深度学习caffe中的分类程序（classification）制作成动态链接库（dll）

          最近因公司项目需要把caffe中的classification分类程序融入到自己的项目程序中，因此把Caffe中的classification封装成dll供源程序进行调用。经过两天的不懈努力，终于把caffe中的分类程序封装成dll，以供项目程序调用。在此中间遇到各种库依赖的问题，在这进行相应的总结，以备文档留存。

 

第一：在VS2013下新建Win32控制台程序，命名为ClassJpg，下一步，勾选Dll与空项目，点击完成。

 

 

第二：点击属性VC++目录在包含目录中添加以下头文件路径，同时将caffe原工程的include目录复制到 caffe-class\include中。

 

// Debug & Rlease
E:\caffe-class\include
E:\caffe-class\NugetPackages\gflags.2.1.2.1\build\native\include
E:\caffe-class\NugetPackages\glog.0.3.3.0\build\native\include
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0\include
E:\caffe-class\NugetPackages\protobuf-v120.2.6.1\build\native\include
E:\caffe-class\NugetPackages\OpenCV.2.4.10\build\native\include
E:\caffe-class\NugetPackages\OpenBLAS.0.2.14.1\lib\native\include
E:\caffe-class\NugetPackages\boost.1.59.0.0\lib\native\include

 

第三：为工程添加相应的lib，点击属性VC++目录在库目录中添加以下库文件路径；

/ Debug
E:\caffe-class\caffelib
E:\caffe-class\NugetPackages\OpenCV.2.4.10\build\native\lib\x64\v120\Debug
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0\lib\x64
E:\caffe-class\NugetPackages\gflags.2.1.2.1\build\native\x64\v120\dynamic\Lib
E:\caffe-class\NugetPackages\glog.0.3.3.0\build\native\lib\x64\v120\Debug\dynamic
E:\caffe-class\NugetPackages\OpenBLAS.0.2.14.1\lib\native\lib\x64
E:\caffe-class\NugetPackages\protobuf-v120.2.6.1\build\native\lib\x64\v120\Debug
E:\caffe-class\NugetPackages\LevelDB-vc120.1.2.0.0\build\native\lib\x64\v120\Debug
E:\caffe-class\NugetPackages\hdf5-v120-complete.1.8.15.2\lib\native\lib\x64
E:\caffe-class\NugetPackages\boost_date_time-vc120.1.59.0.0\lib\native\address-model-64\lib
E:\caffe-class\NugetPackages\boost_filesystem-vc120.1.59.0.0\lib\native\address-model-64\lib
E:\caffe-class\NugetPackages\boost_system-vc120.1.59.0.0\lib\native\address-model-64\lib
E:\caffe-class\NugetPackages\boost_thread-vc120.1.59.0.0\lib\native\address-model-64\lib
E:\caffe-class\NugetPackages\boost_chrono-vc120.1.59.0.0\lib\native\address-model-64\lib

第四：添加相关的库依赖，打开属性-连接器-输入-附加依赖项中输入以下内容；

// Debug
libglog.lib 
libcaffe.lib         
gflagsd.lib   
gflags_nothreadsd.lib 
hdf5.lib         
hdf5_hl.lib     
libprotobuf.lib     
libopenblas.dll.a  
cublas.lib 
cuda.lib   
curand.lib 
cudart.lib 
cudnn.lib 
Shlwapi.lib
LevelDb.lib 
lmdbD.lib 
opencv_core2410d.lib       
opencv_highgui2410d.lib    
opencv_imgproc2410d.lib   
opencv_video2410d.lib      
opencv_objdetect2410d.lib
// Release
libglog.lib
libcaffe.lib
gflags.lib
gflags_nothreads.lib
hdf5.lib
hdf5_hl.lib
libprotobuf.lib
libopenblas.dll.a
cublas.lib
cuda.lib
curand.lib
cudart.lib
cudnn.lib
Shlwapi.lib
LevelDb.lib
lmdb.lib
opencv_core2410.lib
opencv_highgui2410.lib
opencv_imgproc2410.lib
opencv_video2410.lib
opencv_objdetect2410.lib

第五：在属性—C/C++—预处理器中添加以下命令；

_SCL_SECURE_NO_WARNINGS

第六：新建头文件命名为class-jpg-caffe.h，输入以下的类定义：

#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>

#pragma once

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

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

class  _declspec(dllexport)  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);

	~Classifier();

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_;
};

第七：新建头文件head.h，输入以下语句；

#include "caffe/common.hpp"
#include "caffe/layers/input_layer.hpp"
#include "caffe/layers/inner_product_layer.hpp"
#include "caffe/layers/dropout_layer.hpp"
#include "caffe/layers/conv_layer.hpp"
#include "caffe/layers/relu_layer.hpp"

#include "caffe/layers/pooling_layer.hpp"
#include "caffe/layers/lrn_layer.hpp"
#include "caffe/layers/softmax_layer.hpp"


namespace caffe
{

	extern INSTANTIATE_CLASS(InputLayer);
	extern INSTANTIATE_CLASS(InnerProductLayer);
	extern INSTANTIATE_CLASS(DropoutLayer);
	extern INSTANTIATE_CLASS(ConvolutionLayer);
	REGISTER_LAYER_CLASS(Convolution);
	extern INSTANTIATE_CLASS(ReLULayer);
	REGISTER_LAYER_CLASS(ReLU);
	extern INSTANTIATE_CLASS(PoolingLayer);
	REGISTER_LAYER_CLASS(Pooling);
	extern INSTANTIATE_CLASS(LRNLayer);
	REGISTER_LAYER_CLASS(LRN);
	extern INSTANTIATE_CLASS(SoftmaxLayer);
	REGISTER_LAYER_CLASS(Softmax);

}
第八：新建源文件命名为class-jpg-caffe.cpp，输入以下语句；
#include "class-jpg-caffe.h"
#include "head.h"

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
	Caffe::set_mode(Caffe::GPU);
	/* 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], static_cast<int>(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.";
}

Classifier::~Classifier()
{
｝