File: svm_nu_trainer_abstract.h

package info (click to toggle)
mldemos 0.5.1-3
  • links: PTS, VCS
  • area: main
  • in suites: jessie, jessie-kfreebsd
  • size: 32,224 kB
  • ctags: 46,525
  • sloc: cpp: 306,887; ansic: 167,718; ml: 126; sh: 109; makefile: 2
file content (210 lines) | stat: -rw-r--r-- 6,860 bytes parent folder | download | duplicates (4)
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
// Copyright (C) 2007  Davis E. King (davis@dlib.net)
// License: Boost Software License   See LICENSE.txt for the full license.
#undef DLIB_SVm_NU_TRAINER_ABSTRACT_
#ifdef DLIB_SVm_NU_TRAINER_ABSTRACT_

#include <cmath>
#include <limits>
#include <sstream>
#include "../matrix/matrix_abstract.h"
#include "../algs.h"
#include "../serialize.h"
#include "function_abstract.h"
#include "kernel_abstract.h"
#include "../optimization/optimization_solve_qp2_using_smo_abstract.h"

namespace dlib
{

// ----------------------------------------------------------------------------------------

    template <
        typename K 
        >
    class svm_nu_trainer
    {
        /*!
            REQUIREMENTS ON K 
                is a kernel function object as defined in dlib/svm/kernel_abstract.h 

            WHAT THIS OBJECT REPRESENTS
                This object implements a trainer for a nu support vector machine for 
                solving binary classification problems.  It is implemented using the SMO
                algorithm.

                The implementation of the nu-svm training algorithm used by this object is based
                on the following excellent papers:
                    - Chang and Lin, Training {nu}-Support Vector Classifiers: Theory and Algorithms
                    - Chih-Chung Chang and Chih-Jen Lin, LIBSVM : a library for support vector 
                      machines, 2001. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm

        !*/

    public:
        typedef K kernel_type;
        typedef typename kernel_type::scalar_type scalar_type;
        typedef typename kernel_type::sample_type sample_type;
        typedef typename kernel_type::mem_manager_type mem_manager_type;
        typedef decision_function<kernel_type> trained_function_type;

        svm_nu_trainer (
        );
        /*!
            ensures
                - This object is properly initialized and ready to be used
                  to train a support vector machine.
                - #get_nu() == 0.1 
                - #get_cache_size() == 200
                - #get_epsilon() == 0.001
        !*/

        svm_nu_trainer (
            const kernel_type& kernel, 
            const scalar_type& nu
        );
        /*!
            requires
                - 0 < nu <= 1
            ensures
                - This object is properly initialized and ready to be used
                  to train a support vector machine.
                - #get_kernel() == kernel
                - #get_nu() == nu
                - #get_cache_size() == 200
                - #get_epsilon() == 0.001
        !*/

        void set_cache_size (
            long cache_size
        );
        /*!
            requires
                - cache_size > 0
            ensures
                - #get_cache_size() == cache_size 
        !*/

        const long get_cache_size (
        ) const;
        /*!
            ensures
                - returns the number of megabytes of cache this object will use
                  when it performs training via the this->train() function.
                  (bigger values of this may make training go faster but won't affect 
                  the result.  However, too big a value will cause you to run out of 
                  memory, obviously.)
        !*/

        void set_epsilon (
            scalar_type eps
        );
        /*!
            requires
                - eps > 0
            ensures
                - #get_epsilon() == eps 
        !*/

        const scalar_type get_epsilon (
        ) const;
        /*!
            ensures
                - returns the error epsilon that determines when training should stop.
                  Generally a good value for this is 0.001.  Smaller values may result
                  in a more accurate solution but take longer to execute.
        !*/

        void set_kernel (
            const kernel_type& k
        );
        /*!
            ensures
                - #get_kernel() == k 
        !*/

        const kernel_type& get_kernel (
        ) const;
        /*!
            ensures
                - returns a copy of the kernel function in use by this object
        !*/

        void set_nu (
            scalar_type nu
        );
        /*!
            requires
                - 0 < nu <= 1
            ensures
                - #get_nu() == nu
        !*/

        const scalar_type get_nu (
        ) const;
        /*!
            ensures
                - returns the nu svm parameter.  This is a value between 0 and
                  1.  It is the parameter that determines the trade off between
                  trying to fit the training data exactly or allowing more errors 
                  but hopefully improving the generalization ability of the 
                  resulting classifier.  Smaller values encourage exact fitting 
                  while larger values of nu may encourage better generalization. 
                  For more information you should consult the papers referenced 
                  above.
        !*/

        template <
            typename in_sample_vector_type,
            typename in_scalar_vector_type
            >
        const decision_function<kernel_type> train (
            const in_sample_vector_type& x,
            const in_scalar_vector_type& y
        ) const;
        /*!
            requires
                - is_binary_classification_problem(x,y) == true
                - x == a matrix or something convertible to a matrix via vector_to_matrix().
                  Also, x should contain sample_type objects.
                - y == a matrix or something convertible to a matrix via vector_to_matrix().
                  Also, y should contain scalar_type objects.
            ensures
                - trains a nu support vector classifier given the training samples in x and 
                  labels in y.  Training is done when the error is less than get_epsilon().
                - returns a decision function F with the following properties:
                    - if (new_x is a sample predicted have +1 label) then
                        - F(new_x) >= 0
                    - else
                        - F(new_x) < 0
            throws
                - invalid_nu_error
                  This exception is thrown if get_nu() >= maximum_nu(y)
                - std::bad_alloc
        !*/

        void swap (
            svm_nu_trainer& item
        );
        /*!
            ensures
                - swaps *this and item
        !*/
    }; 

    template <typename K>
    void swap (
        svm_nu_trainer<K>& a,
        svm_nu_trainer<K>& b
    ) { a.swap(b); }
    /*!
        provides a global swap
    !*/

// ----------------------------------------------------------------------------------------

}

#endif // DLIB_SVm_NU_TRAINER_ABSTRACT_