【深度学习】【caffe实用工具6】笔记28 windows下SSD网络中的convert

/**************************************************************************************************************************
文件说明:【1】这个程序用于将图像数据集合(a set of images)和与这个图像相关的注释(annotations)转换为caffe专用的数据库LMDB/LEVELDB格式【2】使用方法:convert_annoset [FLAGS] ROOTFOLDER/ LISTFILE DB_NAME[1]ROOTFOLDER/----------------图像数据所在的文件夹[2]LISTFILE-------------------输入图像数据的文件列表，其每一行为subfolder1/file1.JPEG 7[3][FLAGS]--------------------可选参数，是否使用shuffle，颜色空间，编码等【3】对于【分类任务】，文件的格式如下所示:imgfolder1/img1.JPEG 7【4】对于【检测任务】，文件的格式如下所示:imgfolder1/img1.JPEG annofolder1/anno1.xml
检测任务的使用举例:代码需要进行三处修改:【1】DEFINE_string(anno_type,   "detection","The type of annotation {classification, detection}.");【2】DEFINE_string(label_map_file,"E://caffeInstall2013SSDCUDA//caffe-ssd-microsoft//data//ssd//labelmap_voc.prototxt","A file with LabelMap protobuf message.");【3】主函数中代码修改:argv[1] = "E://caffeInstall2013SSDCUDA//caffe-ssd-microsoft//data//ssd//";argv[2] = "E://caffeInstall2013SSDCUDA//caffe-ssd-microsoft//data//ssd//test.txt";argv[3] = "E://caffeInstall2013SSDCUDA//caffe-ssd-microsoft//examples//ssd//ssd_test_lmdb";
开发环境:Win10+cuda7.5+cuDnnV5.0+ccaffe_windows_ssd+OpenCv+VS2013
时间地点:陕西师范大学 文津楼 2017.8.10
作    者:九 月
***************************************************************************************************************************/
#include <algorithm>
#include <fstream>  // NOLINT(readability/streams)
#include <map>
#include <string>
#include <utility>
#include <vector>#include "boost/scoped_ptr.hpp"
#include "boost/variant.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_string(anno_type,   "detection","The type of annotation {classification, detection}.");
DEFINE_string(label_type,  "xml",      "The type of annotation file format.");
DEFINE_string(label_map_file,"E://caffeInstall2013SSDCUDA//caffe-ssd-microsoft//data//ssd//labelmap_voc.prototxt",      "A file with LabelMap protobuf message.");
DEFINE_bool(  check_label,  false,    "When this option is on, check that there is no duplicated name/label.");
DEFINE_int32( min_dim,      0,         "Minimum dimension images are resized to (keep same aspect ratio)");
DEFINE_int32( max_dim,      0,         "Maximum dimension images are resized to (keep same aspect ratio)");
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;
#endifgflags::SetUsageMessage("Convert a set of images and annotations to the ""leveldb/lmdb format used as input for Caffe.\n""Usage:\n""    convert_annoset [FLAGS] ROOTFOLDER/ LISTFILE DB_NAME\n");argv[1] = "E://caffeInstall2013SSDCUDA//caffe-ssd-microsoft//data//ssd//";argv[2] = "E://caffeInstall2013SSDCUDA//caffe-ssd-microsoft//data//ssd//test.txt";argv[3] = "E://caffeInstall2013SSDCUDA//caffe-ssd-microsoft//examples//ssd//ssd_test_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;const string anno_type   = FLAGS_anno_type;AnnotatedDatum_AnnotationType type;const string label_type     = FLAGS_label_type;const string label_map_file = FLAGS_label_map_file;const bool check_label     = FLAGS_check_label;std::map<std::string, int> name_to_label;std::ifstream infile(argv[2]);std::vector<std::pair<std::string, boost::variant<int, std::string> > > lines;std::string filename;int         label;std::string labelname;if (anno_type == "classification") {while (infile >> filename >> label) {lines.push_back(std::make_pair(filename, label));}} else if (anno_type == "detection") {type = AnnotatedDatum_AnnotationType_BBOX;LabelMap label_map;CHECK(ReadProtoFromTextFile(label_map_file, &label_map))<< "Failed to read label map file.";CHECK(MapNameToLabel(label_map, check_label, &name_to_label))<< "Failed to convert name to label.";while (infile >> filename >> labelname) {lines.push_back(std::make_pair(filename, labelname));}}if (FLAGS_shuffle) {// randomly shuffle dataLOG(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 min_dim       = std::max<int>(0, FLAGS_min_dim);int max_dim       = std::max<int>(0, FLAGS_max_dim);int resize_height = std::max<int>(0, FLAGS_resize_height);int resize_width  = std::max<int>(0, FLAGS_resize_width);// Create new DBscoped_ptr<db::DB> db(db::GetDB(FLAGS_backend));db->Open(argv[3], db::NEW);scoped_ptr<db::Transaction> txn(db->NewTransaction());// Storing to dbstd::string root_folder(argv[1]);AnnotatedDatum anno_datum;Datum* datum = anno_datum.mutable_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 = true;std::string enc = encode_type;if (encoded && !enc.size()) {// Guess the encoding type from the file namestring 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);}filename = root_folder + lines[line_id].first;if (anno_type == "classification") {label = boost::get<int>(lines[line_id].second);status = ReadImageToDatum(filename, label, resize_height, resize_width,min_dim, max_dim, is_color, enc, datum);} else if (anno_type == "detection") {labelname = root_folder + boost::get<std::string>(lines[line_id].second);status = ReadRichImageToAnnotatedDatum(filename, labelname, resize_height,resize_width, min_dim, max_dim, is_color, enc, type, label_type,name_to_label, &anno_datum);anno_datum.set_type(AnnotatedDatum_AnnotationType_BBOX);}if (status == false) {LOG(WARNING) << "Failed to read " << lines[line_id].first;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();}}// sequentialstring key_str = caffe::format_int(line_id, 8) + "_" + lines[line_id].first;// Put in dbstring out;CHECK(anno_datum.SerializeToString(&out));txn->Put(key_str, out);if (++count % 1000 == 0) {// Commit dbtxn->Commit();txn.reset(db->NewTransaction());LOG(INFO) << "Processed " << count << " files.";}}// write the last batchif (count % 1000 != 0) {txn->Commit();LOG(INFO) << "Processed " << count << " files.";}std::system("pause");
#elseLOG(FATAL) << "This tool requires OpenCV; compile with USE_OPENCV.";
#endif  // USE_OPENCVreturn 0;
}

用了30分钟，终于生成了训练阶段所需要的LMDB数据库文件，如下所示：

【深度学习】【caffe实用工具6】笔记28 windows下SSD网络中的convert_annoset工具的使用相关推荐

深度学习核心技术精讲100篇（二）-图网络中的社群及社群发现算法
前言本篇博文主要讲解Graph中社群的概念,然后介绍了一种简单的社群发现算法Louvain Algorithm,最后提供可重叠的社群发现,提出BigCLAM算法,用来识别节点从属关系. 01 Gra ...
吴恩达【优化深度神经网络】笔记01——深度学习的实用层面
文章目录引言一.训练集/验证集/测试集(Train/Dev/Test sets) 1. 数据集选择 2. 补充:交叉验证(cross validation) 二.偏差和方差(Bias/Varian ...
吴恩达《优化深度神经网络》精炼笔记（1）-- 深度学习的实用层面
AI有道不可错过的AI技术公众号关注吴恩达的深度学习专项课程的第一门课<神经网络与深度学习>的所有精炼笔记我已经整理完毕.迷路的小伙伴请见文章末尾的推荐阅读: 在接下来的几次笔记中, ...
吴恩达深度学习笔记5-Course2-Week1【深度学习的实用层面】
改善深层神经网络:超参数调试.正则化以及优化深度学习的实用层面一.训练.验证.测试集样本数据分成以下三个部分: 训练集(train set): 用于对模型进行训练. 验证集(hold-out c ...
深度学习硬啃计划与笔记
标题:爱看不看,你怎么还不死提示:直观的图表有助于理论的理解与加深记忆,学习的重心是理解算法,由浅入深从来不是问题. 6.22 上午复习Logistic回归和梯度下降 6.22 下午复习Logi ...
Python 深度学习架构实用指南：第一、二部分
原文:Hands-On Deep Learning Architectures with Python 协议:CC BY-NC-SA 4.0 译者:飞龙本文来自[ApacheCN 深度学习译文集] ...
深度学习总结——CS231n课程深度学习（机器视觉相关）笔记整理
深度学习笔记整理说明基本知识点一:模型的设置(基本) 1. 激活函数的设置 2. 损失函数的设置 (1) 分类问题 (2) 属性问题 (3) 回归问题 3. 正则化方式的设置 (1) 损失函数添加 ...
网络存储 linux 访问,Linux基础教程学习笔记28——使用Samba访问网络存储
Linux基础教程学习笔记28--使用Samba访问网络存储 SMB用于Windows和类Linux系统直接的文件共享安装samba client包: [root@linuxidc~]# yum i ...
caffe模型文件解析_深度学习 Caffe 初始化流程理解（数据流建立）
深度学习 Caffe 初始化流程理解(数据流建立) 之前在简书的文章,搬迁过来 ^-^ 本文是作者原创,如有理解错误,恳请大家指出,如需引用,请注明出处. #Caffe FeatureMap数据流的建 ...

【深度学习】【caffe实用工具6】笔记28 windows下SSD网络中的convert_annoset工具的使用

【深度学习】【caffe实用工具6】笔记28 windows下SSD网络中的convert_annoset工具的使用相关推荐

最新文章

热门文章