转载:
https://www.cnblogs.com/linyuanzhou/p/6370677.html
我花开后百花残
机器学习&算法设计
std::ifstream infile(argv[2]);
std::vector<std::pair<std::string, std::vector<float>> > lines;
std::string filename;
std::string label_count_string = argv[5];
int label_count = std::atoi(label_count_string.c_str());
std::vector<float> label(label_count);
while (infile >> filename) {
for (int i = 0; i < label_count; i++)
infile >> label[i];
lines.push_back(std::make_pair(filename, 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_image(db::GetDB(FLAGS_backend));
scoped_ptr<db::DB> db_label(db::GetDB(FLAGS_backend));
db_image->Open(argv[3], db::NEW);
db_label->Open(argv[4], db::NEW);
scoped_ptr<db::Transaction> txn_image(db_image->NewTransaction());
scoped_ptr<db::Transaction> txn_label(db_label->NewTransaction());
// // 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_image;
Datum datum_label;
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[0], resize_height, resize_width, is_color,
enc, &datum_image);
if (status == false) continue;
if (check_size) {
if (!data_size_initialized) {
data_size = datum_image.channels() * datum_image.height() * datum_image.width();
data_size_initialized = true;
} else {
const std::string& data = datum_image.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_image.SerializeToString(&out));
txn_image->Put(key_str, out);
//
datum_label.set_channels(label_count);
datum_label.set_height(1);
datum_label.set_width(1);
datum_label.clear_data();
datum_label.clear_float_data();
datum_label.set_encoded(false);
std::vector<float> label_vec = lines[line_id].second;
for (int i = 0; i < label_vec.size();i++)
{
datum_label.add_float_data(label_vec[i]);
}
string out_label;
CHECK(datum_label.SerializeToString(&out_label));
txn_label->Put(key_str, out_label);
//
if (++count % 1000 == 0) {
// Commit db
txn_image->Commit();
txn_image.reset(db_image->NewTransaction());
txn_label->Commit();
txn_label.reset(db_label->NewTransaction());
LOG(INFO) << "Processed " << count << " files.";
}
}
// write the last batch
if (count % 1000 != 0) {
txn_image->Commit();
txn_label->Commit();
LOG(INFO) << "Processed " << count << " files.";
}
# -*- coding: utf-8 -*-
"""
Created on Sat Dec 24 20:57:28 2016
@author: zhouly
"""
import lmdb
from skimage import io
import numpy as np
import sys
caffe_root = '../../'
sys.path.insert(0, caffe_root + '/python')
import caffe
import cv2
root = '../../'
file_input=open(root+'data/train.txt','r')
in_image_db=lmdb.open(root+'examples/99/train_image_lmdb', map_size=int(1e12))
in_label_db=lmdb.open(root+'examples/99/train_label_lmdb', map_size=int(1e12))
in_image_txn = in_image_db.begin(write=True)
in_label_txn = in_label_db.begin(write=True)
for in_idx, in_ in enumerate(file_input):
content = in_.strip()
content = content.split(' ')
im_file = root + 'data/verification/' + content[0]
try:
im = io.imread(im_file)
except:
print '-------------------------', im_file
continue
im = im[:,:, 3]
im = cv2.resize(im, (224, 224), interpolation=cv2.INTER_LINEAR)
data = np.zeros((3, 224, 224), np.uint8)
data[0, :, :] = im[:, :]
data[1, :, :] = im[:, :]
data[2, :, :] = im[:, :]
im_dat = caffe.io.array_to_datum(data)
in_image_txn.put('{:0>10d}'.format(in_idx), im_dat.SerializeToString())
print 'data train: {} [{}]'.format(content[0], in_idx + 1)
del im_file, im, im_dat, data
target_label = np.zeros((4, 1, 1))
target_label[0, 0, 0] = int(content[1])
target_label[1, 0, 0] = int(content[2])
target_label[2, 0, 0] = int(content[3])
target_label[3, 0, 0] = int(content[4])
label_data = caffe.io.array_to_datum(target_label)
in_label_txn.put('{:0>10d}'.format(in_idx), label_data.SerializeToString())
del target_label, label_data
in_image_txn.commit()
in_label_txn.commit()
in_image_db.close()
in_label_db.close()
file_input.close()