4
#include "boost/algorithm/string.hpp"
5
#include "google/protobuf/text_format.h"
7
#include "caffe/blob.hpp"
8
#include "caffe/common.hpp"
9
#include "caffe/net.hpp"
10
#include "caffe/proto/caffe.pb.h"
11
#include "caffe/util/db.hpp"
12
#include "caffe/util/format.hpp"
13
#include "caffe/util/io.hpp"
20
namespace db = caffe::db;
22
template<typename Dtype>
23
int feature_extraction_pipeline(int argc, char** argv);
25
int main(int argc, char** argv) {
26
return feature_extraction_pipeline<float>(argc, argv);
27
// return feature_extraction_pipeline<double>(argc, argv);
30
template<typename Dtype>
31
int feature_extraction_pipeline(int argc, char** argv) {
32
::google::InitGoogleLogging(argv[0]);
33
const int num_required_args = 7;
34
if (argc < num_required_args) {
36
"This program takes in a trained network and an input data layer, and then"
37
" extract features of the input data produced by the net.\n"
38
"Usage: extract_features pretrained_net_param"
39
" feature_extraction_proto_file extract_feature_blob_name1[,name2,...]"
40
" save_feature_dataset_name1[,name2,...] num_mini_batches db_type"
41
" [CPU/GPU] [DEVICE_ID=0]\n"
42
"Note: you can extract multiple features in one pass by specifying"
43
" multiple feature blob names and dataset names separated by ','."
44
" The names cannot contain white space characters and the number of blobs"
45
" and datasets must be equal.";
48
int arg_pos = num_required_args;
50
arg_pos = num_required_args;
51
if (argc > arg_pos && strcmp(argv[arg_pos], "GPU") == 0) {
52
LOG(ERROR)<< "Using GPU";
54
if (argc > arg_pos + 1) {
55
device_id = atoi(argv[arg_pos + 1]);
56
CHECK_GE(device_id, 0);
58
LOG(ERROR) << "Using Device_id=" << device_id;
59
Caffe::SetDevice(device_id);
60
Caffe::set_mode(Caffe::GPU);
62
LOG(ERROR) << "Using CPU";
63
Caffe::set_mode(Caffe::CPU);
66
arg_pos = 0; // the name of the executable
67
std::string pretrained_binary_proto(argv[++arg_pos]);
69
// Expected prototxt contains at least one data layer such as
70
// the layer data_layer_name and one feature blob such as the
71
// fc7 top blob to extract features.
74
name: "data_layer_name"
77
source: "/path/to/your/images/to/extract/feature/images_leveldb"
78
mean_file: "/path/to/your/image_mean.binaryproto"
84
top: "label_blob_name"
96
std::string feature_extraction_proto(argv[++arg_pos]);
97
boost::shared_ptr<Net<Dtype> > feature_extraction_net(
98
new Net<Dtype>(feature_extraction_proto, caffe::TEST));
99
feature_extraction_net->CopyTrainedLayersFrom(pretrained_binary_proto);
101
std::string extract_feature_blob_names(argv[++arg_pos]);
102
std::vector<std::string> blob_names;
103
boost::split(blob_names, extract_feature_blob_names, boost::is_any_of(","));
105
std::string save_feature_dataset_names(argv[++arg_pos]);
106
std::vector<std::string> dataset_names;
107
boost::split(dataset_names, save_feature_dataset_names,
108
boost::is_any_of(","));
109
CHECK_EQ(blob_names.size(), dataset_names.size()) <<
110
" the number of blob names and dataset names must be equal";
111
size_t num_features = blob_names.size();
113
for (size_t i = 0; i < num_features; i++) {
114
CHECK(feature_extraction_net->has_blob(blob_names[i]))
115
<< "Unknown feature blob name " << blob_names[i]
116
<< " in the network " << feature_extraction_proto;
119
int num_mini_batches = atoi(argv[++arg_pos]);
121
std::vector<boost::shared_ptr<db::DB> > feature_dbs;
122
std::vector<boost::shared_ptr<db::Transaction> > txns;
123
const char* db_type = argv[++arg_pos];
124
for (size_t i = 0; i < num_features; ++i) {
125
LOG(INFO)<< "Opening dataset " << dataset_names[i];
126
boost::shared_ptr<db::DB> db(db::GetDB(db_type));
127
db->Open(dataset_names.at(i), db::NEW);
128
feature_dbs.push_back(db);
129
boost::shared_ptr<db::Transaction> txn(db->NewTransaction());
133
LOG(ERROR)<< "Extracting Features";
136
std::vector<int> image_indices(num_features, 0);
137
for (int batch_index = 0; batch_index < num_mini_batches; ++batch_index) {
138
feature_extraction_net->Forward();
139
for (int i = 0; i < num_features; ++i) {
140
const boost::shared_ptr<Blob<Dtype> > feature_blob =
141
feature_extraction_net->blob_by_name(blob_names[i]);
142
int batch_size = feature_blob->num();
143
int dim_features = feature_blob->count() / batch_size;
144
const Dtype* feature_blob_data;
145
for (int n = 0; n < batch_size; ++n) {
146
datum.set_height(feature_blob->height());
147
datum.set_width(feature_blob->width());
148
datum.set_channels(feature_blob->channels());
150
datum.clear_float_data();
151
feature_blob_data = feature_blob->cpu_data() +
152
feature_blob->offset(n);
153
for (int d = 0; d < dim_features; ++d) {
154
datum.add_float_data(feature_blob_data[d]);
156
string key_str = caffe::format_int(image_indices[i], 10);
159
CHECK(datum.SerializeToString(&out));
160
txns.at(i)->Put(key_str, out);
162
if (image_indices[i] % 1000 == 0) {
163
txns.at(i)->Commit();
164
txns.at(i).reset(feature_dbs.at(i)->NewTransaction());
165
LOG(ERROR)<< "Extracted features of " << image_indices[i] <<
166
" query images for feature blob " << blob_names[i];
168
} // for (int n = 0; n < batch_size; ++n)
169
} // for (int i = 0; i < num_features; ++i)
170
} // for (int batch_index = 0; batch_index < num_mini_batches; ++batch_index)
171
// write the last batch
172
for (int i = 0; i < num_features; ++i) {
173
if (image_indices[i] % 1000 != 0) {
174
txns.at(i)->Commit();
176
LOG(ERROR)<< "Extracted features of " << image_indices[i] <<
177
" query images for feature blob " << blob_names[i];
178
feature_dbs.at(i)->Close();
181
LOG(ERROR)<< "Successfully extracted the features!";