MFC/Qt下呼叫caffe原始碼（一）---將caffe原始碼生成動態連結庫dll
阿新 • • 發佈：2018-12-21
本人研一，最近想將用caffe訓出的模型，通過MFC做出一個介面，扔進一張圖片，點選預測，即可呼叫預測分類函式完成測試，並且通過MessageBox彈出最終分類的資訊。
首先通過查資料總結出兩種方法，第一：直接呼叫編譯好的caffe原始碼；（本次用到的原始碼是classification.cpp）
第二：將caffe原始碼生成動態連結庫dll,然後在其它工程專案下進行呼叫。由於caffe的原始碼依賴 項太多，稍微錯一點就編譯不通過，故本次操作採用呼叫dll的方式。
1.win7 vs2013,新建win32控制檯程式，如下所示：
2.首先將專案的屬性改成release和x64編譯模式，新增兩個.h檔案和一個cpp檔案：
（1）我採用的是dllexport方式匯出的，採用了條件編譯，要將DLL_EXPORTS巨集定義加入到前處理器中以及_SCL_SECURE_NO_WARNINGS
Tip:.h檔案 #ifndef CAFFE_CLASSIFY_H_ #define CAFFE_CLASSIFY_H_ #define CPU_ONLY 1 #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; using std::string; using namespace std; using boost::shared_ptr; #ifdef DLL_EXPORTS #define DLL_EXPORTS_API _declspec(dllexport) #else #define DLL_EXPORTS_API _declspec(dllimport) #endif /* Pair (label, confidence) representing a prediction. */ typedef std::pair<string, float> Prediction; class DLL_EXPORTS_API 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: boost::shared_ptr<Net<float> > net_; cv::Size input_geometry_; int num_channels_; cv::Mat mean_; std::vector<string> labels_; }; #endif
（2）.
Tip .h檔案，此檔案是關於層的，缺哪個新增哪個。之前按照網上部落格抄的，後來執行的時候報錯：Unkown Layer 。後來想起來我的網路裡面用到了Concat Layer，後來就自己添加了，特別注意：直接extern 就行，不用REGISTER_LAYER_CLASS(Concat); #ifndef LAYER_H #define LAYER_H #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" #include "caffe/layers/concat_layer.hpp" namespace caffe { extern INSTANTIATE_CLASS(InputLayer); extern INSTANTIATE_CLASS(InnerProductLayer); extern INSTANTIATE_CLASS(DropoutLayer); extern INSTANTIATE_CLASS(ConcatLayer); 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); //extern INSTANTIATE_CLASS(ConcatLayer); //REGISTER_LAYER_CLASS(Concat); } #endif
（3）將classification的原始檔賦值到cpp中，注意新增標頭檔案；
.cpp檔案
#include "Header.h"
#include "SingleDll.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()
{}
3.開啟屬性管理器，新增caffe相關依賴項。新增完可能會報各種can not open XXX.lib的錯誤。莫著急，這都是由於粗心路徑不對造成的，要注意細節。
包含目錄：
D:\caffe\NugetPackages\gflags.2.1.2.1\build\native\include
D:\caffe\NugetPackages\glog.0.3.3.0\build\native\include
D:\caffe\NugetPackages\protobuf-v120.2.6.1\build\native\include
D:\caffe\NugetPackages\OpenCV.2.4.10\build\native\include
D:\caffe\NugetPackages\OpenBLAS.0.2.14.1\lib\native\include
D:\caffe\NugetPackages\boost.1.59.0.0\lib\native\include
還要加上caffe編譯完生成的include路徑，最好將其複製到該專案下
eg.D:\caffe-class\include
庫目錄：
E:\caffe\NugetPackages\OpenCV.2.4.10\build\native\lib\x64\v120\Release
E:\caffe\NugetPackages\gflags.2.1.2.1\build\native\x64\v120\dynamic\Lib
E:\caffe\NugetPackages\glog.0.3.3.0\build\native\lib\x64\v120\Release \dynamic
E:\caffe\NugetPackages\OpenBLAS.0.2.14.1\lib\native\lib\x64
E:\caffe\NugetPackages\protobuf-v120.2.6.1\build\native\lib\x64\v120\Release
E:\caffe\NugetPackages\LevelDB-vc120.1.2.0.0\build\native\lib\x64\v120\Release
E:\caffe\NugetPackages\hdf5-v120-complete.1.8.15.2\lib\native\lib\x64
E:\caffe\NugetPackages\boost_date_time-vc120.1.59.0.0\lib\native\address-model-64\lib
E:\caffe\NugetPackages\boost_filesystem-vc120.1.59.0.0\lib\native\address-model-64\lib
E:\caffe\NugetPackages\boost_system-vc120.1.59.0.0\lib\native\address-model-64\lib
E:\caffe\NugetPackages\boost_thread-vc120.1.59.0.0\lib\native\address-model-64\lib
E:\caffe\NugetPackages\boost_chrono-vc120.1.59.0.0\lib\native\address-model-64\lib
注意還需新增caffe編譯生成的release檔案Tip：上述庫目錄中少了lmdb ，自己別忘了
新增依賴項
libglog.lib
libcaffe.lib
gflags.lib
gflags_nothreads.lib
hdf5.lib
hdf5_hl.lib
libprotobuf.lib
libopenblas.dll.a
Shlwapi.lib
LevelDb.lib
lmdb.lib
opencv_core2410.lib
opencv_highgui2410.lib
opencv_imgproc2410.lib
opencv_video2410.lib
opencv_objdetect2410.lib
注意：由於我是cpu條件下編譯的（加了巨集定義CPU_ONLY），若您是GPU 則要新增相應的cudn的路徑，以及
cublas.lib
cuda.lib
curand.lib
cudart.lib
cudnn.lib 這些依賴項！！
4.編譯生成，會發現生成dll lib等檔案，但是沒有ink，不知道為啥，那不重要。
最後第一篇生成dll檔案就講解到這裡，生成完後可以測試一下能不能用。我也是先測試能用，才新建MFC工程進行呼叫的。
下次就為大家講解MFC下呼叫，具體實現MFC呼叫caffemodel實現過程。
若需要help,QQ 1443563995.如有錯誤，多多指教！