使用Caffe C++ API调用生成模型进行分类

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/m_buddy/article/details/81194539

1. 前言

对于在Caffe环境之间设计和训练模型，一般是采用python接口，这样比较方便。但是到实际部署的时候，为了速度等因素的考虑，都会使用Caffe下的C++ API接口实现的。在这里使用Caffe自带的classification.cpp进行改造，希望能给大家理解带来帮助。

2. 实现

2.1 Classifier类

首先来看类的声明文件classification.h：

#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <algorithm>
#include <iosfwd>
#include <memory>
#include <string>
#include <utility>
#include <vector>

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

/* Pair (label, confidence) representing a prediction. */
typedef std::pair<string, float> Prediction; //用作结果保存的数据机构，label名称和概率

//类的声明
class Classifier 
{
public:
    Classifier(const string& model_file, //Caffe model的部署文件也就是deploy文件
             const string& trained_file, //model文件
             const string& mean_file, //训练集均值文件
             const string& label_file); //标签文本
    //调用进行分类的接口，默认返回前五个最有可能的类别
    std::vector<Prediction> Classify(const cv::Mat& img, int N = 5);

private:
    //设置均值文件
    void SetMean(const string& mean_file);
    //前向传播，实现分类
    std::vector<float> Predict(const cv::Mat& img);
    //数据输入
    void WrapInputLayer(std::vector<cv::Mat>* input_channels);
    //图像的预处理
    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_;
    std::vector<string> labels_;
};

接下来再来看类的定义classification.cpp：

#include <caffe/caffe.hpp>
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <algorithm>
#include <iosfwd>
#include <memory>
#include <string>
#include <utility>
#include <vector>

#include "classification.h"

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


Classifier::Classifier(const string& model_file,
                       const string& trained_file,
                       const string& mean_file,
                       const string& label_file) 
{
    //Caffe::set_mode(Caffe::CPU);
    Caffe::set_mode(Caffe::GPU);  //GPU mode

    /* Load the network. */
    net_.reset(new Net<float>(model_file, TEST));
    net_->CopyTrainedLayersFrom(trained_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);

    /* Load labels. */
    std::ifstream labels(label_file.c_str());
    //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];
    //CHECK_EQ(labels_.size(), output_layer->channels())
    //    << "Number of labels is different from the output layer dimension.";
}

//vec sort method
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<Prediction> Classifier::Classify(const cv::Mat& img, int N) 
{
     std::vector<float> output = Predict(img);

    N = std::min<int>(labels_.size(), N);
    std::vector<int> maxN = Argmax(output, N);
    std::vector<Prediction> 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);

    /* 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. */
    cv::Scalar channel_mean = cv::mean(mean);
    mean_ = cv::Mat(input_geometry_, mean.type(), channel_mean);
}

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);
    /* 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>* output_layer = net_->output_blobs()[0];
    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<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 Classifier::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.";
}

上面只是在classification.cpp文件进行了简单的拆分，对于这个类的拆分只是简单的处理。在实际使用中可以考虑采用单例模式的思路进行改造，因为模型的加载也是很花时间的，不必每次去跑图片的时候都加载一次。
PS：对于Caffe中deploy文件的具体是干啥的，与train val 文件有什么区别，可以看看这篇文章Caffe中deploy.prototxt 和 train_val.prototxt 区别

2.2 main函数

#include <stdio.h>
#include <iostream>
#include <stdlib.h>
#include <caffe/caffe.hpp>
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <algorithm>
#include <iosfwd>
#include <memory>
#include <string>
#include <utility>
#include <vector>

#include "caffe_classification/classification.h"

using namespace std;

//主函数
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];
  string trained_file = argv[2];
  string mean_file    = argv[3];
  string label_file   = argv[4];
  double time_start = cv::getTickCount();
  Classifier classifier(model_file, trained_file, mean_file, label_file);
  double time_end = cv::getTickCount();
  std::cout << "load model time spend: " << (time_end-time_start)*1000/cv::getTickFrequency() << std::endl;
  string file = argv[5];

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

  cv::Mat img = cv::imread(file, -1);
  CHECK(!img.empty()) << "Unable to decode image " << file;
  std::vector<Prediction> predictions = classifier.Classify(img);

  /* Print the top N predictions. */
  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;
  }
  time_end = cv::getTickCount();
  std::cout << "time spend:" << (time_end-time_start)*1000/cv::getTickFrequency() << std::endl;

  return 0;
}

2.3 相关Makefile文件编写

这是针对上述内容写的Makefile，写得丑，勿喷-_-||…

LIBDIR =  -lpthread -lm -lstdc++ \
          -Wl,--start-group \
          -Wl,--end-group -L. -lcurl\
          -lopencv_imgcodecs -lopencv_imgproc  -lopencv_core -lopencv_highgui -lopencv_videoio\
          -lcaffe -lglog\


CAFFE_LIB =  -L ~/Desktop/caffe/build/lib/ 


CPPFLAGS = -std=c++11 

INCLUDEDIR = -I ~/Desktop/caffe/include/ \
             -I ~/local_install/bin/include/ \  # opencv之类库的安装路径
             -I ~/caffe/.build_release/src/ \
             -I /usr/local/cuda/include/ \

# 当前目录的caffe_classification目录下装前面说到的classifiction.cpp和classifiction.h
CAFFE_CLASSIFICATION = ./caffe_classification/

# run file
my_claasify: main.o classification.o 
    g++ $(CPPFLAGS) -o my_classify $(INCLUDEDIR) $(CAFFE_LIB) $(LIBDIR) main.o classification.o ThreadPool.o

# main.o
main.o: main.cpp $(CAFFE_CLASSIFICATION)classification.h
    g++ $(CPPFLAGS) -c main.cpp $(INCLUDEDIR) $(CAFFE_LIB) $(LIBDIR)

# classification.o
classification.o: $(CAFFE_CLASSIFICATION)classification.cpp  $(CAFFE_CLASSIFICATION)classification.h
    g++ $(CPPFLAGS) -c $(CAFFE_CLASSIFICATION)classification.cpp $(INCLUDEDIR) $(CAFFE_LIB) $(LIBDIR)

之后就是make生成my_claasify可执行文件，按照如下方式执行(路径可能与大家不太一样，参照着改一下)

./my_classify ../deploy.prototxt ../snapshot/solver_iter_55000.caffemodel ../handwrite_mean.binaryproto class_labels.txt test.jpg