【Caffe代碼解析】compute_image_mean

功能：
計算訓練數據庫的平均圖像。
因爲平均歸一化訓練圖像會對結果有提升，所以Caffe裏面，提供了一個可選項。

使用方法：
compute_image_mean [FLAGS] INPUT_DB [OUTPUT_FILE]\n”)
參數：INPUT_DB： 數據庫
參數（可選）：OUTPUT_FILE： 輸出文件名,不提供的話，不保存平均圖像blob

實現方法：

數據源：求平均圖像的方法是直接從數據庫（LevelDB或者LMDB）裏面直接讀取出來的，而不是直接用圖像數據庫裏面求出，意味着，必須先進行圖像到數據庫的轉換後，才能求平均圖像這一步。

接下來就是遍歷KV數據庫的每一個值while (cursor->valid()) 將每一個數據值轉換爲Datum，datum.ParseFromString(cursor->value());

接着將Datum階碼到sum_blob 中，sum_blob 是一個num=1，channels=圖像.channel,height=圖像.height ,width=圖像.width 的blob

累加：

sum_blob.set_data(i, sum_blob.data(i) + (uint8_t)data[i]);

最後求平均：

sum_blob.set_data(i, sum_blob.data(i) / count);

存在的問題：上述代碼只是先累加在處於數目求和，顯然，如果需要求平均的圖像的數目相當多的話，就有可能溢出（浮點溢出），

最後，如果要求簡單一點的話，也可以直接求每個通道的平均值。
源代碼：//2015.06.04版本

#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;  // NOLINT(build/namespaces)

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

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

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

#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");

  gflags::ParseCommandLineFlags(&argc, &argv, true);

  if (argc < 2 || argc > 3) {
    gflags::ShowUsageWithFlagsRestrict(argv[0], "tools/compute_image_mean");
    return 1;
  }

  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;
  }
  return 0;
}