ImageNet数据集和cifar,mnist数据集最大的不同,就是数据量特别大;单张图片尺寸大,训练样本个数多;面对如此大的数据集,在转换成lmdb文件时;使用了很多新的类型对象。
1,动态扩容的数组“vector”,动态地添加新元素
2,pair类型数据对,用于存储成对的对象,例如存储文件名和对应标签
3,利用OpenCV中的图像处理函数,来读取和处理大尺寸图像
一:程序开始
由于要向imageNet数据集中设置resize和是否乱序等参数,所以本文使用gflags命令行解析工具;在Create.sh文件中,调用convert_imageset.bin语句为:
-
"code" class="cpp">GLOG_logtostderr=1$TOOLS/convert_imageset \
- --resize_height=$RESIZE_HEIGHT \
- --resize_width=$RESIZE_WIDTH \
- --shuffle \
- $TRAIN_DATA_ROOT \ 图像数据集存放的根目录
- $DATA/train.txt \ 图像的ID和对应的分类标签数字
- $EXAMPLE/ilsvrc12_train_lmdb lmdb文件保存的路径
由于train.txt文件太大,电脑打不开,故打开val.txt一窥之;val.txt中的某个数据为:
65ILSVRC2012_val_00000002.JPEG ,65应该是对应的标签,后面的是图像的编号id。
二:数据转换流程图
三:convert_imageset.cpp函数分析
1引入必要的头文件和命名空间
- #include//输出数组的内容、对数组进行升幂排序、反转数组内容、复制数组内容等操作,
- #include // NOLINT(readability/streams)
- #include
- #include//utility头文件定义了一个pair类型,pair类型用于存储一对数据
- #include//会自动扩展容量的数组
- #include "boost/scoped_ptr.hpp"//智能指针头文件
- #include "gflags/gflags.h"
- #include "glog/logging.h"
- #include"caffe/proto/caffe.pb.h"
- #include "caffe/util/db.hpp" //引入包装好的lmdb操作函数
- #include "caffe/util/io.hpp" //引入opencv中的图像操作函数
- #include "caffe/util/rng.hpp"
头文件和convert_cifar_data.cpp的区别:
1,引入gflags命令行解析工具;
2,引入utility头文件,里面提供了数组洗牌等操作
- using namespace caffe;
- using std::pair;
- using boost::scoped_ptr;
命名空间区别:
1,引入全部caffe命名空间
2,引入pair对命名空间
2 gflags宏定义参数
//通过gflags宏定义一些程序的参数变量
- DEFINE_bool(gray, false,"When thisoption is on, treat images as grayscale ones");
- DEFINE_bool(shuffle, false,"Randomlyshuffle 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 areresized to");
- DEFINE_int32(resize_height, 0, "Height imagesare resized to");
- DEFINE_bool(check_size, false,"When this optionis on, check that all the datum have the samesize");
- DEFINE_bool(encoded, false,"When this option ison, the encoded image will be save in datum");
- DEFINE_string(encode_type, "","Optional:What type should we encode the image as ('png','jpg',...).");
3 main()函数
没有想cifar和mnist的main函数,通过调用convert_data()函数来转换数据,而是直接在main函数内完成了所有数据转换代码。
3.1 通过gflags宏定义接收命令行中传入的参数
- const boolis_color = !FLAGS_gray;
- const boolcheck_size = FLAGS_check_size;
- const boolencoded = FLAGS_encoded;
- const stringencode_type = FLAGS_encode_type;
3.2读取源数据
3.2.1创建读取对象变量
std::ifstream infile(argv[2]);//创建指向train.txt文件的文件读入流
std::vector > lines;//定义向量变量,向量中每个元素为一个pair对,pair对有两个成员变量,一个为string类型,一个为int类型;其中string类型用于存储文件名,int类型,感觉用于存数对应类别的id
如val.txt中前几个字符为“ILSVRC2012_val_00000001.JPEG65ILSVRC2012_val_00000002.JPEG”;感觉这个string= ILSVRC2012_val_00000001.JPEG int=65
std::stringfilename;
int label;
3.2.2 读取数据
//下面一条while语句是把train.txt文件中存放的所有文件名和标签,都存放到vextor类型变量lines中;lines中存放图片的名字和对应的标签,不存储真正的图片数据
- while (infile>> filename >> label) {
- nes.push_back(std::make_pair(filename, label));
//make_pair是pair模板中定义的给pair对象赋值的函数,push_back()函数是vector对象的一个成员函数,用来在末端添加新元素}
3.3判断是否进行洗牌操作
- if(FLAGS_shuffle) {
-
- LOG(INFO)<< "Shuffling data";
- "font-family: Arial, Helvetica, sans-serif; background-color: rgb(255, 255, 255);">
shuffle(lines.begin(), lines.end());//vector.begin() - 回传一个Iterator迭代器,它指向 vector 第一个元素。}
3.4以智能指针的方式创建db::DB类型的对象 db
- scoped_ptrdb(db::GetDB(FLAGS_backend));
-
- db->Open(argv[3], db::NEW);
- scoped_ptrtxn(db->NewTransaction());
3.5 源数据中提取图像数据
3.5.1 通过ReadImageToDatum函数把图像数据读取到datum中
//到源数据位置读取每张图片的数据。(../imagenet/xxx.jpeg,65,256,256,true,jpeg,&datum)
- status= ReadImageToDatum(root_folder + lines[line_id].first,lines[line_id].second, resize_height,resize_width, is_color,enc, &datum);
3.5.2 ReadImageToDatum函数说明
ReadImageToDatum函数为io.cpp文件中定义的函数;io.cpp主要实现了3部分功能:
1,从text文件或者二进制文件中读写proto文件;
2,利用opencv的Mat矩阵,把图像数据读到Mat矩阵中;
3,把Mat矩阵中的值放入到datum中
3.5.3 检查数据尺寸
- 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();
- }
3.6 序列化键和值并放入临时数据库
-
- intlength = snprintf(key_cstr, kMaxKeyLength, "%08d_%s", line_id,lines[line_id].first.c_str());
-
- string out;
- CHECK(datum.SerializeToString(&out));
- txn->Put(string(key_cstr, length), out);
3.7 批量提交到lmdb文件
- if (++count % 1000 == 0) {
-
- txn->Commit();
- txn.reset(db->NewTransaction());
- LOG(ERROR) << "Processed" << count << " files.";
- }
四,相关文件
4.1 Convert_imageset.cpp文件
-
-
-
-
-
-
-
-
-
-
- #include //输出数组的内容、对数组进行升幂排序、反转数组内容、复制数组内容等操作,
- #include // NOLINT(readability/streams)
- #include
- #include //utility头文件定义了一个pair类型
- #include //会自动扩展容量的数组
-
- #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"
- #include "caffe/util/rng.hpp"
-
- using namespace caffe;
- 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) {
- ::google::InitGoogleLogging(argv[0]);
-
- #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::vectorint> > lines;
- std::string filename;
- int label;
-
- while (infile >> filename >> label) {
- lines.push_back(std::make_pair(filename, label));
- }
- if (FLAGS_shuffle) {
-
- 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);
-
-
- scoped_ptr db(db::GetDB(FLAGS_backend));
- db->Open(argv[3], db::NEW);
- scoped_ptr txn(db->NewTransaction());
-
-
- std::string root_folder(argv[1]);
- Datum datum;
- int count = 0;
- const int kMaxKeyLength = 256;
- char key_cstr[kMaxKeyLength];
- 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()) {
-
- 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();
- }
- }
-
- int length = snprintf(key_cstr, kMaxKeyLength, "%08d_%s", line_id,
- lines[line_id].first.c_str());
-
-
- string out;
- CHECK(datum.SerializeToString(&out));
- txn->Put(string(key_cstr, length), out);
-
- if (++count % 1000 == 0) {
-
- txn->Commit();
- txn.reset(db->NewTransaction());
- LOG(ERROR) << "Processed " << count << " files.";
- }
- }
-
- if (count % 1000 != 0) {
- txn->Commit();
- LOG(ERROR) << "Processed " << count << " files.";
- }
- return 0;
- }
4.2 io.cpp文件
- #include
- #include
- #include
- #include
- #include
- #include
- #include
- #include
- #include
-
- #include
- #include // NOLINT(readability/streams)
- #include
- #include
-
- #include "caffe/common.hpp"
- #include "caffe/proto/caffe.pb.h"
- #include "caffe/util/io.hpp"
-
- const int kProtoReadBytesLimit = INT_MAX;
-
- namespace caffe {
-
- using google::protobuf::io::FileInputStream;
- using google::protobuf::io::FileOutputStream;
- using google::protobuf::io::ZeroCopyInputStream;
- using google::protobuf::io::CodedInputStream;
- using google::protobuf::io::ZeroCopyOutputStream;
- using google::protobuf::io::CodedOutputStream;
- using google::protobuf::Message;
-
- bool ReadProtoFromTextFile(const char* filename, Message* proto) {
- int fd = open(filename, O_RDONLY);
- CHECK_NE(fd, -1) << "File not found: " << filename;
- FileInputStream* input = new FileInputStream(fd);
- bool success = google::protobuf::TextFormat::Parse(input, proto);
- delete input;
- close(fd);
- return success;
- }
-
- void WriteProtoToTextFile(const Message& proto, const char* filename) {
- int fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC, 0644);
- FileOutputStream* output = new FileOutputStream(fd);
- CHECK(google::protobuf::TextFormat::Print(proto, output));
- delete output;
- close(fd);
- }
-
- bool ReadProtoFromBinaryFile(const char* filename, Message* proto) {
- int fd = open(filename, O_RDONLY);
- CHECK_NE(fd, -1) << "File not found: " << filename;
- ZeroCopyInputStream* raw_input = new FileInputStream(fd);
- CodedInputStream* coded_input = new CodedInputStream(raw_input);
- coded_input->SetTotalBytesLimit(kProtoReadBytesLimit, 536870912);
-
- bool success = proto->ParseFromCodedStream(coded_input);
-
- delete coded_input;
- delete raw_input;
- close(fd);
- return success;
- }
-
- void WriteProtoToBinaryFile(const Message& proto, const char* filename) {
- fstream output(filename, ios::out | ios::trunc | ios::binary);
- CHECK(proto.SerializeToOstream(&output));
- }
-
-
-
-
-
-
-
- cv::Mat ReadImageToCVMat(const string& filename,
- const int height, const int width, const bool is_color) {
- cv::Mat cv_img;
- int cv_read_flag = (is_color ? CV_LOAD_IMAGE_COLOR :
- CV_LOAD_IMAGE_GRAYSCALE);
- cv::Mat cv_img_origin = cv::imread(filename, cv_read_flag);
- if (!cv_img_origin.data) {
- LOG(ERROR) << "Could not open or find file " << filename;
- return cv_img_origin;
- }
- if (height > 0 && width > 0) {
- cv::resize(cv_img_origin, cv_img, cv::Size(width, height));
- } else {
- cv_img = cv_img_origin;
- }
- return cv_img;
- }
-
- cv::Mat ReadImageToCVMat(const string& filename,
- const int height, const int width) {
- return ReadImageToCVMat(filename, height, width, true);
- }
-
- cv::Mat ReadImageToCVMat(const string& filename,
- const bool is_color) {
- return ReadImageToCVMat(filename, 0, 0, is_color);
- }
-
- cv::Mat ReadImageToCVMat(const string& filename) {
- return ReadImageToCVMat(filename, 0, 0, true);
- }
-
- static bool matchExt(const std::string & fn,
- std::string en) {
- size_t p = fn.rfind('.');
- std::string ext = p != fn.npos ? fn.substr(p) : fn;
- std::transform(ext.begin(), ext.end(), ext.begin(), ::tolower);
- std::transform(en.begin(), en.end(), en.begin(), ::tolower);
- if ( ext == en )
- return true;
- if ( en == "jpg" && ext == "jpeg" )
- return true;
- return false;
- }
-
- bool ReadImageToDatum(const string& filename, const int label,
- const int height, const int width, const bool is_color,
- const std::string & encoding, Datum* datum) {
- cv::Mat cv_img = ReadImageToCVMat(filename, height, width, is_color);
- if (cv_img.data) {
- if (encoding.size()) {
- if ( (cv_img.channels() == 3) == is_color && !height && !width &&
- matchExt(filename, encoding) )
- return ReadFileToDatum(filename, label, datum);
-
- std::vector buf;
- cv::imencode("."+encoding, cv_img, buf);
- datum->set_data(std::string(reinterpret_cast<char*>(&buf[0]),
- buf.size()));
- datum->set_label(label);
- datum->set_encoded(true);
- return true;
- }
- CVMatToDatum(cv_img, datum);
- datum->set_label(label);
- return true;
- } else {
- return false;
- }
- }
-
- bool ReadFileToDatum(const string& filename, const int label,
- Datum* datum) {
- std::streampos size;
-
- fstream file(filename.c_str(), ios::in|ios::binary|ios::ate);
- if (file.is_open()) {
- size = file.tellg();
- std::string buffer(size, ' ');
- file.seekg(0, ios::beg);
- file.read(&buffer[0], size);
- file.close();
- datum->set_data(buffer);
- datum->set_label(label);
- datum->set_encoded(true);
- return true;
- } else {
- return false;
- }
- }
-
- cv::Mat DecodeDatumToCVMatNative(const Datum& datum) {
- cv::Mat cv_img;
- CHECK(datum.encoded()) << "Datum not encoded";
- const string& data = datum.data();
- std::vector<char> vec_data(data.c_str(), data.c_str() + data.size());
- cv_img = cv::imdecode(vec_data, -1);
- if (!cv_img.data) {
- LOG(ERROR) << "Could not decode datum ";
- }
- return cv_img;
- }
- cv::Mat DecodeDatumToCVMat(const Datum& datum, bool is_color) {
- cv::Mat cv_img;
- CHECK(datum.encoded()) << "Datum not encoded";
- const string& data = datum.data();
- std::vector<char> vec_data(data.c_str(), data.c_str() + data.size());
- int cv_read_flag = (is_color ? CV_LOAD_IMAGE_COLOR :
- CV_LOAD_IMAGE_GRAYSCALE);
- cv_img = cv::imdecode(vec_data, cv_read_flag);
- if (!cv_img.data) {
- LOG(ERROR) << "Could not decode datum ";
- }
- return cv_img;
- }
-
-
-
- bool DecodeDatumNative(Datum* datum) {
- if (datum->encoded()) {
- cv::Mat cv_img = DecodeDatumToCVMatNative((*datum));
- CVMatToDatum(cv_img, datum);
- return true;
- } else {
- return false;
- }
- }
- bool DecodeDatum(Datum* datum, bool is_color) {
- if (datum->encoded()) {
- cv::Mat cv_img = DecodeDatumToCVMat((*datum), is_color);
- CVMatToDatum(cv_img, datum);
- return true;
- } else {
- return false;
- }
- }
-
- void CVMatToDatum(const cv::Mat& cv_img, Datum* datum) {
- CHECK(cv_img.depth() == CV_8U) << "Image data type must be unsigned byte";
- datum->set_channels(cv_img.channels());
- datum->set_height(cv_img.rows);
- datum->set_width(cv_img.cols);
- datum->clear_data();
- datum->clear_float_data();
- datum->set_encoded(false);
- int datum_channels = datum->channels();
- int datum_height = datum->height();
- int datum_width = datum->width();
- int datum_size = datum_channels * datum_height * datum_width;
- std::string buffer(datum_size, ' ');
- for (int h = 0; h < datum_height; ++h) {
- const uchar* ptr = cv_img.ptr(h);
- int img_index = 0;
- for (int w = 0; w < datum_width; ++w) {
- for (int c = 0; c < datum_channels; ++c) {
- int datum_index = (c * datum_height + h) * datum_width + w;
- buffer[datum_index] = static_cast<char>(ptr[img_index++]);
- }
- }
- }
- datum->set_data(buffer);
- }
- 。。。。。
五,
以上代码注释为个人理解,如有遗漏,错误还望大家多多交流,指正,以便共同学习,进步!!