caffe笔记

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

①  文字识别例子

#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[*];

    //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(,,CV_8UC1,cv::Scalar());
    cv::putText(gray,argv[],cv::Point(,),,1.4,cv::Scalar(),);

    //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=;i<*;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[],caffe::TEST);

    //load net train file caffemodel
    lenet.CopyTrainedLayersFrom(argv[]);

    Blob<type> *input_ptr = lenet.input_blobs()[];
    input_ptr->Reshape(,,,);

    Blob<type> *output_ptr= lenet.output_blobs()[];
    output_ptr->Reshape(,,,);

    //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=;
    for(int i=;i<;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=;i<;i++)
        cout<<i<<"\t"<<begin[i]<<endl;

    // 展示最后的预测结果
    cout<<"res:\t"<<index<<"\t"<<begin[index]<<endl;
    return ;
}

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 = );

 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(), ) << "Network should have exactly one input.";
  CHECK_EQ(net_->num_outputs(), ) << "Network should have exactly one output.";

  Blob<float>* input_layer = net_->input_blobs()[];
  num_channels_ = input_layer->channels();
  CHECK(num_channels_ ==  || num_channels_ == )
    << "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()[];
  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 = ; 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 = ; 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 = ; 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 = ; 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()[];
  input_layer->Reshape(, 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()[];
  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()[];

  int width = input_layer->width();
  int height = input_layer->height();
  float* input_data = input_layer->mutable_cpu_data();
  for (int i = ; 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() ==  && num_channels_ == )
    cv::cvtColor(img, sample, cv::COLOR_BGR2GRAY);
  else if (img.channels() ==  && num_channels_ == )
    cv::cvtColor(img, sample, cv::COLOR_BGRA2GRAY);
  else if (img.channels() ==  && num_channels_ == )
    cv::cvtColor(img, sample, cv::COLOR_BGRA2BGR);
  else if (img.channels() ==  && num_channels_ == )
    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_ == )
    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().data)
        == net_->input_blobs()[]->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 != ) {
    std::cerr << "Usage: " << argv[]
              << " deploy.prototxt network.caffemodel"
              << " mean.binaryproto labels.txt img.jpg" << std::endl;
    return ;
  }

  ::google::InitGoogleLogging(argv[]);

  string model_file   = argv[];
  string trained_file = argv[];
  string mean_file    = argv[];
  string label_file   = argv[];
  Classifier classifier(model_file, trained_file, mean_file, label_file);    //*.caffemodel.h5      

  string file = argv[];

  std::cout << "---------- Prediction for "
            << file << " ----------" << std::endl;

  cv::Mat img = cv::imread(file, -);
  CHECK(!img.empty()) << "Unable to decode image " << file;
  std::vector<Prediction> predictions = classifier.Classify(img);

  /* Print the top N predictions. */
  for (size_t i = ; i < predictions.size(); ++i) {
    Prediction p = predictions[i];
    std::cout << std::fixed << std::setprecision() << 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