2022-02-26 update:
说学习笔记听起来像在分析代码。。。但是实际上什么都没干,还是写"使用笔记"好了
大三的时候看过一点levelDB的源码,不过没有怎么用过。
最近有个需求是存人脸的feature到硬盘,似乎使用levelDB比较合适,因此来学习一下使用。
先放参考资料。
关于levelDB的语法,看这里就好了。
以及由于caffe中使用了levelDB,因此也可以参考下caffe源码。不过caffe中对levelDB的使用是又封装了一层。
具体可以参考:
1#ifdef USE_LEVELDB
2#ifndef CAFFE_UTIL_DB_LEVELDB_HPP
3#define CAFFE_UTIL_DB_LEVELDB_HPP
4
5#include <string>
6
7#include "leveldb/db.h"
8#include "leveldb/write_batch.h"
9
10#include "caffe/util/db.hpp"
11
12namespace caffe { namespace db {
13
14class LevelDBCursor : public Cursor {
15 public:
16 explicit LevelDBCursor(leveldb::Iterator* iter)
17 : iter_(iter) {
18 SeekToFirst();
19 CHECK(iter_->status().ok()) << iter_->status().ToString();
20 }
21 ~LevelDBCursor() { delete iter_; }
22 virtual void SeekToFirst() { iter_->SeekToFirst(); }
23 virtual void Next() { iter_->Next(); }
24 virtual string key() { return iter_->key().ToString(); }
25 virtual string value() { return iter_->value().ToString(); }
26 virtual bool valid() { return iter_->Valid(); }
27
28 private:
29 leveldb::Iterator* iter_;
30};
31
32class LevelDBTransaction : public Transaction {
33 public:
34 explicit LevelDBTransaction(leveldb::DB* db) : db_(db) { CHECK_NOTNULL(db_); }
35 virtual void Put(const string& key, const string& value) {
36 batch_.Put(key, value);
37 }
38 virtual void Commit() {
39 leveldb::Status status = db_->Write(leveldb::WriteOptions(), &batch_);
40 CHECK(status.ok()) << "Failed to write batch to leveldb "
41 << std::endl << status.ToString();
42 }
43
44 private:
45 leveldb::DB* db_;
46 leveldb::WriteBatch batch_;
47
48 DISABLE_COPY_AND_ASSIGN(LevelDBTransaction);
49};
50
51class LevelDB : public DB {
52 public:
53 LevelDB() : db_(NULL) { }
54 virtual ~LevelDB() { Close(); }
55 virtual void Open(const string& source, Mode mode);
56 virtual void Close() {
57 if (db_ != NULL) {
58 delete db_;
59 db_ = NULL;
60 }
61 }
62 virtual LevelDBCursor* NewCursor() {
63 return new LevelDBCursor(db_->NewIterator(leveldb::ReadOptions()));
64 }
65 virtual LevelDBTransaction* NewTransaction() {
66 return new LevelDBTransaction(db_);
67 }
68
69 private:
70 leveldb::DB* db_;
71};
72
73
74} // namespace db
75} // namespace caffe
76
77#endif // CAFFE_UTIL_DB_LEVELDB_HPP
78#endif // USE_LEVELDB
79
80
81
82
83
84
85#ifndef CAFFE_UTIL_DB_HPP
86#define CAFFE_UTIL_DB_HPP
87
88#include <string>
89
90#include "caffe/common.hpp"
91#include "caffe/proto/caffe.pb.h"
92
93namespace caffe { namespace db {
94
95enum Mode { READ, WRITE, NEW };
96
97class Cursor {
98 public:
99 Cursor() { }
100 virtual ~Cursor() { }
101 virtual void SeekToFirst() = 0;
102 virtual void Next() = 0;
103 virtual string key() = 0;
104 virtual string value() = 0;
105 virtual bool valid() = 0;
106
107 DISABLE_COPY_AND_ASSIGN(Cursor);
108};
109
110class Transaction {
111 public:
112 Transaction() { }
113 virtual ~Transaction() { }
114 virtual void Put(const string& key, const string& value) = 0;
115 virtual void Commit() = 0;
116
117 DISABLE_COPY_AND_ASSIGN(Transaction);
118};
119
120class DB {
121 public:
122 DB() { }
123 virtual ~DB() { }
124 virtual void Open(const string& source, Mode mode) = 0;
125 virtual void Close() = 0;
126 virtual Cursor* NewCursor() = 0;
127 virtual Transaction* NewTransaction() = 0;
128
129 DISABLE_COPY_AND_ASSIGN(DB);
130};
131
132DB* GetDB(DataParameter::DB backend);
133DB* GetDB(const string& backend);
134
135} // namespace db
136} // namespace caffe
137
138#endif // CAFFE_UTIL_DB_HPP
139
140
141
142
143
144
145#ifdef USE_LEVELDB
146#include "caffe/util/db_leveldb.hpp"
147
148#include <string>
149
150namespace caffe { namespace db {
151
152void LevelDB::Open(const string& source, Mode mode) {
153 leveldb::Options options;
154 options.block_size = 65536;
155 options.write_buffer_size = 268435456;
156 options.max_open_files = 100;
157 options.error_if_exists = mode == NEW;
158 options.create_if_missing = mode != READ;
159 leveldb::Status status = leveldb::DB::Open(options, source, &db_);
160 CHECK(status.ok()) << "Failed to open leveldb " << source
161 << std::endl << status.ToString();
162 LOG(INFO) << "Opened leveldb " << source;
163}
164
165} // namespace db
166} // namespace caffe
167#endif // USE_LEVELDB
168
169
170
171
172
173
174#include "caffe/util/db.hpp"
175#include "caffe/util/db_leveldb.hpp"
176#include "caffe/util/db_lmdb.hpp"
177
178#include <string>
179
180namespace caffe { namespace db {
181
182DB* GetDB(DataParameter::DB backend) {
183 switch (backend) {
184#ifdef USE_LEVELDB
185 case DataParameter_DB_LEVELDB:
186 return new LevelDB();
187#endif // USE_LEVELDB
188#ifdef USE_LMDB
189 case DataParameter_DB_LMDB:
190 return new LMDB();
191#endif // USE_LMDB
192 default:
193 LOG(FATAL) << "Unknown database backend";
194 return NULL;
195 }
196}
197
198DB* GetDB(const string& backend) {
199#ifdef USE_LEVELDB
200 if (backend == "leveldb") {
201 return new LevelDB();
202 }
203#endif // USE_LEVELDB
204#ifdef USE_LMDB
205 if (backend == "lmdb") {
206 return new LMDB();
207 }
208#endif // USE_LMDB
209 LOG(FATAL) << "Unknown database backend";
210 return NULL;
211}
212
213} // namespace db
214} // namespace caffe
215
216
217
218
219
220// This program converts a set of images to a lmdb/leveldb by storing them
221// as Datum proto buffers.
222// Usage:
223// convert_imageset [FLAGS] ROOTFOLDER/ LISTFILE DB_NAME
224//
225// where ROOTFOLDER is the root folder that holds all the images, and LISTFILE
226// should be a list of files as well as their labels, in the format as
227// subfolder1/file1.JPEG 7
228// ....
229
230#include <algorithm>
231#include <fstream> // NOLINT(readability/streams)
232#include <string>
233#include <utility>
234#include <vector>
235
236#include "boost/scoped_ptr.hpp"
237#include "gflags/gflags.h"
238#include "glog/logging.h"
239
240#include "caffe/proto/caffe.pb.h"
241#include "caffe/util/db.hpp"
242#include "caffe/util/format.hpp"
243#include "caffe/util/io.hpp"
244#include "caffe/util/rng.hpp"
245
246using namespace caffe; // NOLINT(build/namespaces)
247using std::pair;
248using boost::scoped_ptr;
249
250DEFINE_bool(gray, false,
251 "When this option is on, treat images as grayscale ones");
252DEFINE_bool(shuffle, false,
253 "Randomly shuffle the order of images and their labels");
254DEFINE_string(backend, "lmdb",
255 "The backend {lmdb, leveldb} for storing the result");
256DEFINE_int32(resize_width, 0, "Width images are resized to");
257DEFINE_int32(resize_height, 0, "Height images are resized to");
258DEFINE_bool(check_size, false,
259 "When this option is on, check that all the datum have the same size");
260DEFINE_bool(encoded, false,
261 "When this option is on, the encoded image will be save in datum");
262DEFINE_string(encode_type, "",
263 "Optional: What type should we encode the image as ('png','jpg',...).");
264
265int main(int argc, char** argv) {
266#ifdef USE_OPENCV
267 ::google::InitGoogleLogging(argv[0]);
268 // Print output to stderr (while still logging)
269 FLAGS_alsologtostderr = 1;
270
271#ifndef GFLAGS_GFLAGS_H_
272 namespace gflags = google;
273#endif
274
275 gflags::SetUsageMessage("Convert a set of images to the leveldb/lmdb\n"
276 "format used as input for Caffe.\n"
277 "Usage:\n"
278 " convert_imageset [FLAGS] ROOTFOLDER/ LISTFILE DB_NAME\n"
279 "The ImageNet dataset for the training demo is at\n"
280 " http://www.image-net.org/download-images\n");
281 gflags::ParseCommandLineFlags(&argc, &argv, true);
282
283 if (argc < 4) {
284 gflags::ShowUsageWithFlagsRestrict(argv[0], "tools/convert_imageset");
285 return 1;
286 }
287
288 const bool is_color = !FLAGS_gray;
289 const bool check_size = FLAGS_check_size;
290 const bool encoded = FLAGS_encoded;
291 const string encode_type = FLAGS_encode_type;
292
293 std::ifstream infile(argv[2]);
294 std::vector<std::pair<std::string, int> > lines;
295 std::string line;
296 size_t pos;
297 int label;
298 while (std::getline(infile, line)) {
299 pos = line.find_last_of(' ');
300 label = atoi(line.substr(pos + 1).c_str());
301 lines.push_back(std::make_pair(line.substr(0, pos), label));
302 }
303 if (FLAGS_shuffle) {
304 // randomly shuffle data
305 LOG(INFO) << "Shuffling data";
306 shuffle(lines.begin(), lines.end());
307 }
308 LOG(INFO) << "A total of " << lines.size() << " images.";
309
310 if (encode_type.size() && !encoded)
311 LOG(INFO) << "encode_type specified, assuming encoded=true.";
312
313 int resize_height = std::max<int>(0, FLAGS_resize_height);
314 int resize_width = std::max<int>(0, FLAGS_resize_width);
315
316 // Create new DB
317 scoped_ptr<db::DB> db(db::GetDB(FLAGS_backend));
318 db->Open(argv[3], db::NEW);
319 scoped_ptr<db::Transaction> txn(db->NewTransaction());
320
321 // Storing to db
322 std::string root_folder(argv[1]);
323 Datum datum;
324 int count = 0;
325 int data_size = 0;
326 bool data_size_initialized = false;
327
328 for (int line_id = 0; line_id < lines.size(); ++line_id) {
329 bool status;
330 std::string enc = encode_type;
331 if (encoded && !enc.size()) {
332 // Guess the encoding type from the file name
333 string fn = lines[line_id].first;
334 size_t p = fn.rfind('.');
335 if ( p == fn.npos )
336 LOG(WARNING) << "Failed to guess the encoding of '" << fn << "'";
337 enc = fn.substr(p+1);
338 std::transform(enc.begin(), enc.end(), enc.begin(), ::tolower);
339 }
340 status = ReadImageToDatum(root_folder + lines[line_id].first,
341 lines[line_id].second, resize_height, resize_width, is_color,
342 enc, &datum);
343 if (status == false) continue;
344 if (check_size) {
345 if (!data_size_initialized) {
346 data_size = datum.channels() * datum.height() * datum.width();
347 data_size_initialized = true;
348 } else {
349 const std::string& data = datum.data();
350 CHECK_EQ(data.size(), data_size) << "Incorrect data field size "
351 << data.size();
352 }
353 }
354 // sequential
355 string key_str = caffe::format_int(line_id, 8) + "_" + lines[line_id].first;
356
357 // Put in db
358 string out;
359 CHECK(datum.SerializeToString(&out));
360 txn->Put(key_str, out);
361
362 if (++count % 1000 == 0) {
363 // Commit db
364 txn->Commit();
365 txn.reset(db->NewTransaction());
366 LOG(INFO) << "Processed " << count << " files.";
367 }
368 }
369 // write the last batch
370 if (count % 1000 != 0) {
371 txn->Commit();
372 LOG(INFO) << "Processed " << count << " files.";
373 }
374#else
375 LOG(FATAL) << "This tool requires OpenCV; compile with USE_OPENCV.";
376#endif // USE_OPENCV
377 return 0;
378}几个文件。。。感觉比看文档更有实际意义orz
levelDB简介#
Leveldb是google开源的一个高效率的K/V数据库.有如下特点:
1. 首先,LevelDb是一个持久化存储的KV系统,和Redis这种内存型的KV系统不同,LevelDb不会像Redis一样狂吃内存,而是将大部分数据存储到磁盘上。
2. 其次,LevleDb在存储数据时,是根据记录的key值有序存储的,就是说相邻的key值在存储文件中是依次顺序存储的,而应用可以自定义key大小比较函数,LevleDb会按照用户定义的比较函数依序存储这些记录。
3. 再次,像大多数KV系统一样,LevelDb的操作接口很简单,基本操作包括写记录,读记录以及删除记录。也支持针对多条操作的原子批量操作。
4. 另外,LevelDb支持数据快照(snapshot)功能,使得读取操作不受写操作影响,可以在读操作过程中始终看到一致的数据。
5. 除此外,LevelDb还支持数据压缩等操作,这对于减小存储空间以及增快IO效率都有直接的帮助。
6. LevelDb性能非常突出,官方网站报道其随机写性能达到40万条记录每秒,而随机读性能达到6万条记录每秒。总体来说,LevelDb的写操作要大大快于读操作,而顺序读写操作则大大快于随机读写操作。
LevelDB的安装#
以ubuntu14.04为例,但实际上除了路径可能不同,其他部分是系统无关的。
然后记得切换到指定tag
可以使用git tag命令得到,然后用git checkout命令切换,我这里使用的是1.20版本
之后直接执行make
之后将头文件拷贝到系统路径下:
sudo cp -r include/leveldb /usr/include
编译之后分别会得到out-shared和out-static两个文件夹,分别是动态库和静态库
我们进入out-shared文件夹,讲libleveldb.so*的三个文件(有两个是链接)拷贝到/usr/lib下
然后用sudo ldconfig 命令将动态库加到缓存中。
我们用如下代码测试一下:
1#include <iostream>
2#include <cassert>
3#include <cstdlib>
4#include <string>
5#include <leveldb/db.h>
6using namespace std;
7int main(void)
8{
9 leveldb::DB *db;
10 leveldb::Options options;
11 options.create_if_missing=true;
12 leveldb::Status status = leveldb::DB::Open(options,"./testdb",&db);
13 assert(status.ok());
14 std::string key1="people";
15 std::string value1="jason";
16 std::string value;
17 leveldb::Status s=db->Put(leveldb::WriteOptions(),key1,value1);
18 if(s.ok())
19 s=db->Get(leveldb::ReadOptions(),"people",&value);
20 if(s.ok())
21 cout<<value<<endl;
22 else
23 cout<<s.ToString()<<endl;
24 delete db;
25 return 0;
26}编译选项为:
g++ mytest.cc -o mytest -lpthread -lleveldb
如果运行得到jason,表示安装成功。
LevelDB的使用#
一些基本操作可以参考github文档
不过发现levelDB的接口似乎只支持key和value都是string类型。。
然而对于人脸提取feature,实际上需要的是string映射到float**
,偶然发现caffe中使用了levelDB,
发现它的做法是使用protobuf将数据序列化,然后再存储。
注意事项#
记录一些踩坑的经历..
如果有100条数据,想要每10条存一个数据库,那么每10条执行一次DB::Open就行了…不然会报错在put那里,导致core dumped