修改多个输入的 Caffe C++ 预测代码

Question

我实现了Caffe C++ example 的修改版本，虽然它工作得非常好，但速度非常慢，因为它只接受一张一张的图像。理想情况下，我想向 Caffe 传递一个包含 200 个图像的向量并返回每个图像的最佳预测。我收到了一些great help from Fanglin Wang 并实施了他的一些建议，但在弄清楚如何从每张图像中检索最佳结果时仍然遇到了一些麻烦。

Classify 方法现在传递了一个cv::Mat 对象的向量（变量input_channels），它是一个灰度浮点图像的向量。我已经消除了代码中的预处理方法，因为我不需要将这些图像转换为浮点数或减去平均图像。我也一直在尝试摆脱 N 变量，因为我只想返回每个图像的最高预测和概率。

#include "Classifier.h"
using namespace caffe;
using std::string;

Classifier::Classifier(const string& model_file, const string& trained_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);

  Blob<float>* input_layer = net_->input_blobs()[0];
  num_channels_ = input_layer->channels();
  input_geometry_ = cv::Size(input_layer->width(), input_layer->height());

  /* 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 std::vector<cv::Mat> &input_channels) {
  std::vector<float> output = Predict(input_channels);

    std::vector<int> maxN = Argmax(output, 1);
    int idx = maxN[0];
    predictions.push_back(std::make_pair(labels_[idx], output[idx]));
    return predictions;
}

std::vector<float> Classifier::Predict(const std::vector<cv::Mat> &input_channels, int num_images) {
  Blob<float>* input_layer = net_->input_blobs()[0];
  input_layer->Reshape(num_images, num_channels_,
                       input_geometry_.height, input_geometry_.width);
  /* Forward dimension change to all layers. */
  net_->Reshape();

  WrapInputLayer(&input_channels);

  net_->ForwardPrefilled();

  /* 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 + num_images * 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() * num_images; ++i) {
    cv::Mat channel(height, width, CV_32FC1, input_data);
    input_channels->push_back(channel);
    input_data += width * height;
  }
}

更新

非常感谢您的帮助 Shai，我进行了您推荐的更改，但似乎遇到了一些我无法解决的奇怪编译问题（我设法解决了一些问题）。

这些是我所做的更改：

头文件：

#ifndef __CLASSIFIER_H__
#define __CLASSIFIER_H__

#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& label_file);

  std::vector< std::pair<int,float> > Classify(const std::vector<cv::Mat>& img);

 private:

  std::vector< std::vector<float> > Predict(const std::vector<cv::Mat>& img, int nImages);

  void WrapInputLayer(std::vector<cv::Mat>* input_channels, int nImages);

  void Preprocess(const std::vector<cv::Mat>& img,
                  std::vector<cv::Mat>* input_channels, int nImages);

 private:
  shared_ptr<Net<float> > net_;
  cv::Size input_geometry_;
  int num_channels_;
  std::vector<string> labels_;
};

#endif /* __CLASSIFIER_H__ */

类文件：

#define CPU_ONLY
#include "Classifier.h"

using namespace caffe;  // NOLINT(build/namespaces)
using std::string;

Classifier::Classifier(const string& model_file,
                       const string& trained_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 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;
}

std::vector< std::pair<int,float> > Classifier::Classify(const std::vector<cv::Mat>& img) {
  std::vector< std::vector<float> > output = Predict(img, img.size());

  std::vector< std::pair<int,float> > predictions;
  for ( int i = 0 ; i < output.size(); i++ ) {
    std::vector<int> maxN = Argmax(output[i], 1);
    int idx = maxN[0];
    predictions.push_back(std::make_pair(labels_[idx], output[idx]));
  }
  return predictions;
}

std::vector< std::vector<float> > Classifier::Predict(const std::vector<cv::Mat>& img, int nImages) {
  Blob<float>* input_layer = net_->input_blobs()[0];
  input_layer->Reshape(nImages, 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, nImages);

  Preprocess(img, &input_channels, nImages);

  net_->ForwardPrefilled();

  /* Copy the output layer to a std::vector */

  Blob<float>* output_layer = net_->output_blobs()[0];
  std::vector <std::vector<float> > ret;
  for (int i = 0; i < nImages; i++) {
    const float* begin = output_layer->cpu_data() + i*output_layer->channels();
    const float* end = begin + output_layer->channels();
    ret.push_back( std::vector<float>(begin, end) );
  }
  return ret;
}

/* 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, int nImages) {
  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()* nImages; ++i) {
    cv::Mat channel(height, width, CV_32FC1, input_data);
    input_channels->push_back(channel);
    input_data += width * height;
  }
}

void Classifier::Preprocess(const std::vector<cv::Mat>& img,
                            std::vector<cv::Mat>* input_channels, int nImages) {
  for (int i = 0; i < nImages; i++) {
      vector<cv::Mat> channels;
      cv::split(img[i], channels);
      for (int j = 0; j < channels.size(); j++){
           channels[j].copyTo((*input_channels)[i*num_channels_[0]+j]);
      }
  }
}

Answer 1

不幸的是，我认为网络前向传递的并行化尚未实现。但是，如果您愿意，您可以简单地实现自己的包装器，以并行地通过网络副本重复运行数据？

看看How many images can you pass to Caffe at a time?

在链接的 prototxt 中你需要定义的是

input_shape {
  dim: 64 // num of images
  dim: 1
  dim: 28 // height
  dim: 28 // width
}

现有的实现评估一批 64 张图像，但不一定是并行的。但是，如果在 GPU 上运行，处理 64 个批处理将比 64 个单图像批处理快。

Answer 2

如果我正确理解您的问题，您输入n 图像，期望n 对(label, prob)，但只得到一个这样的对。

我相信这些修改应该对你有用：

1. Classifier::Predict 应该返回一个vector< vector<float> >，即每个输入图像的概率的向量。那是大小为n 的向量的大小为output_layer->channels() 的vector：

   std::vector< std::vecot<float> > 
   Classifier::Predict(const std::vector<cv::Mat> &input_channels, 
                       int num_images) {
     // same code here...
   
     /* changes here: Copy the output layer to a std::vector */
     Blob<float>* output_layer = net_->output_blobs()[0];
     std::vector< std::vector<float> > ret;
     for ( int i = 0 ; i < num_images ; i++ ) {
         const float* begin = output_layer->cpu_data() + i*output_layer->channels();
         const float* end = begin + output_layer->channels();
         ret.push_back( std::vector<float>(begin, end) );
     }
     return ret;
   }
   

2. 在Classifier::Classify 中，您需要独立处理每个vector<float> 到Argmax：

    std::vector< std::pair<int,float> > 
    Classifier::Classify(const std::vector<cv::Mat> &input_channels) {
   
      std::vector< std::vector<float> > output = Predict(input_channels);
   
      std::vector< std::pair<int,float> > predictions;
      for ( int i = 0 ; i < output.size(); i++ ) {
          std::vector<int> maxN = Argmax(output[i], 1);
          int idx = maxN[0];
          predictions.push_back(std::make_pair(labels_[idx], output[idx]));
      }
      return predictions;
    }