1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
|
#include <stdint.h>
#include <algorithm>
#include <string>
#include <utility>
#include <vector>
#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"
using namespace caffe; // NOLINT(build/namespaces)
using std::max;
using std::pair;
using boost::scoped_ptr;
DEFINE_string(backend, "lmdb",
"The backend {leveldb, lmdb} containing the images");
int main(int argc, char** argv) {
::google::InitGoogleLogging(argv[0]);
#ifndef GFLAGS_GFLAGS_H_
namespace gflags = google;
#endif
gflags::SetUsageMessage("Compute the mean_image of a set of images given by"
" a leveldb/lmdb\n"
"Usage:\n"
" compute_image_mean [FLAGS] INPUT_DB [OUTPUT_FILE]\n");
gflags::ParseCommandLineFlags(&argc, &argv, true);
if (argc < 2 || argc > 3) {
gflags::ShowUsageWithFlagsRestrict(argv[0], "tools/compute_image_mean");
return 1;
}
scoped_ptr<db::DB> db(db::GetDB(FLAGS_backend));
db->Open(argv[1], db::READ);
scoped_ptr<db::Cursor> cursor(db->NewCursor());
BlobProto sum_blob;
int count = 0;
// load first datum
Datum datum;
datum.ParseFromString(cursor->value());
if (DecodeDatumNative(&datum)) {
LOG(INFO) << "Decoding Datum";
}
sum_blob.set_num(1);
sum_blob.set_channels(datum.channels());
sum_blob.set_height(datum.height());
sum_blob.set_width(datum.width());
const int data_size = datum.channels() * datum.height() * datum.width();
int size_in_datum = std::max<int>(datum.data().size(),
datum.float_data_size());
for (int i = 0; i < size_in_datum; ++i) {
sum_blob.add_data(0.);
}
LOG(INFO) << "Starting Iteration";
while (cursor->valid()) {
Datum datum;
datum.ParseFromString(cursor->value());
DecodeDatumNative(&datum);
const std::string& data = datum.data();
size_in_datum = std::max<int>(datum.data().size(),
datum.float_data_size());
CHECK_EQ(size_in_datum, data_size) << "Incorrect data field size " <<
size_in_datum;
if (data.size() != 0) {
CHECK_EQ(data.size(), size_in_datum);
for (int i = 0; i < size_in_datum; ++i) {
sum_blob.set_data(i, sum_blob.data(i) + (uint8_t)data[i]);
}
} else {
CHECK_EQ(datum.float_data_size(), size_in_datum);
for (int i = 0; i < size_in_datum; ++i) {
sum_blob.set_data(i, sum_blob.data(i) +
static_cast<float>(datum.float_data(i)));
}
}
++count;
if (count % 10000 == 0) {
LOG(INFO) << "Processed " << count << " files.";
}
cursor->Next();
}
if (count % 10000 != 0) {
LOG(INFO) << "Processed " << count << " files.";
}
for (int i = 0; i < sum_blob.data_size(); ++i) {
sum_blob.set_data(i, sum_blob.data(i) / count);
}
// Write to disk
if (argc == 3) {
LOG(INFO) << "Write to " << argv[2];
WriteProtoToBinaryFile(sum_blob, argv[2]);
}
const int channels = sum_blob.channels();
const int dim = sum_blob.height() * sum_blob.width();
std::vector<float> mean_values(channels, 0.0);
LOG(INFO) << "Number of channels: " << channels;
for (int c = 0; c < channels; ++c) {
for (int i = 0; i < dim; ++i) {
mean_values[c] += sum_blob.data(dim * c + i);
}
LOG(INFO) << "mean_value channel [" << c << "]:" << mean_values[c] / dim;
}
return 0;
}
|
