1. 训练 cifar10 示例
①
cd caffe.1.0.0
./data/cifar10/get_cifar10.sh #获取图片
② ./examples/cifar10/create_cifar10.sh #图片转换为cifar10_train_lmdb 并且求其均值保存为mean.binaryproto
③ cifar10_quick_solver.prototxt 编写的模型参数
cifar10_quick_solver的CNN模型由卷基层(convolution)、池化层(pooling)、非线性ReLU层(rectified linear unit (ReLU) nonlinearities)和在顶端的局部对比归一化线性分类器组成(local contrast normalization with a linear classifier on top of it all)。
④ time sh ./examples/cifar10/train_quick.sh # 训练 加time 能显示训练的时长。
⑤ 训练生成的文件
- cifar10_quick_iter_5000.caffemodel.h5：迭代5000次训练出来的模型，后面就用这个模型来做分类
- cifar10_quick_iter_5000.solverstate.h5：也是迭代5000次训练出来的模型，应该是用来中断后继续训练用的文件。
对于如何使用自己训练好的cifar10_quick_iter_5000.caffemodel.h5模型进行图片预测，会在随后的笔记中进行讲解。
⑥ prototxt 参数
cifar10_quick_solver的CNN模型由卷基层(convolution)、池化层(pooling)、非线性ReLU层
2. 使用
https://blog.csdn.net/fengbingchun/article/details/72999346
#include <iostream> #include <opencv2/opencv.hpp> #include <caffe/caffe.hpp> #include <string> using namespace caffe; using namespace std; int main(int argc,char* argv[]) { typedef float type; type ary[28*28]; //在28*28的图片颜色为RGB(255,255,255)背景上写RGB(0,0,0)数字. cv::Mat gray(28,28,CV_8UC1,cv::Scalar(255)); cv::putText(gray,argv[3],cv::Point(4,22),5,1.4,cv::Scalar(0),2); //将图像的数值从uchar[0,255]转换成float[0.0f,1.0f],的数, 且颜色取相反的 . for(int i=0;i<28*28;i++){ // f_val =(255-uchar_val)/255.0f ary[i] = static_cast<type>(gray.data[i]^0xFF)*0.00390625; } cv::imshow("x",gray); cv::waitKey(); //set cpu running software Caffe::set_mode(Caffe::CPU); //load net file , caffe::TEST 用于测试时使用 Net<type> lenet(argv[1],caffe::TEST); //load net train file caffemodel lenet.CopyTrainedLayersFrom(argv[2]); Blob<type> *input_ptr = lenet.input_blobs()[0]; input_ptr->Reshape(1,1,28,28); Blob<type> *output_ptr= lenet.output_blobs()[0]; output_ptr->Reshape(1,10,1,1); //copy data from <ary> to <input_ptr> input_ptr->set_cpu_data(ary); //begin once predict lenet.Forward(); const type* begin = output_ptr->cpu_data(); // get the maximum index int index=0; for(int i=1;i<10;i++){ if(begin[index]<begin[i]) index=i; } // 打印这次预测[0,9]的每一个置信度 for(int i=0;i<10;i++) cout<<i<<" "<<begin[i]<<endl; // 展示最后的预测结果 cout<<"res: "<<index<<" "<<begin[index]<<endl; return 0; }
② C++ 调用cirfar10 的model
//classification.bin deploy.prototxt bvlc_reference_caffenet.caffemodel magenet_mean.binaryproto synset_words.txt cat.jpg
#include <caffe/caffe.hpp> #define USE_OPENCV #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_OPENCV 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."; } //classification.bin deploy.prototxt bvlc_reference_caffenet.caffemodel magenet_mean.binaryproto synset_words.txt cat.jpg 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); //*.caffemodel.h5 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; } } #else int main(int argc, char** argv) { LOG(FATAL) << "This example requires OpenCV; compile with USE_OPENCV."; } #endif // USE_OPENCV