caffe测试单张图片

所有的操作是基于caffe的根目录/caffe-master/来操作的：

在caffe框架中用训练好的模型分类单张图片需要用到classification.bin，本博客主要提供其源码文件classification.cpp的注释。

1、caffe提供了一个用已经训练好的caffemodel来分类单张图片的库(./build/examples/cpp_classification/classification.bin)，该库的源码为文件./examples/cpp-classification/classification.cpp。

2、利用该库的分类单张图片的具体方法：：

./build/examples/cpp_classification/classification.bin \
网络结构文件：xx/xx/deploy.prototxt                      \
训练的模型文件：xx/xx/xx.caffemodel                      \
训练的图像的均值文件：xx/xx/xx.binaryproto                \
类别名称标签文件：xx/xx/synset_words.txt                 \
待测试图像：xx/xx/xx.jpg                                

具体可见这位大牛的博客：http://www.cnblogs.com/denny402/p/5111018.html

下面记录下我在看classification.cpp代码时一些注释，如有错误望指教：：：

#include 
#ifdef USE_OPENCV
#include 
#include 
#include 
#endif  // USE_OPENCV
#include 
#include 
#include 
#include 
#include 
#include 

#ifdef USE_OPENCV
using namespace caffe;  // NOLINT(build/namespaces)
using std::string;

/* Pair (label, confidence) representing a prediction. */
typedef std::pair<string, float> Prediction;

class Classifier {
 public:
  Classifier(const string& model_file,
             const string& trained_file,
             const string& mean_file,
             const string& label_file);

  std::vector Classify(const cv::Mat& img, int N = 5);

 private:
  void SetMean(const string& mean_file);

  std::vector<float> Predict(const cv::Mat& img);

  void WrapInputLayer(std::vector* input_channels);

  void Preprocess(const cv::Mat& img,
                  std::vector* input_channels);

 private:
  shared_ptrfloat> > net_;
  cv::Size input_geometry_;
  int num_channels_;
  cv::Mat mean_;
  std::vector<string> labels_;
};


/*分类对象构造文件*/
Classifier::Classifier(const string& model_file,
                       const string& trained_file,
                       const string& mean_file,
                       const string& label_file) {
#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)); /*复制网络结构*/
  net_->CopyTrainedLayersFrom(trained_file);   /*加载caffemodel,该函数在net.cpp中实现*/

  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();    /*该网络结构所要求的图片输入通道数*/
  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());  /*输入层需要的图片宽高*/

  /* Load the binaryproto mean file. */
  SetMean(mean_file);   /*加载均值文件*/

  /* Load labels. */
  std::ifstream labels(label_file.c_str());  /*加载标签名称文件*/
  CHECK(labels) << "Unable to open labels file " << label_file;
  string line;
  while (std::getline(labels, line))
    labels_.push_back(string(line));

  Blob<float>* output_layer = net_->output_blobs()[0];   /*检查标签个数与网络的输出结点个数是否一样*/
  CHECK_EQ(labels_.size(), output_layer->channels())
    << "Number of labels is different from the output layer dimension.";
}

static bool PairCompare(const std::pair<float, int>& lhs,
                        const std::pair<float, int>& rhs) {
  return lhs.first > rhs.first;
}

/* Return the indices of the top N values of vector v. */
static std::vector<int> Argmax(const std::vector<float>& v, int N) {
  std::vector<std::pair<float, int> > pairs;
  for (size_t i = 0; i < v.size(); ++i)
    pairs.push_back(std::make_pair(v[i], i));
  std::partial_sort(pairs.begin(), pairs.begin() + N, pairs.end(), PairCompare);

  std::vector<int> result;
  for (int i = 0; i < N; ++i)
    result.push_back(pairs[i].second);
  return result;
}

/* Return the top N predictions. */
std::vector Classifier::Classify(const cv::Mat& img, int N) {
  std::vector<float> output = Predict(img);  /*调用这个函数做分类*/

  N = std::min<int>(labels_.size(), N);
  std::vector<int> maxN = Argmax(output, N);
  std::vector predictions;
  for (int i = 0; i < N; ++i) {
    int idx = maxN[i];
    predictions.push_back(std::make_pair(labels_[idx], output[idx]));
  }

  return predictions;
}

/* Load the mean file in binaryproto format. */
void Classifier::SetMean(const string& mean_file) {
  BlobProto blob_proto;
  ReadProtoFromBinaryFileOrDie(mean_file.c_str(), &blob_proto);  /*读入均值文件在Io.cpp中实现*/

  /* Convert from BlobProto to Blob */
  Blob<float> mean_blob;
  mean_blob.FromProto(blob_proto);  /*将读入的均值文件转成Blob对象*//*Blob类在Blob.hpp中定义*/
  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 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();
  }  /*将均值图像的每个通道图像拷贝到channel中*/

  /* Merge the separate channels into a single image. */
  cv::Mat mean;
  cv::merge(channels, mean);  /*合并每个通道图像*/

  /* Compute the global mean pixel value and create a mean image
   * filled with this value. */
  cv::Scalar channel_mean = cv::mean(mean);
  mean_ = cv::Mat(input_geometry_, mean.type(), channel_mean);
}

/*测试函数*/
std::vector<float> Classifier::Predict(const cv::Mat& img) {
  Blob<float>* input_layer = net_->input_blobs()[0];
  input_layer->Reshape(1, num_channels_,
                       input_geometry_.height, input_geometry_.width);/*没太看懂，应该是一些缩放*/
  /* Forward dimension change to all layers. */
  net_->Reshape();

  std::vector input_channels;
  WrapInputLayer(&input_channels);/*对输入层数据进行包装*/

  Preprocess(img, &input_channels);  /*把传入的测试图像写入到输入层*/

  net_->Forward();    /*网络前向传播：计算出该测试图像属于哪个每个类别的概率也就是最终的输出层*/

  /* Copy the output layer to a std::vector */
  Blob<float>* output_layer = net_->output_blobs()[0];   /*将输出层拷贝到向量*/
  const float* begin = output_layer->cpu_data();
  const float* end = begin + output_layer->channels();
  return std::vector<float>(begin, end);
}

/* 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 Classifier::WrapInputLayer(std::vector* 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 Classifier::Preprocess(const cv::Mat& img,
                            std::vector* 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;/*将输入的图像转换成输入层需要的图像格式*/

  cv::Mat sample_resized;
  if (sample.size() != input_geometry_)
    cv::resize(sample, sample_resized, input_geometry_);    /*如果大小不一致则需要缩放*/
  else
    sample_resized = sample;

  cv::Mat sample_float;
  if (num_channels_ == 3)
    sample_resized.convertTo(sample_float, CV_32FC3);       /*将数据转化成浮点型*/
  else
    sample_resized.convertTo(sample_float, CV_32FC1);

  cv::Mat sample_normalized;
  cv::subtract(sample_float, mean_, sample_normalized);     /*应该是当前图像减去均值图像*/

  /* 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);   /*把测试的图像通过之前的定义的wraper写入到输入层*/

  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.";
}

int main(int argc, char** argv) {
  if (argc != 6) {
    std::cerr << "Usage: " << argv[0]
              << " deploy.prototxt network.caffemodel"
              << " mean.binaryproto labels.txt img.jpg" << std::endl;
    return 1;
  }

  ::google::InitGoogleLogging(argv[0]);

  string model_file   = argv[1];   /*标识网络结构的deploy.prototxt文件*/
  string trained_file = argv[2];   /*训练出来的模型文件caffemodel*/
  string mean_file    = argv[3];   /*均值.binaryproto文件*/
  string label_file   = argv[4];   /*标签文件:标识类别的名称*/
  Classifier classifier(model_file, trained_file, mean_file, label_file);  /*创建对象并初始化网络、模型、均值、标签各类对象*/

  string file = argv[5];   /*传入的待测试图片*/

  std::cout << "---------- Prediction for "
            << file << " ----------" << std::endl;

  cv::Mat img = cv::imread(file, -1);
  CHECK(!img.empty()) << "Unable to decode image " << file;
  std::vector predictions = classifier.Classify(img);   /*具体测试传入的图片并返回测试的结果：类别ID与概率值的Prediction类型数组*/

  /* Print the top N predictions. *//*将测试的结果打印*/
  for (size_t i = 0; i < predictions.size(); ++i) {
    Prediction p = predictions[i];
    std::cout << std::fixed << std::setprecision(4) << p.second << " - \""
              << p.first << "\"" << std::endl;
  }
}
#else
int main(int argc, char** argv) {
  LOG(FATAL) << "This example requires OpenCV; compile with USE_OPENCV.";
}
#endif  // USE_OPENCV

感谢：：：：：http://blog.csdn.net/csyanbin/article/details/50877359