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()
{
}