利用Clion调用caffe的c++接口

版权声明：本文为博主原创文章，转载请注明出处。 https://blog.csdn.net/hjxu2016/article/details/83301912

之前简单学习了一下CMake的知识,现在就应用到caffe里.

CLION调用caffe关键是CMakeLists.txt文件的编写,涉及到一些CMake的知识.

首先用CLion建立一个caffeReadImgClassify工程,这时候发现工程目录下有main.cpp和CmakeLists.txt两个文件

看 CMakeLists.txt文件内容,注意,有的路径需要自己改变一下

cmake_minimum_required(VERSION 3.12) # 最低的CMAKE版本
project(caffeReadImgClassify)
# 可以用这个指令定义工程的名称,并指定工程支持的语言,语言列表是可以忽略的,默认情况表示支持所有语言
# 这个指令还隐式定义了两个cmake变量 projectname_BINARY_DIR 和 projectname_SOURCE_DIR,因为采用的是内部编
#　译,两个变量目前指的是工作所在路径，如果是外部编译，两者所指代的内容会有所不同，但是如果改变工程名，
# 那么这两个变量也需要修改，那会很麻烦，所有，建议直接使用PROJECT_BINARY_DIR 和 PROJECT_SOURCE_DIR
# 外部编译时,PROJECT_BINATY_DIR指的是编译路径, PROJECT_SOURCE_DIR指工程路径

set(CMAKE_CXX_STANDARD 14)  #用来定义显式变量

include_directories(/home/hjxu/git/caffe/include
        /usr/local/cuda/include /usr/include/opencv
        /usr/include/boost
        /home/hjxu/git/caffe/.build_release/src)

# INCLUDE_DIRECTORIES([AFTER|BEFORE] [SYSTEM] dir1 dir2 ...)
# 这条指令可以用来向工程中添加多个特定的头文件搜索路径, 路径之间用空格分割,如果路径中包含了空格,
# 可以用双引号将它括起来, 默认的行为是追加到当前头文件搜索路径的后面,当然,也可以通过两种方式来控制搜索路径添加的方式
# 一种方式:CMAKE_INCLUDE_DIRECORIES_BEFORE,通过SET这个cmake变量为on,可以将添加的头文件搜索路径放在已有路径的前面
# 第二种方式: 通过AFTER 或者 BEFORE 参数控制是追加还是置前

find_library(caffe /home/hjxu/git/caffe/build/lib)
# find_library(<VAR> name1 path1 path2 ...)
#  VAR变量表示要找的库的全路径, 包含库文件名


link_libraries("/home/hjxu/git/caffe/.build_release/lib/libcaffe.so"
        "/usr/lib/x86_64-linux-gnu/libglog.so"
        "/usr/lib/x86_64-linux-gnu/libboost_filesystem.so"
        "/usr/lib/x86_64-linux-gnu/libboost_system.so")
# LINL_LIBRARIES 添加需要库链接的库文件路径,这里是全路径

find_package(OpenCV REQUIRED)
# FIND_PACKAGE(<name> [major.minor] [QUIET] [NO_MODULE] [[REQUIRED|COMPONENTS] [componets...]])
# QUIET 会执行 caffeReadImgClassify_FIND_QUIETLY,如果不指定这个参数,就会执行
# MESSAGE(STATUS "Found caffeReadImgClassify: &{caffeReadImgClassify_LIBRARY}")
# REQUIRED 参数, 其含义是这个共享库是否是工程必须的,如果使用了这个参数,说明这个链接库是必须库,
# 如果找不到这个链接库,则工程不能编译,对应于.cmake模块中的HELLO_FIND_REQUIRED 变量

link_directories("/usr/local/lib/")
# 添加非标准共享库的搜索路径, 如果,在工程内部同时存在共享库和可执行二进制, 在编译时就需要指定一下这些共享库的路径.

set(SOURCE_FILES main.cpp)

add_executable(caffeReadImgClassify ${SOURCE_FILES})
# cmake会自动的在本目录查找main.c或者main.cpp等,但是最好不要投这个懒,万一目录中有 main.

target_link_libraries(caffeReadImgClassify ${OpenCV_LIBS})
# TARGET_LINK_LIBRARIES(target library1 <debug | optimized> library2 ...)
# 这个指令可以用来为target添加需要链接的共享库,本例中是一个可执行文件,但是同样可以用于为自己编写的共享库
# 添加共享库链接

再看main.cpp的内容,这部分内容和caffe目录下的test中的cpp接口差不多

#include <iostream>
#include "opencv2/opencv.hpp"
#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 <boost/smart_ptr/shared_ptr.hpp>
#include "openslide/openslide.h"
using boost::shared_ptr;
using namespace caffe;  // NOLINT(build/namespaces)
using std::string;
using namespace std;
using namespace cv;
/* 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<Prediction> 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<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_;
    std::vector<string> labels_;
};

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));
    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.";
}

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.";
}



int main() {

    const char *fileName = "/home../tempC5.jpg";
    string model_file = "/home/../profile/deploy_vgg16_places365.prototxt";
    string trained_file = "/home/../vgg16-model/vgg_iter_100000.caffemodel";
    string mean_file = "/home/../lmdb_5/train_mean.binaryproto";
    string label_file = "/home/hjxu/CLionProjects/caffeClassification/labels.txt";

    Classifier classifier(model_file, trained_file, mean_file, label_file);

    cv::Mat img = cv::imread(fileName, -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;
    }
//

}

由于CSDN在ubuntu下代码不清洁的问题, 现将工程逐步更新到github上,本例子github地址如下:

https://github.com/hjxu2016/caffeReadImgClassify