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
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
|
// Copyright 2014 kloudkl@github
#include <stdio.h> // for snprintf
#include <cuda_runtime.h>
#include <google/protobuf/text_format.h>
#include <leveldb/db.h>
#include <leveldb/write_batch.h>
#include "caffe/blob.hpp"
#include "caffe/common.hpp"
#include "caffe/net.hpp"
#include "caffe/vision_layers.hpp"
#include "caffe/proto/caffe.pb.h"
#include "caffe/util/io.hpp"
using namespace caffe;
template<typename Dtype>
int feature_extraction_pipeline(int argc, char** argv);
int main(int argc, char** argv) {
return feature_extraction_pipeline<float>(argc, argv);
// return feature_extraction_pipeline<double>(argc, argv);
}
template<typename Dtype>
int feature_extraction_pipeline(int argc, char** argv) {
const int num_required_args = 6;
if (argc < num_required_args) {
LOG(ERROR)<<
"This program takes in a trained network and an input data layer, and then"
" extract features of the input data produced by the net.\n"
"Usage: demo_extract_features pretrained_net_param"
" feature_extraction_proto_file extract_feature_blob_name"
" save_feature_leveldb_name num_mini_batches [CPU/GPU] [DEVICE_ID=0]";
return 1;
}
int arg_pos = num_required_args;
arg_pos = num_required_args;
if (argc > arg_pos && strcmp(argv[arg_pos], "GPU") == 0) {
LOG(ERROR)<< "Using GPU";
uint device_id = 0;
if (argc > arg_pos + 1) {
device_id = atoi(argv[arg_pos + 1]);
CHECK_GE(device_id, 0);
}
LOG(ERROR) << "Using Device_id=" << device_id;
Caffe::SetDevice(device_id);
Caffe::set_mode(Caffe::GPU);
} else {
LOG(ERROR) << "Using CPU";
Caffe::set_mode(Caffe::CPU);
}
Caffe::set_phase(Caffe::TEST);
NetParameter pretrained_net_param;
arg_pos = 0; // the name of the executable
string pretrained_binary_proto(argv[++arg_pos]);
ReadProtoFromBinaryFile(pretrained_binary_proto.c_str(),
&pretrained_net_param);
// Expected prototxt contains at least one data layer such as
// the layer data_layer_name and one feature blob such as the
// fc7 top blob to extract features.
/*
layers {
layer {
name: "data_layer_name"
type: "data"
source: "/path/to/your/images/to/extract/feature/images_leveldb"
meanfile: "/path/to/your/image_mean.binaryproto"
batchsize: 128
cropsize: 227
mirror: false
}
top: "data_blob_name"
top: "label_blob_name"
}
layers {
layer {
name: "drop7"
type: "dropout"
dropout_ratio: 0.5
}
bottom: "fc7"
top: "fc7"
}
*/
NetParameter feature_extraction_net_param;
;
string feature_extraction_proto(argv[++arg_pos]);
ReadProtoFromTextFile(feature_extraction_proto,
&feature_extraction_net_param);
shared_ptr<Net<Dtype> > feature_extraction_net(
new Net<Dtype>(feature_extraction_net_param));
feature_extraction_net->CopyTrainedLayersFrom(pretrained_net_param);
string extract_feature_blob_name(argv[++arg_pos]);
CHECK(feature_extraction_net->HasBlob(extract_feature_blob_name))
<< "Unknown feature blob name " << extract_feature_blob_name
<< " in the network " << feature_extraction_proto;
string save_feature_leveldb_name(argv[++arg_pos]);
leveldb::DB* db;
leveldb::Options options;
options.error_if_exists = true;
options.create_if_missing = true;
options.write_buffer_size = 268435456;
LOG(INFO)<< "Opening leveldb " << save_feature_leveldb_name;
leveldb::Status status = leveldb::DB::Open(options,
save_feature_leveldb_name.c_str(),
&db);
CHECK(status.ok()) << "Failed to open leveldb " << save_feature_leveldb_name;
int num_mini_batches = atoi(argv[++arg_pos]);
LOG(ERROR)<< "Extacting Features";
Datum datum;
leveldb::WriteBatch* batch = new leveldb::WriteBatch();
const int max_key_str_length = 100;
char key_str[max_key_str_length];
int num_bytes_of_binary_code = sizeof(Dtype);
vector<Blob<float>*> input_vec;
int image_index = 0;
for (int batch_index = 0; batch_index < num_mini_batches; ++batch_index) {
feature_extraction_net->Forward(input_vec);
const shared_ptr<Blob<Dtype> > feature_blob = feature_extraction_net
->GetBlob(extract_feature_blob_name);
int num_features = feature_blob->num();
int dim_features = feature_blob->count() / num_features;
for (int n = 0; n < num_features; ++n) {
datum.set_height(dim_features);
datum.set_width(1);
datum.set_channels(1);
datum.clear_data();
datum.clear_float_data();
const Dtype* feature_blob_data = feature_blob->cpu_data();
for (int d = 0; d < dim_features; ++d) {
datum.add_float_data(feature_blob_data[d]);
}
string value;
datum.SerializeToString(&value);
snprintf(key_str, max_key_str_length, "%d", image_index);
batch->Put(string(key_str), value);
++image_index;
if (image_index % 1000 == 0) {
db->Write(leveldb::WriteOptions(), batch);
LOG(ERROR)<< "Extracted features of " << image_index << " query images.";
delete batch;
batch = new leveldb::WriteBatch();
}
}
} // for (int batch_index = 0; batch_index < num_mini_batches; ++batch_index)
// write the last batch
if (image_index % 1000 != 0) {
db->Write(leveldb::WriteOptions(), batch);
LOG(ERROR)<< "Extracted features of " << image_index << " query images.";
delete batch;
batch = new leveldb::WriteBatch();
}
delete batch;
delete db;
LOG(ERROR)<< "Successfully extracted the features!";
return 0;
}
|
