Caffe--在caffe外面使用classification.cpp进行分类预测
2017-07-02 11:34
369 查看
1. classification.cpp
#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> using namespace caffe; // NOLINT(build/namespaces) using std::string; /* 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(int argc, char** argv) { clock_t start_time1,end_time1,start_time2,end_time2; ::google::InitGoogleLogging(argv[0]); string model_file = "/home/zwx/Test/lenet.prototxt"; string trained_file = "/home/zwx/Test/lenet_iter_10000.caffemodel"; string mean_file = "/home/zwx/Test/mean.binaryproto"; string label_file = "/home/zwx/Test/label.txt"; start_time1 = clock(); Classifier classifier(model_file, trained_file, mean_file, label_file); end_time1 = clock(); double seconds1 = (double)(end_time1-start_time1)/CLOCKS_PER_SEC; std::cout<<"init time="<<seconds1<<"s"<<std::endl; string file = "/home/zwx/Test/x3_11.bmp"; std::cout << "---------- Prediction for " << file << " ----------" << std::endl; cv::Mat img = cv::imread(file, -1); CHECK(!img.empty()) << "Unable to decode image " << file; start_time2 = clock(); std::vector<Prediction> predictions = classifier.Classify(img); end_time2 = clock(); double seconds2 = (double)(end_time2-start_time2)/CLOCKS_PER_SEC; std::cout<<"classify time="<<seconds2<<"s"<<std::endl; /* 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; } 这里写代码片 }
2. CMakeLists.txt
cmake_minimum_required(VERSION 2.8.8) set(Caffe_DIR /home/xxx这里写代码片/caffe/build) find_package(Caffe REQUIRED) if (NOT Caffe_FOUND) message(FATAL_ERROR "Caffe NOT Fund!") endif (NOT Caffe_FOUND) include_directories(${Caffe_INCLUDE_DIRS}) add_definitions(${Caffe_DEFINITIONS}) # ex. -DCPU_ONLY add_executable(classification classification.cpp) target_link_libraries(classification ${Caffe_LIBRARIES})
如果在CMAKE_MODULE_PATH中找不到caffe。
那么原因可能是因为安装过程是直接make caffe的,没有对caffe使用cmake。而只有使用了cmake,才能在CMAKE_MODULE_PATH中加入caffe,这样find_package()才能找到caffe。
既然这样,只有cmake caffe了。在caffe里面建立了个cbuild文件夹,执行:cmake ..
3. 使用cmake
,make
进行编译
出现下列错误:fatal error: caffe/proto/caffe.pb.h: No such file or directory
解决办法:参考
$ cd /home/xxx/caffe $ protoc src/caffe/proto/caffe.proto --cpp_out=. $ mkdir include/caffe/proto $ mv src/caffe/proto/caffe.pb.h include/caffe/proto
相关文章推荐
- 使用caffe训练好的模型进行分类
- 深度学习Caffe平台实例——CIFAR-10数据集在caffe平台上模型训练及实例使用模型进行预测
- 使用深度学习Caffe框架的C++接口进行物体分类
- caffe学习--使用caffe中的imagenet对自己的图片进行分类训练(超级详细版) -----linux
- 使用caffe中的imagenet对自己的图片进行分类训练(超级详细版)
- 关于caffe做分类的classification.cpp
- 数据挖掘-K-近邻分类器-Iris数据集分析-使用K-近邻分类器进行分类预测(四)
- 使用Spark MLlib的逻辑回归(LogisticRegression)进行用户分类预测识别
- 【TensorFlow】Caffe模型转tensorflow模型并使用模型进行预测
- 使用MATLAB加载训练好的caffe模型进行识别分类
- 使用caffe中的imagenet对自己的图片进行分类训练(超级详细版)
- caffe+python 使用训练好的VGG16模型 对 单张图片进行分类,输出置信度
- 【神经网络与深度学习】【Qt开发】【VS开发】从caffe-windows-visual studio2013到Qt5.7使用caffemodel进行分类的移植过程<二>
- 【TensorFlow】Caffe模型转tensorflow模型并使用模型进行预测
- 使用caffe中的imagenet对自己的图片进行分类训练(超级详细版)
- Linux下使用Caffe对图片进行训练并分类的简单流程
- !!使用Caffe对图片进行训练并分类的简单流程
- 怎么使用 Caffe 进行 LetNet-5 的训练和预测
- 【Caffe的C++接口使用说明(三)】Ubuntu14.04下Caffe利用训练好的模型进行分类的C++接口使用说明(三)
- Windows10上使用Caffe的Python接口进行图像分类例程