/*********************************************************************************************************************************
文件说明:
【1】This program converts a set of images to a lmdb/leveldb by storing them as Datum proto buffers.
【2】这个程序用于将图像数据转化为DB(lmdb/leveldb)数据库文件
【3】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
用 法:
【注意1】*.bat文件的使用方法:
convert_imageset [FLAGS] ROOTFOLDER/ LISTFILE DB_NAME
【1】convert_imageset:convert_imageset.exe文件所在的路径
【2】[FLAGS]:可选参数的配置
【3】ROOTFOLDER/:图片集合所在的文件夹所在的路径,如下所示:
argv[1] = "E://caffeInstall2013//caffe-master//data//myself//train//";
【4】LISTFILE:图片文件列表文件所在的路径,如下所示:
argv[2] = "E://caffeInstall2013//caffe-master//data//myself//train.txt";
【5】DB_NAME:生成的DB文件存放的路径以及生成DB数据库的数据库名字
【注意2】直接在代码中进行配置,运行:
【1】首先根据自己要转换图片数据集合的图片规格等,对可选参数进行配置
【2】添加如下的代码:
argv[1] = "E://caffeInstall2013//caffe-master//data//myself//train//";
argv[2] = "E://caffeInstall2013//caffe-master//data//myself//train.txt";
argv[3] = "E://caffeInstall2013//caffe-master//examples//myself//myself_train_lmdb";
【注意3】:*.bat文件形式的具体使用方法,可以参考下面的博客:
http://www.cnblogs.com/LiuSY/p/5761781.html
操作步骤:
【1】首先,在目录E:\caffeInstall2013\caffe-master\data下建立自己的图像数据集合文件,例如train,val
【2】其次,再建立这些图像文件的文件列表train.txt val.txt
【3】然后,配置程序(就是本程序)
【4】运行程序,生成DB数据库文件
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 <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;
/**********************************************************************************************************************
模块说明:
可选参数的定义
参数说明:
【1】-gray: 是否以灰度图的方式打开图片。程序调用opencv库中的imread()函数来打开图片,默认为false
【2】-shuffle: 是否随机打乱图片顺序。默认为false
【3】-backend:需要转换成的db文件格式,可选为leveldb或lmdb,默认为lmdb
【4】-resize_width/resize_height: 改变图片的大小。在运行中,要求所有图片的尺寸一致,因此需要改变图片大小。
程序调用opencv库的resize()函数来对图片放大缩小,默认为0,不改变
【5】-check_size: 检查所有的数据是否有相同的尺寸。默认为false,不检查
【6】-encoded: 是否将原图片编码放入最终的数据中,默认为false
【7】-encode_type: 与前一个参数对应,将图片编码为哪一个格式:‘png','jpg'......
***********************************************************************************************************************/
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, 256, "Width images are resized to");
DEFINE_int32(resize_height, 256, "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");
argv[1] = "E://caffeInstall2013//caffe-master//data//myself//train//";
argv[2] = "E://caffeInstall2013//caffe-master//data//myself//train.txt";
argv[3] = "E://caffeInstall2013//caffe-master//examples//myself//myself_train_lmdb";
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.";
}
std::system("pause");
#else
LOG(FATAL) << "This tool requires OpenCV; compile with USE_OPENCV.";
#endif // USE_OPENCV
return 0;
}
convert.bat的格式为
convert_imageset.exe的位置+空格+FLAGS+空格+图片所在的位置+空格+你生成的list的位置+空格+将要生成的db格式要保存的位置
建议都使用绝对位置!!!
例子:
D:/deeptools/caffe-windows-master/bin/convert_imageset.exe --shuffle --resize_height=256 --resize_width=256 D:/deeptools/caffe-windows-master/data/re/ D:/deeptools/caffe-windows-master/examples/myfile/train.txt D:/deeptools/caffe-windows-master/examples/myfile/train_db pause
其中FLAGS可以选择为:
(1)--shuffle 是否随机打乱图片顺序 【默认为false】
D:/deeptools/caffe-windows-master/bin/convert_imageset.exe --shuffle D:/deeptools/caffe-windows-master/data/mnist/train-images/ D:/deeptools/caffe-windows-master/examples/mymnist/train.txt D:/deeptools/caffe-windows-master/examples/mymnist/train_lmdb
pause
为什么要随机打乱图片顺序?
待答。。。
(2)--gray 是否以灰度图片的方式打开【默认为false】
D:/deeptools/caffe-windows-master/bin/convert_imageset.exe --gray D:/deeptools/caffe-windows-master/data/mnist/train-images/ D:/deeptools/caffe-windows-master/examples/mymnist/train.txt D:/deeptools/caffe-windows-master/examples/mymnist/traingray_lmdb pause
(3)--resize_width
--resize_height 改变图片大小(缩放)【默认为原图】
(4)--backend 需要转换成什么格式的db,可选为leveldb与lmdb格式【默认为lmdb】
D:/deeptools/caffe-windows-master/bin/convert_imageset.exe --backend=leveldb D:/deeptools/caffe-windows-master/data/mnist/train-images/ D:/deeptools/caffe-windows-master/examples/mymnist/train.txt D:/deeptools/caffe-windows-master/examples/mymnist/trainbackend_leveldb
pause
结果:
现在我们认真解读一下这个leveldb格式:
http://www.2cto.com/kf/201607/527860.html
待续。。。不知道里面的纠结是什么东西
(5)--check_size 检查所有的数据是否为同一个size【默认为false,不检查】
(6)--encoded 是否将原图编码放入最终的数据中【默认为false】
(7)--encode_type 与前边呼应,将图片改为哪种格式【png,jpg。。】
貌似这个得需要opencv。。我没有安装opencv出错如下