本文假设你已经安装CUDA,CUDA版本是7.5。
caffe.pb.h
和caffe.pb.cc
两个c++文件,和caffe_pb2.py
这个python使用的文件。然后,用vs2013打开./buildVS2013/MainBuilder.sln,打开之后切换编译模式至Release X64模式。如果你的CUDA版本不是7.5,打开之后可能显示加载失败,这时就要用记事本打开./buildVS2013/MSVC/MainBuilder.vcxproj,搜索CUDA 7.5,把这个7.5换成你自己的CUDA版本,就可以正常打开了。
../../3rdparty/include ../../src ../../include C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v7.5\include链接器 ——> 常规,附加库目录修改如下(CUDA路径按自己的修改):
../../3rdparty/lib ..\..\bin C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v7.5\lib\x64
Matcaffe项目:
附加包含目录:
../../3rdparty/include ../../src ../../include C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v7.5\include D:\Program Files\MATLAB\R2014a\extern\include
附加库目录:
../../3rdparty/lib C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v7.5\lib\x64 D:\Program Files\MATLAB\R2014a\extern\lib\win64\microsoft
Pycaffe项目:
附加包含目录:
../../3rdparty/include ../../src ../../include C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v7.5\include D:\Python27\include D:\Python27\Lib\site-packages\numpy\core\include
附加库目录:
../../3rdparty/lib C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v7.5\lib\x64 D:\Python27\libs
#include <caffe/caffe.hpp> #include <opencv2/core/core.hpp> #include <opencv2/highgui/highgui.hpp> #include <opencv2/imgproc/imgproc.hpp> #include <iosfwd> #include <memory> #include <utility> #include <vector> #include <iostream> #include <string> #include <fstream> using namespace caffe; using std::string; 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 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()); SetMean(mean_file); std::ifstream labels(label_file); 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; } 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; } std::vector<Prediction> Classifier::Classify(const cv::Mat& img, int N) { std::vector<float> output = Predict(img); 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; } void Classifier::SetMean(const string& mean_file) { BlobProto blob_proto; ReadProtoFromBinaryFileOrDie(mean_file.c_str(), &blob_proto); 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."; std::vector<cv::Mat> channels; float* data = mean_blob.mutable_cpu_data(); for (int i = 0; i < num_channels_; ++i) { cv::Mat channel(mean_blob.height(), mean_blob.width(), CV_32FC1, data); channels.push_back(channel); data += mean_blob.height() * mean_blob.width(); } cv::Mat mean; cv::merge(channels, mean); 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); net_->Reshape(); std::vector<cv::Mat> input_channels; WrapInputLayer(&input_channels); Preprocess(img, &input_channels); net_->ForwardPrefilled(); 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); } 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) { cv::Mat sample; if (img.channels() == 3 && num_channels_ == 1) cv::cvtColor(img, sample, CV_BGR2GRAY); else if (img.channels() == 4 && num_channels_ == 1) cv::cvtColor(img, sample, CV_BGRA2GRAY); else if (img.channels() == 4 && num_channels_ == 3) cv::cvtColor(img, sample, CV_BGRA2BGR); else if (img.channels() == 1 && num_channels_ == 3) cv::cvtColor(img, sample, CV_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); 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(int argc, char** argv) { #ifdef _MSC_VER #pragma comment( linker, "/subsystem:\"windows\" /entry:\"mainCRTStartup\"" ) #endif ::google::InitGoogleLogging(argv[0]); string model_file = "C:\\Users\\Desktop\\classification\\ResNet\\deploy.prototxt"; string trained_file = "C:\\Users\\Desktop\\classification\\ResNet\\ResNet_iter_150000.caffemodel"; string mean_file = "C:\\Users\\Desktop\\classification\\ResNet\\my_mean.binaryproto"; string label_file = "C:\\Users\\Desktop\\classification\\ResNet\\car_words.txt"; string picture_path = "C:\\Users\\Desktop\\classification\\car.jpg"; Classifier classifier(model_file, trained_file, mean_file, label_file); cv::Mat img = cv::imread(picture_path, -1); cv::Mat img2; std::vector<Prediction> predictions = classifier.Classify(img); Prediction p = predictions[0]; CvSize sz; sz.width = img.cols; sz.height = img.rows; float scal = 0; scal = sz.width > sz.height ? (300 / (float)sz.width) : (300 / (float)sz.height); sz.width *= scal; sz.height *= scal; resize(img, img2, sz, 0, 0, CV_INTER_LINEAR); /*********************用FreeType库输出中文***********************/ string text = p.first; char buff[20]; _gcvt(p.second, 4, buff); text = text + ":" + buff; CvxText mytext("../../model/simhei.ttf"); const char *msg = text.c_str(); CvScalar size; size.val[0] = 26; size.val[1] = 0.5; size.val[2] = 0.1; size.val[3] = 0; mytext.setFont(NULL,&size, NULL, NULL); // 设置字体大小 mytext.putText(&IplImage(img2), msg, cvPoint(50, 50), cvScalar(0, 0, 255, NULL)); /*********************************************************/ IplImage* show = cvCreateImage(sz, IPL_DEPTH_8U, 3); cvCopy(&(IplImage)img2, show); cvNamedWindow("结果展示"); cvShowImage("结果展示", show); int c = cvWaitKey(); cvDestroyWindow("结果展示"); cvReleaseImage(&show); return 0; }
将caffe.cpp中的main函数注释掉就可以了。