* map) {
                                ^

这个问题拿去google了一下，https://github.com/BVLC/caffe/issues/5671提示说是

caffe.pb.h这个文件有问题。

在本地find了一下，

发现是有这个文件的，

于是在/ssd/caffe/include/caffe下 mkdir一下 proto，然后把 caffe.bp.h 复制过来就好了。

如果没有 caffe.pb.h可以用命令生成这个文件，生成方法google一下就好了。。。。

2.链接库的问题。错误提示说明用到了这个库，但是程序没找到。在CMakeList.txt里填上 libflags.so即可 ，其他so库同理。

/usr/bin/ld: CMakeFiles/ssd_detect.dir/ssd_detect.cpp.o: undefined reference to symbol '_ZN6google14FlagRegistererC1EPKcS2_S2_S2_PvS3_'
/usr/lib/x86_64-linux-gnu/libgflags.so.2: error adding symbols: DSO missing from command line
collect2: error: ld returned 1 exit status
CMakeFiles/ssd_detect.dir/build.make:102: recipe for target 'ssd_detect' failed
make[2]: *** [ssd_detect] Error 1

 

 

 

这个是CMakeList.txt内容。 就是指定好include路径，还有需要用到的各种库的路径。

cmake_minimum_required (VERSION 2.8)  
add_definitions(-std=c++11)
project (ssd_detect)  
  
add_executable(ssd_detect ssd_detect.cpp)  
  
include_directories (/home/yourpath/ssd/caffe/include      
    /usr/include    
    /usr/local/include  
    /usr/local/cuda/include    
         
     )  
  
target_link_libraries(ssd_detect  
     /home/yourpath/ssd/caffe/build/lib/libcaffe.so
     /usr/local/lib/libopencv_core.so 
     /usr/local/lib/libopencv_imgproc.so
     /usr/local/lib/libopencv_imgcodecs.so 
    /usr/local/lib/libopencv_highgui.so
    /usr/local/lib/libopencv_videoio.so
    /usr/lib/x86_64-linux-gnu/libgflags.so     
    /usr/lib/x86_64-linux-gnu/libglog.so    
    /usr/lib/x86_64-linux-gnu/libprotobuf.so    
    /usr/lib/x86_64-linux-gnu/libboost_system.so    
    )  

 3.发现github上下载的默认的ssd_detect.cpp默认没有添加 using namespace std;

添加之后，会有错误。 error: reference to ‘shared_ptr’ is ambiguous

ssd_detect.cpp:54:3: error: reference to ‘shared_ptr’ is ambiguous
   shared_ptr<Net<float> > net_;
   ^
In file included from /usr/include/c++/5/bits/shared_ptr.h:52:0,
                 from /usr/include/c++/5/memory:82,
                 from /usr/include/boost/config/no_tr1/memory.hpp:21,
                 from /usr/include/boost/smart_ptr/shared_ptr.hpp:23,
                 from /usr/include/boost/shared_ptr.hpp:17,
                 from /home/jiawenhao/ssd/caffe/include/caffe/common.hpp:4,
                 from /home/jiawenhao/ssd/caffe/include/caffe/blob.hpp:8,
                 from /home/jiawenhao/ssd/caffe/include/caffe/caffe.hpp:7,
                 from /data/jiawenhao/ssdtest/ssd_detect.cpp:16:
/usr/include/c++/5/bits/shared_ptr_base.h:345:11: note: candidates are: template<class _Tp> class std::shared_ptr
     class shared_ptr;
           ^
In file included from /usr/include/boost/throw_exception.hpp:42:0,
                 from /usr/include/boost/smart_ptr/shared_ptr.hpp:27,
                 from /usr/include/boost/shared_ptr.hpp:17,
                 from /home/jiawenhao/ssd/caffe/include/caffe/common.hpp:4,
                 from /home/jiawenhao/ssd/caffe/include/caffe/blob.hpp:8,
                 from /home/jiawenhao/ssd/caffe/include/caffe/caffe.hpp:7,
                 from /data/jiawenhao/ssdtest/ssd_detect.cpp:16:
/usr/include/boost/exception/exception.hpp:148:11: note:                 template<class T> class boost::shared_ptr
     class shared_ptr;
           ^
/data/jiawenhao/ssdtest/ssd_detect.cpp: In constructor ‘Detector::Detector(const string&, const string&, const string&, const string&)’:
/data/jiawenhao/ssdtest/ssd_detect.cpp:71:3: error: ‘net_’ was not declared in this scope
   net_.reset(new Net<float>(model_file, TEST));

在shared_ptr<Net<float> > net_前面添加上boost即可。

boost::shared_ptr<Net<float> > net_;

 

 

修改后的ssd_detect.cpp源码如下：

// 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
//
#define USE_OPENCV 1
#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)
using namespace cv;
using namespace std;

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:
  boost::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_ONLY
  Caffe::set_mode(Caffe::CPU);
#else
  Caffe::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));
      channels.push_back(channel);
    }
    cv::merge(channels, 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. */
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);
  else
    sample = img;

  cv::Mat sample_resized;
  if (sample.size() != input_geometry_)
    cv::resize(sample, sample_resized, input_geometry_);
  else
    sample_resized = sample;

  cv::Mat sample_float;
  if (num_channels_ == 3)
    sample_resized.convertTo(sample_float, CV_32FC3);
  else
    sample_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, 0.6,
    "Only store detections with score higher than the threshold.");

vector<string> labels = {"background", 
                         "aeroplane", "bicycle","bird", "boat", "bottle",
                        "bus", "car", "cat","chair","cow",
                        "diningtable","dog","horse","motorbike","person",
                        "pottedplant","sheep","sofa","train","tvmonitor"};

int main(int argc, char** argv) {

  const string& model_file = "deploy.prototxt";
  const string& weights_file = "/home/jiawenhao/ssd/caffe/models/VGGNet/VOC0712/SSD_300x300/VGG_VOC0712_SSD_300x300_iter_120000.caffemodel";
  const string& mean_file = FLAGS_mean_file;
  const string& mean_value = "104, 117, 123";
  const string& file_type = "image";
  const string& out_file = "a.outfile";
  const float confidence_threshold = 0.6;

  // Initialize the network.
  Detector detector(model_file, weights_file, mean_file, mean_value);

  // Set the output mode.
  std::streambuf* buf = std::cout.rdbuf();
  std::ofstream outfile;
  if (!out_file.empty()) {
    outfile.open(out_file.c_str());
    if (outfile.good()) {
      buf = outfile.rdbuf();
    }
  }
  std::ostream out(buf);

  // Process image one by one.
  std::ifstream infile("testimg.list");
  std::string file;
  std::string imgName;

  int cnt = 0;
  while (infile >> file) 
  {
    if (file_type == "image")
    {
       std::cout << file <<"    "<<cnt++<<std::endl;
       int pos = file.find_last_of('/');
       imgName = file.substr(pos + 1, file.size() - pos);

      cv::Mat img = cv::imread(file, -1);
      CHECK(!img.empty()) << "Unable to decode image " << file;
      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;
        // Detection format: [image_id, label, score, xmin, ymin, xmax, ymax].
        CHECK_EQ(d.size(), 7);
        const float score = d[2];
        if (score >= confidence_threshold) {
          out << file << " ";
          out << static_cast<int>(d[1]) << " ";
          out << score << " ";
          out << static_cast<int>(d[3] * img.cols) << " ";
          out << static_cast<int>(d[4] * img.rows) << " ";
          out << static_cast<int>(d[5] * img.cols) << " ";
          out << static_cast<int>(d[6] * img.rows) << std::endl;


          int x = static_cast<int>(d[3] * img.cols);
          int y = static_cast<int>(d[4] * img.rows);
          int width = static_cast<int>(d[5] * img.cols) - x;
          int height = static_cast<int>(d[6] * img.rows) - y;

          Rect rect(max(x,0), max(y,0), width, height);

          rectangle(img, rect, Scalar(0,255,0));
          string sco = to_string(score).substr(0, 5);
          putText(img, labels[static_cast<int>(d[1])] + ":" + sco, Point(max(x, 0), max(y + height / 2, 0)),
              FONT_HERSHEY_SIMPLEX, 1, Scalar(0,255,0));
          imwrite("result/" + imgName, img);
        }
      }
    } else if (file_type == "video") {
      cv::VideoCapture cap(file);
      if (!cap.isOpened()) {
        LOG(FATAL) << "Failed to open video: " << file;
      }
      cv::Mat img;
      int frame_count = 0;
      while (true) {
        bool success = cap.read(img);
        if (!success) {
          LOG(INFO) << "Process " << frame_count << " frames from " << file;
          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;
          // Detection format: [image_id, label, score, xmin, ymin, xmax, ymax].
          CHECK_EQ(d.size(), 7);
          const float score = d[2];
          if (score >= confidence_threshold) {
            out << file << "_";
            out << std::setfill('0') << std::setw(6) << frame_count << " ";
            out << static_cast<int>(d[1]) << " ";
            out << score << " ";
            out << static_cast<int>(d[3] * img.cols) << " ";
            out << static_cast<int>(d[4] * img.rows) << " ";
            out << static_cast<int>(d[5] * img.cols) << " ";
            out << static_cast<int>(d[6] * img.rows) << std::endl;
          }
        }
        ++frame_count;
      }
      if (cap.isOpened()) {
        cap.release();
      }
    } else {
      LOG(FATAL) << "Unknown file_type: " << file_type;
    }
  }
  return 0;
}
#else
int main(int argc, char** argv) {
  LOG(FATAL) << "This example requires OpenCV; compile with USE_OPENCV.";
}
#endif  // USE_OPENCV

 

 最后，放一张识别结果：