python输出activation map与层参数：https://blog.csdn.net/tina_ttl/article/details/51033660
caffe::Net文档：
https://caffe.berkeleyvision.org/doxygen/classcaffe_1_1Net.html#a6f6cf9d40637f7576828d856bb1b1826
caffe::Blob文档：
http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1Blob.html
图像通道分离与合并cv::split() cv::merge()
https://blog.csdn.net/guduruyu/article/details/70837779
caffe官方提供的prediction代码
caffe提供了一个用已经训练好的caffemodel来分类单张图片的库(./build/examples/cpp_classification/classification.bin)，该库的源码为文件./examples/cpp-classification/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_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_; }; /*分类对象构造文件*/ 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)); /*复制网络结构*/ net_->CopyTrainedLayersFrom(trained_file); /*加载caffemodel,该函数在net.cpp中实现*/ 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(); /*该网络结构所要求的图片输入通道数*/ 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()); /*输入层需要的图片宽高*/ /* Load the binaryproto mean file. */ SetMean(mean_file); /*加载均值文件*/ /* Load labels. */ std::ifstream labels(label_file.c_str()); /*加载标签名称文件*/ 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]; /*检查标签个数与网络的输出结点个数是否一样*/ 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); /*调用这个函数做分类*/ 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); /*读入均值文件在Io.cpp中实现*/ /* Convert from BlobProto to Blob<float> */ Blob<float> mean_blob; mean_blob.FromProto(blob_proto); /*将读入的均值文件转成Blob对象*//*Blob类在Blob.hpp中定义*/ 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(); } /*将均值图像的每个通道图像拷贝到channel中*/ /* Merge the separate channels into a single image. */ cv::Mat mean; cv::merge(channels, mean); /*合并每个通道图像*/ /* 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); } /*测试函数*/ 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);/*没太看懂，应该是一些缩放*/ /* Forward dimension change to all layers. */ net_->Reshape(); std::vector<cv::Mat> input_channels; WrapInputLayer(&input_channels);/*对输入层数据进行包装*/ Preprocess(img, &input_channels); /*把传入的测试图像写入到输入层*/ net_->Forward(); /*网络前向传播：计算出该测试图像属于哪个每个类别的概率也就是最终的输出层*/ /* Copy the output layer to a std::vector */ Blob<float>* output_layer = net_->output_blobs()[0]; /*将输出层拷贝到向量*/ 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;/*将输入的图像转换成输入层需要的图像格式*/ cv::Mat sample_resized; if (sample.size() != input_geometry_) cv::resize(sample, sample_resized, input_geometry_); /*如果大小不一致则需要缩放*/ else sample_resized = sample; cv::Mat sample_float; if (num_channels_ == 3) sample_resized.convertTo(sample_float, CV_32FC3); /*将数据转化成浮点型*/ else sample_resized.convertTo(sample_float, CV_32FC1); cv::Mat sample_normalized; cv::subtract(sample_float, mean_, sample_normalized); /*应该是当前图像减去均值图像*/ /* 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); /*把测试的图像通过之前的定义的wraper写入到输入层*/ 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]; /*标识网络结构的deploy.prototxt文件*/ string trained_file = argv[2]; /*训练出来的模型文件caffemodel*/ string mean_file = argv[3]; /*均值.binaryproto文件*/ string label_file = argv[4]; /*标签文件:标识类别的名称*/ Classifier classifier(model_file, trained_file, mean_file, label_file); /*创建对象并初始化网络、模型、均值、标签各类对象*/ string file = argv[5]; /*传入的待测试图片*/ 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); /*具体测试传入的图片并返回测试的结果：类别ID与概率值的Prediction类型数组*/ /* Print the top N predictions. *//*将测试的结果打印*/ 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
输出activation map代码
输出层参数代码
本站文章如无特殊说明，均为本站原创，如若转载，请注明出处：c++ caffe 输出 activation map 、 层参数 - Python技术站
微信扫一扫 
支付宝扫一扫 
