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
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
|
// Copyright (C) 2011 Davis E. King (davis@dlib.net)
// License: Boost Software License See LICENSE.txt for the full license.
#ifndef DLIB_STRUCTURAL_SEQUENCE_LABELING_TRAiNER_Hh_
#define DLIB_STRUCTURAL_SEQUENCE_LABELING_TRAiNER_Hh_
#include "structural_sequence_labeling_trainer_abstract.h"
#include "../algs.h"
#include "../optimization.h"
#include "structural_svm_sequence_labeling_problem.h"
#include "num_nonnegative_weights.h"
namespace dlib
{
// ----------------------------------------------------------------------------------------
template <
typename feature_extractor
>
class structural_sequence_labeling_trainer
{
public:
typedef typename feature_extractor::sequence_type sample_sequence_type;
typedef std::vector<unsigned long> labeled_sequence_type;
typedef sequence_labeler<feature_extractor> trained_function_type;
explicit structural_sequence_labeling_trainer (
const feature_extractor& fe_
) : fe(fe_)
{
set_defaults();
}
structural_sequence_labeling_trainer (
)
{
set_defaults();
}
const feature_extractor& get_feature_extractor (
) const { return fe; }
unsigned long num_labels (
) const { return fe.num_labels(); }
void set_num_threads (
unsigned long num
)
{
num_threads = num;
}
unsigned long get_num_threads (
) const
{
return num_threads;
}
void set_epsilon (
double eps_
)
{
// make sure requires clause is not broken
DLIB_ASSERT(eps_ > 0,
"\t void structural_sequence_labeling_trainer::set_epsilon()"
<< "\n\t eps_ must be greater than 0"
<< "\n\t eps_: " << eps_
<< "\n\t this: " << this
);
eps = eps_;
}
double get_epsilon (
) const { return eps; }
unsigned long get_max_iterations (
) const { return max_iterations; }
void set_max_iterations (
unsigned long max_iter
)
{
max_iterations = max_iter;
}
void set_max_cache_size (
unsigned long max_size
)
{
max_cache_size = max_size;
}
unsigned long get_max_cache_size (
) const
{
return max_cache_size;
}
void be_verbose (
)
{
verbose = true;
}
void be_quiet (
)
{
verbose = false;
}
void set_oca (
const oca& item
)
{
solver = item;
}
const oca get_oca (
) const
{
return solver;
}
void set_c (
double C_
)
{
// make sure requires clause is not broken
DLIB_ASSERT(C_ > 0,
"\t void structural_sequence_labeling_trainer::set_c()"
<< "\n\t C_ must be greater than 0"
<< "\n\t C_: " << C_
<< "\n\t this: " << this
);
C = C_;
}
double get_c (
) const
{
return C;
}
double get_loss (
unsigned long label
) const
{
// make sure requires clause is not broken
DLIB_ASSERT(label < num_labels(),
"\t void structural_sequence_labeling_trainer::get_loss()"
<< "\n\t invalid inputs were given to this function"
<< "\n\t label: " << label
<< "\n\t num_labels(): " << num_labels()
<< "\n\t this: " << this
);
return loss_values[label];
}
void set_loss (
unsigned long label,
double value
)
{
// make sure requires clause is not broken
DLIB_ASSERT(label < num_labels() && value >= 0,
"\t void structural_sequence_labeling_trainer::set_loss()"
<< "\n\t invalid inputs were given to this function"
<< "\n\t label: " << label
<< "\n\t num_labels(): " << num_labels()
<< "\n\t value: " << value
<< "\n\t this: " << this
);
loss_values[label] = value;
}
const sequence_labeler<feature_extractor> train(
const std::vector<sample_sequence_type>& x,
const std::vector<labeled_sequence_type>& y
) const
{
// make sure requires clause is not broken
DLIB_ASSERT(is_sequence_labeling_problem(x,y) == true &&
contains_invalid_labeling(get_feature_extractor(), x, y) == false,
"\t sequence_labeler structural_sequence_labeling_trainer::train(x,y)"
<< "\n\t invalid inputs were given to this function"
<< "\n\t x.size(): " << x.size()
<< "\n\t is_sequence_labeling_problem(x,y): " << is_sequence_labeling_problem(x,y)
<< "\n\t contains_invalid_labeling(get_feature_extractor(),x,y): " << contains_invalid_labeling(get_feature_extractor(),x,y)
<< "\n\t this: " << this
);
#ifdef ENABLE_ASSERTS
for (unsigned long i = 0; i < y.size(); ++i)
{
for (unsigned long j = 0; j < y[i].size(); ++j)
{
// make sure requires clause is not broken
DLIB_ASSERT(y[i][j] < num_labels(),
"\t sequence_labeler structural_sequence_labeling_trainer::train(x,y)"
<< "\n\t The given labels in y are invalid."
<< "\n\t y[i][j]: " << y[i][j]
<< "\n\t num_labels(): " << num_labels()
<< "\n\t i: " << i
<< "\n\t j: " << j
<< "\n\t this: " << this
);
}
}
#endif
structural_svm_sequence_labeling_problem<feature_extractor> prob(x, y, fe, num_threads);
matrix<double,0,1> weights;
if (verbose)
prob.be_verbose();
prob.set_epsilon(eps);
prob.set_max_iterations(max_iterations);
prob.set_c(C);
prob.set_max_cache_size(max_cache_size);
for (unsigned long i = 0; i < loss_values.size(); ++i)
prob.set_loss(i,loss_values[i]);
solver(prob, weights, num_nonnegative_weights(fe));
return sequence_labeler<feature_extractor>(weights,fe);
}
private:
double C;
oca solver;
double eps;
unsigned long max_iterations;
bool verbose;
unsigned long num_threads;
unsigned long max_cache_size;
std::vector<double> loss_values;
void set_defaults ()
{
C = 100;
verbose = false;
eps = 0.1;
max_iterations = 10000;
num_threads = 2;
max_cache_size = 5;
loss_values.assign(num_labels(), 1);
}
feature_extractor fe;
};
// ----------------------------------------------------------------------------------------
}
#endif // DLIB_STRUCTURAL_SEQUENCE_LABELING_TRAiNER_Hh_
|
