caffe之classification.cpp & cmake
来源:互联网 发布:linux配置tomcat 编辑:程序博客网 时间:2024/06/03 13:15
classification.cpp
#include <caffe/caffe.hpp>#ifdef USE_OPENCV#include <opencv2/core/core.hpp>#include <opencv2/highgui/highgui.hpp>#include <opencv2/imgproc/imgproc.hpp>#endif // USE_OPENCV#include <algorithm>#include <iosfwd>#include <memory>#include <string>#include <utility>#include <vector>#ifdef USE_OPENCVusing 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) { if (argc != 6) { std::cerr << "Usage: " << argv[0] << " deploy.prototxt network.caffemodel" << " mean.binaryproto labels.txt img.jpg" << std::endl; return 1; } ::google::InitGoogleLogging(argv[0]); string model_file = argv[1]; string trained_file = argv[2]; string mean_file = argv[3]; string label_file = argv[4]; Classifier classifier(model_file, trained_file, mean_file, label_file); string file = argv[5]; std::cout << "---------- Prediction for " << file << " ----------" << std::endl; cv::Mat img = cv::imread(file, -1); CHECK(!img.empty()) << "Unable to decode image " << file; std::vector<Prediction> predictions = classifier.Classify(img); /* 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; }}#elseint main(int argc, char** argv) { LOG(FATAL) << "This example requires OpenCV; compile with USE_OPENCV.";}#endif // USE_OPENCV
cmakelists.txt
cmake_minimum_required(VERSION 2.8)find_package(Caffe)include_directories(${Caffe_INCLUDE_DIRS})add_definitions(${Caffe_DEFINITIONS})add_executable(classification.bin main.cpp)target_link_libraries(yourApplication ${Caffe_LIBRARIES})
sh
#!/usr/bin/env shclearcdcd caffe-masterclass_path=examples/my_imagenet/classdir=$(ls $class_path)for i in $dirdo echo "图像为$i" ./build/examples/cpp_classification/classification.bin \ examples/my_imagenet/lenet_train_test.prototxt \ examples/my_imagenet/lenet_iter_10000.caffemodel \ examples/my_imagenet/imagenet_mean.binaryproto \ examples/my_imagenet/class.txt \ examples/my_imagenet/class/$idone
deploy.prototxt
name: "LeNet"layer { name: "data" type: "Input" top: "data" input_param { shape: { dim: 1 dim: 3 dim: 28 dim: 28 } }}layer { name: "conv1" type: "Convolution" bottom: "data" top: "conv1" convolution_param { num_output: 20 kernel_size: 5 stride: 1 weight_filler { type: "xavier" } }}layer { name: "pool1" type: "Pooling" bottom: "conv1" top: "pool1" pooling_param { pool: MAX kernel_size: 2 stride: 2 }}layer { name: "conv2" type: "Convolution" bottom: "pool1" top: "conv2" convolution_param { num_output: 50 kernel_size: 5 stride: 1 weight_filler { type: "xavier" } }}layer { name: "pool2" type: "Pooling" bottom: "conv2" top: "pool2" pooling_param { pool: MAX kernel_size: 2 stride: 2 }}layer { name: "ip1" type: "InnerProduct" bottom: "pool2" top: "ip1" inner_product_param { num_output: 500 weight_filler { type: "xavier" } }}layer { name: "relu1" type: "ReLU" bottom: "ip1" top: "ip1"}layer { name: "ip2" type: "InnerProduct" bottom: "ip1" top: "ip2" inner_product_param { num_output: 10 weight_filler { type: "xavier" } }}layer { name: "prob" type: "Softmax" bottom: "ip2" top: "prob"}
0 0
- caffe之classification.cpp & cmake
- caffe之classification.cpp 接口源码解读
- Caffe之Classification
- 关于caffe做分类的classification.cpp
- caffe 中classification.cpp的源码注释
- Caffe--在caffe外面使用classification.cpp进行分类预测
- caffe中去掉均值文件的classification.cpp
- Caffe C++接口实现图像分类(非官方Classification.cpp)
- 改写caffe classification.cpp使其支持批量读取图片
- caffe 中classification.cpp的源码详解、改写
- caffe学习:通过研读classification.cpp了解如何使用caffe模型
- caffe源码之blob.cpp
- 【caffe-Windows】mnist实例编译之model的使用-classification
- 【caffe-Windows】mnist实例编译之model的使用-classification
- caffe之blob_demo.cpp正常运行大法
- 四、caffe.cpp之命令解析
- caffe之blob_demo.cpp正常运行大法
- caffe introduction & classification
- 赫夫曼编码C语言实现
- 动态替换文本中部分内容
- 线性查找相关算法
- android surface管理
- C#身份证验证封装的函数方法
- caffe之classification.cpp & cmake
- 仿京东地址选择器
- Unity-Android通信
- 如何删除openfire for苹果,彻底卸载!
- 关于ios发布的一些问题,待补充
- was启动时9080端口被占用,如何关闭FIN_WAIT1状态的连接
- 用jquery添加新的类名后,却无法新添加的类名进行操作
- 多线程程序设计-------------(Linux---C)
- 郝斌数据结构 28 链表的插入和删除算法的演示