这是一个caffe提供的函数,能将数据转换为caffe可用的,lmdb/leveldb格式的数据。
具体调用参考我的另一篇博文:http://blog.csdn.net/u011070171/article/details/51548823
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
//
// 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
// ....
//这份代码是caffe提供的,在caffe里的tools文件目录里,用于将图像数据转换为lmdb或者leveldb格式。
//使用方法: 在shell 脚本里写入以下代码
// convert_imageset [参数设置] [图像存放路径] [图像的LISTFILE文件] [转换后数据存储位置]
//例子:
// $TOOLS/convert_imageset \
// --resize_height=$RESIZE_HEIGHT \
// --resize_width=$RESIZE_WIDTH \
// --shuffle \
// $VAL_DATA_ROOT \
// $IMAGE_LIST_ROOT/val_2.list \
// $ROOT_LMDB/val
#include <algorithm> //输出数组的内容,对数组进行升幂排序,反转数组内容等操作
#include <fstream> // NOLINT(readability/streams)
#include <string>
#include <utility> //定义了一个pair类型,pair类型用于存储一对数据
#include <vector>
#include "boost/scoped_ptr.hpp" //智能指针头文件
#include "gflags/gflags.h"
#include "glog/logging.h" //glog头文件,google的开源日志系统
#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;
//参数选择
DEFINE_bool(gray, false, //将图像作为灰度图处理,处理后为单通道的
"When this option is on, treat images as grayscale ones");
DEFINE_bool(shuffle, false, //随机乱序处理图像及其标注
"Randomly shuffle the order of images and their labels");
DEFINE_string(backend, "lmdb", //数据存储格式,默认lmdb
"The backend {lmdb, leveldb} for storing the result");
DEFINE_int32(resize_width, 0, "Width images are resized to"); //图像宽度重置
DEFINE_int32(resize_height, 0, "Height images are resized to");//图像高度重置
DEFINE_bool(check_size, false, //检查所有数据大小一致
"When this option is on, check that all the datum have the same size");
DEFINE_bool(encoded, false, //是否将处理的图像保存
"When this option is on, the encoded image will be save in datum");
DEFINE_string(encode_type, "", //处理得到的图像保存的格式
"Optional: What type should we encode the image as ('png','jpg',...).");
int main(int argc, char** argv) {
#ifdef USE_OPENCV
::google::InitGoogleLogging(argv[0]); //初始化日志
// 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" //设置使用信息
"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); //调用解析命令行函数
//argc,传给main()的命令行参数个数
//argv:字符串数组
//argc,argv就是main函数的入口参数,因为这个函数会改变他们的值,所以都是以指针传入
//第三个参数被称为remove_flags,若为true,ParseCommandLineFlags会从argv中移除标识和它们的参数,相应减少argc的值。然后 argv 只保留命令行参数;若为false,ParseCommandLineFlags会保留argc不变,但将会重新调整它们的顺序,使得标识在前面
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;
//argv第二个参数为图像的LISTFILE
std::ifstream infile(argv[2]);
std::vector<std::pair<std::string, int> > lines;
std::string filename;
int label;
//存储文件名和标注
while (infile >> filename >> label) {
lines.push_back(std::make_pair(filename, label));
}
//乱序存储
if (FLAGS_shuffle) {
// randomly shuffle data
LOG(INFO) << "Shuffling data"; //打印,类似于C++的stream
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.";
//设置图像的长度,宽度
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); //argv第三个参数为db存储位置
scoped_ptr<db::Transaction> txn(db->NewTransaction());
// Storing to db
std::string root_folder(argv[1]); //argv第一个参数为图像路径
Datum datum;
int count = 0;
int data_size = 0;
bool data_size_initialized = false;
//将LISTFILE里的记录,逐条转换为lmdb/leveldb格式
for (int line_id = 0; line_id < lines.size(); ++line_id) {
bool status;
std::string enc = encode_type;
//保存图像处理
if (encoded && !enc.size()) {
// Guess the encoding type from the file name
string fn = lines[line_id].first; //list 里的第一个参数,即为文件的路径名
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;
//检查图像尺寸
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;
}