caffe:把图片转为lmdb或者leveldb文件（四）

废话少说，让我们开始深度学习的第一步：制作自己的数据

1.了解文件存放

在caffe中，原作者给我们提供了一个convert_imageset.cpp.该文件放在caffe/tools/文件下，当我们把它编译了之后就会在build/tools/下面生成可执行文件。

2.源代码convert_imageset.cpp

// This program converts a set of images to a lmdb/leveldb by storing them
// as Datum proto buffers.
// Usage:
//   convert_imageset [FLAGS] ROOTFOLDER/ LISTFILE DB_NAME
//   FLAGS:图片参数数组。在tensorflow中也有类似参数组
//      --gray：是否依灰度的方式打开图片，默认为false，程序调用的是opencv里面的函数imread（）来打开图片。
//      --shuffle：是否要打乱图片的顺序，默认为flase
//      --backend：转为什么样格式的数据，默认为lmdb。可选leveldb
//      --resize_width or resize_height:改变图片的大小（要求所有的图片大小一样），调用opencv
//      中的resize()函数对图像放大或者缩小，默认为0，不改变
//      --check_size:检查图像的大小是否一样，默认为false
//      --encoded：是否将图片编码放入到最终的数据中，default：false
//      --encode_type：与前一个参数对应，将图片编码为哪一种图像
//   ROOTFLODER/ 图片放的绝对路径，/home/inc/caffe/data/..
//   LISTFILE：图片文件列表，经常使用txt文件，好处理，囧.. 一行一个图片
//   DB_NAME:生成的db文件要放的目录
//   说明：文件列表需要自己建立，保存为一个txt文件就ok
// where ROOTFOLDER is the root folder that holds all the images, and LISTFILE
// should be a list of files as well as their labels, in the format as
//   subfolder1/file1.JPEG 7
//   ....

#include <algorithm>
#include <fstream>  // NOLINT(readability/streams)
#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/format.hpp"
#include "caffe/util/io.hpp"
#include "caffe/util/rng.hpp"

using namespace caffe;  // NOLINT(build/namespaces)
using std::pair;
using boost::scoped_ptr;

DEFINE_bool(gray, false,
    "When this option is on, treat images as grayscale ones");
DEFINE_bool(shuffle, false,
    "Randomly shuffle the order of images and their labels");
DEFINE_string(backend, "lmdb",
        "The backend {lmdb, leveldb} for storing the result");
DEFINE_int32(resize_width, 0, "Width images are resized to");
DEFINE_int32(resize_height, 0, "Height images are resized to");
DEFINE_bool(check_size, false,
    "When this option is on, check that all the datum have the same size");
DEFINE_bool(encoded, false,
    "When this option is on, the encoded image will be save in datum");
DEFINE_string(encode_type, "",
    "Optional: What type should we encode the image as ('png','jpg',...).");

int main(int argc, char** argv) {
#ifdef USE_OPENCV
  ::google::InitGoogleLogging(argv[0]);
  // Print output to stderr (while still logging)
  FLAGS_alsologtostderr = 1;

#ifndef GFLAGS_GFLAGS_H_
  namespace gflags = google;
#endif

  gflags::SetUsageMessage("Convert a set of images to the leveldb/lmdb\n"
        "format used as input for Caffe.\n"
        "Usage:\n"
        "    convert_imageset [FLAGS] ROOTFOLDER/ LISTFILE DB_NAME\n"
        "The ImageNet dataset for the training demo is at\n"
        "    http://www.image-net.org/download-images\n");
  gflags::ParseCommandLineFlags(&argc, &argv, true);

  if (argc < 4) {
    gflags::ShowUsageWithFlagsRestrict(argv[0], "tools/convert_imageset");
    return 1;
  }

  const bool is_color = !FLAGS_gray;
  const bool check_size = FLAGS_check_size;
  const bool encoded = FLAGS_encoded;
  const string encode_type = FLAGS_encode_type;

  std::ifstream infile(argv[2]);
  std::vector<std::pair<std::string, int> > lines;
  std::string line;
  size_t pos;
  int label;
  while (std::getline(infile, line)) {
    pos = line.find_last_of(' ');
    label = atoi(line.substr(pos + 1).c_str());
    lines.push_back(std::make_pair(line.substr(0, pos), label));
  }
  if (FLAGS_shuffle) {
    // randomly shuffle data
    LOG(INFO) << "Shuffling data";
    shuffle(lines.begin(), lines.end());
  }
  LOG(INFO) << "A total of " << lines.size() << " images.";

  if (encode_type.size() && !encoded)
    LOG(INFO) << "encode_type specified, assuming encoded=true.";

  int resize_height = std::max<int>(0, FLAGS_resize_height);
  int resize_width = std::max<int>(0, FLAGS_resize_width);

  // Create new DB
  scoped_ptr<db::DB> db(db::GetDB(FLAGS_backend));
  db->Open(argv[3], db::NEW);
  scoped_ptr<db::Transaction> txn(db->NewTransaction());

  // Storing to db
  std::string root_folder(argv[1]);
  Datum datum;
  int count = 0;
  int data_size = 0;
  bool data_size_initialized = false;

  for (int line_id = 0; line_id < lines.size(); ++line_id) {
    bool status;
    std::string enc = encode_type;
    if (encoded && !enc.size()) {
      // Guess the encoding type from the file name
      string fn = lines[line_id].first;
      size_t p = fn.rfind('.');
      if ( p == fn.npos )
        LOG(WARNING) << "Failed to guess the encoding of '" << fn << "'";
      enc = fn.substr(p);
      std::transform(enc.begin(), enc.end(), enc.begin(), ::tolower);
    }
    status = ReadImageToDatum(root_folder + lines[line_id].first,
        lines[line_id].second, resize_height, resize_width, is_color,
        enc, &datum);
    if (status == false) continue;
    if (check_size) {
      if (!data_size_initialized) {
        data_size = datum.channels() * datum.height() * datum.width();
        data_size_initialized = true;
      } else {
        const std::string& data = datum.data();
        CHECK_EQ(data.size(), data_size) << "Incorrect data field size "
            << data.size();
      }
    }
    // sequential
    string key_str = caffe::format_int(line_id, 8) + "_" + lines[line_id].first;

    // Put in db
    string out;
    CHECK(datum.SerializeToString(&out));
    txn->Put(key_str, out);

    if (++count % 1000 == 0) {
      // Commit db
      txn->Commit();
      txn.reset(db->NewTransaction());
      LOG(INFO) << "Processed " << count << " files.";
    }
  }
  // write the last batch
  if (count % 1000 != 0) {
    txn->Commit();
    LOG(INFO) << "Processed " << count << " files.";
  }
#else
  LOG(FATAL) << "This tool requires OpenCV; compile with USE_OPENCV.";
#endif  // USE_OPENCV
  return 0;
}

3.一个生成图片清单的脚本文件

在～/caffe/examples/images/下新建一个脚本文件，取名inc_filelist.sh

使用cat.jpg和另一张fish_bike.jpg表示两个类别。
# /usr/bin/env sh
DATA=examples/images
echo "Create inc_train.txt..."
rm -rf $DATA/inc_train.txt
find $DATA -name *cat.jpg | cut -d '/' -f3 | sed "s/$/ 1/">>$DATA/inc_train.txt
find $DATA -name *bike.jpg | cut -d '/' -f3 | sed "s/$/ 2/">>$DATA/tmp.txt
cat $DATA/tmp.txt>>$DATA/inc_train.txt
rm -rf $DATA/tmp.txt
echo "Done.."

执行前给文件加执行的
chmod u+x inc_filelist.sh   
解释如下：
DATA：是在当前目录下开始的文件目录
rm:linux 删除命令，在images/目录下如果有inc_train.txt 文件，就山删除
find:在images/目录下找name为cat.jpg的文件。
cut：截取路径。
sed: 在每行的最后面加上标注。将找到的*cat.jpg文件加入标注为1，找到的*bike.jpg文件加入标注为2
cat：将两个txt文件合并为一个文件。
结果截图：

 - *cat.jpg为什么用*?       
 - 这样可以对所有cat的图片进行编号。

4.写一个脚本生成lmdb文件

在images/下新建一个create_lmdb.sh文件，内容如下：

#!/usr/bin/env sh
DATA=examples/images
rm -rf $DATA/inc_train_lmdb
build/tools/convert_imageset --shuffle --resize_height=256 --resize_width=256 \
/home/inc/caffe/examples/images/ $DATA/inc_train.txt  $DATA/inc_train_lmdb

运行脚本，在images文件目录下生成lmdb文件。

待续。。。