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
|
/*
Copyright (c) 2013, Taiga Nomi
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the <organization> nor the
names of its contributors may be used to endorse or promote products
derived from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY
EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include <iostream>
#include "tiny_dnn/tiny_dnn.h"
using namespace tiny_dnn;
using namespace tiny_dnn::activation;
void construct_net(network<sequential>& nn) {
// connection table [Y.Lecun, 1998 Table.1]
#define O true
#define X false
static const bool tbl[] = {
O, X, X, X, O, O, O, X, X, O, O, O, O, X, O, O,
O, O, X, X, X, O, O, O, X, X, O, O, O, O, X, O,
O, O, O, X, X, X, O, O, O, X, X, O, X, O, O, O,
X, O, O, O, X, X, O, O, O, O, X, X, O, X, O, O,
X, X, O, O, O, X, X, O, O, O, O, X, O, O, X, O,
X, X, X, O, O, O, X, X, O, O, O, O, X, O, O, O
};
#undef O
#undef X
core::backend_t backend_type = core::backend_t::internal;
// construct nets
//
// C : convolution
// S : sub-sampling
// F : fully connected
nn << quantized_convolutional_layer<tan_h>(32, 32, 5, 1, 6, // C1, 1@32x32-in, 6@28x28-out
padding::valid, true, 1, 1, backend_type)
<< average_pooling_layer<tan_h>(28, 28, 6, 2) // S2, 6@28x28-in, 6@14x14-out
<< quantized_convolutional_layer<tan_h>(14, 14, 5, 6, 16, // C3, 6@14x14-in, 16@10x10-in
connection_table(tbl, 6, 16),
padding::valid, true, 1, 1, backend_type)
<< average_pooling_layer<tan_h>(10, 10, 16, 2) // S4, 16@10x10-in, 16@5x5-out
<< quantized_convolutional_layer<tan_h>(5, 5, 5, 16, 120, // C5, 16@5x5-in, 120@1x1-out
padding::valid, true, 1, 1, backend_type)
<< quantized_fully_connected_layer<tan_h>(120, 10, // F6, 120-in, 10-out
true, backend_type)
;
}
static void train_lenet(const std::string& data_dir_path) {
// specify loss-function and learning strategy
network<sequential> nn;
adagrad optimizer;
construct_net(nn);
std::cout << "load models..." << std::endl;
// load MNIST dataset
std::vector<label_t> train_labels, test_labels;
std::vector<vec_t> train_images, test_images;
parse_mnist_labels(data_dir_path + "/train-labels.idx1-ubyte",
&train_labels);
parse_mnist_images(data_dir_path + "/train-images.idx3-ubyte",
&train_images, -1.0, 1.0, 2, 2);
parse_mnist_labels(data_dir_path + "/t10k-labels.idx1-ubyte",
&test_labels);
parse_mnist_images(data_dir_path + "/t10k-images.idx3-ubyte",
&test_images, -1.0, 1.0, 2, 2);
std::cout << "start training" << std::endl;
progress_display disp(static_cast<unsigned long>(train_images.size()));
timer t;
int minibatch_size = 10;
int num_epochs = 30;
optimizer.alpha *= static_cast<tiny_dnn::float_t>(std::sqrt(minibatch_size));
// create callback
auto on_enumerate_epoch = [&](){
std::cout << t.elapsed() << "s elapsed." << std::endl;
tiny_dnn::result res = nn.test(test_images, test_labels);
std::cout << res.num_success << "/" << res.num_total << std::endl;
disp.restart(static_cast<unsigned long>(train_images.size()));
t.restart();
};
auto on_enumerate_minibatch = [&](){
disp += minibatch_size;
};
// training
nn.train<mse>(optimizer, train_images, train_labels, minibatch_size, num_epochs,
on_enumerate_minibatch, on_enumerate_epoch);
std::cout << "end training." << std::endl;
// test and show results
nn.test(test_images, test_labels).print_detail(std::cout);
// save network model & trained weights
nn.save("LeNet-model");
}
int main(int argc, char **argv) {
if (argc != 2) {
std::cerr << "Usage : " << argv[0]
<< " path_to_data (example:../data)" << std::endl;
return -1;
}
train_lenet(argv[1]);
return 0;
}
|
