【深度学习】【caffe实用工具2】笔记24 Windows下【Caffe实用工具】之【计算图像均值】compute_image_mean的用法

/*********************************************************************************************************************************
文件说明:
       【1】Windows下【Caffe使用工具】之【计算图像的均值】compute_image_mean的用法
	   【2】在【数据读取层】的Transform阶段，需要进行减均值操作
	   【3】均值文件一般需要用原始数据计算得到，在此块，将介绍caffe实用工具中的这一源代码的使用
使用说明:
       【用法1】从LEVELDB类型的数据库中求解均值文件:
	           【1】修改代码：
			        DEFINE_string(backend, "lmdb","The backend {leveldb, lmdb} containing the images");
					将代码:
					DEFINE_string(backend, "lmdb","The backend {leveldb, lmdb} containing the images");
					改为:
					DEFINE_string(backend, "leveldb","The backend {leveldb, lmdb} containing the images");
				【2】添加代码:
					argc = 3;
					argv[1] = "E://caffeInstall2013CUDAVersion//caffe-master//examples//cifar10//cifar10_train_leveldb";
					argv[2] = "E://caffeInstall2013CUDAVersion//caffe-master//examples//cifar10//cifar10_mean.binaryproto";
		【用法2】从LMDB类型的数据库中求解均值文件:
		         【1】确保代码:
				     DEFINE_string(backend, "lmdb","The backend {leveldb, lmdb} containing the images");是这样的
                 【2】添加代码:
					 argc = 3;
					 argv[1] = "E://caffeInstall2013CUDAVersion//caffe-master//examples//cifar10//cifar10_train_lmdb";
					 argv[2] = "E://caffeInstall2013CUDAVersion//caffe-master//examples//cifar10//cifar10_mean.binaryproto";
		【用法3】*bat文件的使用，请参考下面的博客:
		          http://www.cnblogs.com/LiuSY/p/5765810.html
开发环境:
        windows+cuda7.5+cuDnnV5+opencv+caffe1+vs2013
时间地点:
        陕西师范大学 文津楼 2017.8.9
作    者:
        九 月
**********************************************************************************************************************************/
#include <stdint.h>
#include <algorithm>
#include <string>
#include <utility>
#include <vector>

#include "boost/scoped_ptr.hpp"
#include "gflags/gflags.h"
#include "glog/logging.h"

#include "caffe/proto/caffe.pb.h"
#include "caffe/util/db.hpp"
#include "caffe/util/io.hpp"

using namespace caffe;  

using std::max;
using std::pair;
using boost::scoped_ptr;

DEFINE_string(backend, "leveldb","The backend {leveldb, lmdb} containing the images");

int main(int argc, char** argv) 
{
  ::google::InitGoogleLogging(argv[0]);

#ifdef USE_OPENCV
#ifndef GFLAGS_GFLAGS_H_
  namespace gflags = google;
#endif

  gflags::SetUsageMessage("Compute the mean_image of a set of images given by"
					      " a leveldb/lmdb\n"
					      " Usage:\n"
					      " compute_image_mean [FLAGS] INPUT_DB [OUTPUT_FILE]\n");
  argc = 3;
  argv[1] = "E://caffeInstall2013CUDAVersion//caffe-master//examples//cifar10//cifar10_train_leveldb";
  argv[2] = "E://caffeInstall2013CUDAVersion//caffe-master//examples//cifar10//cifar10_mean.binaryproto";

  scoped_ptr<db::DB> db(db::GetDB(FLAGS_backend));
  db->Open(argv[1], db::READ);
  scoped_ptr<db::Cursor> cursor(db->NewCursor());

  BlobProto sum_blob;
  int count = 0;
  // load first datum
  Datum datum;
  datum.ParseFromString(cursor->value());

  if (DecodeDatumNative(&datum)) 
  {
    LOG(INFO) << "Decoding Datum";
  }

  sum_blob.set_num(1);
  sum_blob.set_channels(datum.channels());
  sum_blob.set_height(datum.height());
  sum_blob.set_width(datum.width());


  const int data_size = datum.channels() * datum.height() * datum.width();
  int size_in_datum    = std::max<int>(datum.data().size(),datum.float_data_size());


  for (int i = 0; i < size_in_datum; ++i) 
  {
    sum_blob.add_data(0.);
  }

  LOG(INFO) << "Starting Iteration";
  while (cursor->valid()) 
  {
    Datum datum;
    datum.ParseFromString(cursor->value());
    DecodeDatumNative(&datum);

    const std::string& data = datum.data();
    size_in_datum = std::max<int>(datum.data().size(),datum.float_data_size());

    CHECK_EQ(size_in_datum, data_size) << "Incorrect data field size " <<size_in_datum;

    if (data.size() != 0) 
	{

      CHECK_EQ(data.size(), size_in_datum);

      for (int i = 0; i < size_in_datum; ++i) 
	  {
        sum_blob.set_data(i, sum_blob.data(i) + (uint8_t)data[i]);
      }
    } 
	else 
	{
      CHECK_EQ(datum.float_data_size(), size_in_datum);
      for (int i = 0; i < size_in_datum; ++i) 
	  {
        sum_blob.set_data(i, sum_blob.data(i) + static_cast<float>(datum.float_data(i)));
      }
    }
    ++count;
    if (count % 10000 == 0) 
	{
      LOG(INFO) << "Processed " << count << " files.";
    }
    cursor->Next();
  }

  if (count % 10000 != 0) 
  {
    LOG(INFO) << "Processed " << count << " files.";
  }
  for (int i = 0; i < sum_blob.data_size(); ++i) 
  {
    sum_blob.set_data(i, sum_blob.data(i) / count);
  }
  // Write to disk
  if (argc == 3) 
  {
    LOG(INFO) << "Write to " << argv[2];
    WriteProtoToBinaryFile(sum_blob, argv[2]);
  }
  const int channels = sum_blob.channels();
  const int dim      = sum_blob.height() * sum_blob.width();

  std::vector<float> mean_values(channels, 0.0);

  LOG(INFO) << "Number of channels: " << channels;

  for (int c = 0; c < channels; ++c) 
  {
    for (int i = 0; i < dim; ++i) 
	{
      mean_values[c] += sum_blob.data(dim * c + i);
    }
    LOG(INFO) << "mean_value channel [" << c << "]:" << mean_values[c] / dim;
  }
  std::system("pause");
#else
  LOG(FATAL) << "This tool requires OpenCV; compile with USE_OPENCV.";
#endif  // USE_OPENCV
  return 0;
}

生成的均值文件如下所示:

1.首先我们使用lmdb数据格式（怎样得到lmdb数据格式，看我的另一篇）求得均值：

新建ComputeImageMean.bat，里面输入：

D:/deeptools/caffe-windows-master/bin/compute_image_mean.exe D:/deeptools/caffe-windows-master/examples/mymnist/train_lmdb D:/deeptools/caffe-windows-master/examples/mymnist/mean.binaryproto 
pause 

结果：

 

2.现在我们使用leveldb格式（怎么得到leveldb格式，看我的另一篇）来求得均值

新建ComputeImageMean-leveldb.bat，里面输入：

D:/deeptools/caffe-windows-master/bin/compute_image_mean.exe D:/deeptools/caffe-windows-master/examples/mymnist/trainbackend_leveldb D:/deeptools/caffe-windows-master/examples/mymnist/mean-leveldb.binaryproto --backend=leveldb 
pause 

我们可以看到 只是最后加了一个 --backend=leveldb！！！！！！！！

结果：