blob: b5bedfa804e58b40324f38f84de2d8a09fb6a944 (
plain)
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
|
/*
This file is part of ct.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
General Public License for more details.
You should have received a copy of the GNU General Public License
along with ct. If not, see <https://www.gnu.org/licenses/>.
*/
#include "cnn1986.h"
#include "weights.h"
// ===================================================================
// Implementation of a small convolutional neural network
// ===================================================================
static float cur_board[5*5][KERN_CHAN];
static float flattened[CONV_NUM+2];
static float dense1[DENSE1_NUM];
static float dense2[DENSE2_NUM];
#define RELU(x) ((x) = ((x)<0)?0:(x))
float cnn1986_evaluate_black_win(void) {
/* --------------- *
* Populate input *
* --------------- */
for (unsigned int y = 0; y < board_size; y++) {
for (unsigned int x = 0; x < board_size; x++) {
const unsigned int loc = x+y*board_size;
const unsigned int count = COUNT_AT(loc);
colour_stack_t colour = colours[loc];
if (count > 0) {
float lookup = 0;
if (STONE_AT(loc) == STONE_STANDING) {
lookup = (colour & 1) ? +0.25 : -0.25;
} else if (STONE_AT(loc) == STONE_CAPSTONE) {
lookup = (colour & 1) ? +1.00 : -1.00;
} else {
lookup = (colour & 1) ? +0.50 : -0.50;
}
cur_board[loc][0] = lookup;
colour>>=1;
for (unsigned int c = 1; c < count && c < KERN_CHAN; c++, colour>>=1) {
cur_board[loc][c] = (colour & 1) ? +0.50 : -0.50;
}
for (unsigned int c = count; c < KERN_CHAN; c++) {
cur_board[loc][c] = 0;
}
} else {
for (unsigned int c = 0; c < KERN_CHAN; c++) {
cur_board[loc][c] = 0;
}
}
}
}
/* ------------------ *
* Convolution layer *
* ------------------ */
// for each kernel
for (unsigned int kern = 0; kern < KERN_NUM; kern++) {
// the stride is 1, march across the board
for (unsigned int bx = 0; bx < KERN_OSIZE; bx++) {
for (unsigned int by = 0; by < KERN_OSIZE; by++) {
flattened[kern+KERN_NUM*(bx+by*KERN_OSIZE)] =
conv2d_biases[kern];
// Compute the convolution for this position
for (unsigned int ky = 0; ky < KERN_SIZE; ky++) {
for (unsigned int kx = 0; kx < KERN_SIZE; kx++) {
for (unsigned int c = 0; c < KERN_CHAN; c++) {
// Where we are on the board
const unsigned int loc = kx+bx+(ky+by)*board_size;
flattened[kern+KERN_NUM*(bx+by*KERN_OSIZE)]
+= cur_board[loc][c]*conv2d_weights[kern][ky][kx][c];
}
}
}
RELU(flattened[kern+KERN_NUM*(bx+by*KERN_OSIZE)]);
}
}
}
// Add input of flat counts
flattened[CONV_NUM] = (float)(white_count & 127)/21.0;
flattened[CONV_NUM+1] = (float)(black_count & 127)/21.0;
/* ------------------ *
* First dense layer *
* ------------------ */
for (unsigned int d1 = 0; d1 < DENSE1_NUM; d1++) {
dense1[d1] = dense1_biases[d1];
for (unsigned int fl = 0; fl < CONV_NUM+2; fl++) {
dense1[d1] += flattened[fl]*dense1_weights[d1][fl];
}
RELU(dense1[d1]);
}
/* ------------------- *
* Second dense layer *
* ------------------- */
for (unsigned int d2 = 0; d2 < DENSE2_NUM; d2++) {
dense2[d2] = dense2_biases[d2];
for (unsigned int d1 = 0; d1 < DENSE1_NUM; d1++) {
dense2[d2] += dense1[d1]*dense2_weights[d2][d1];
}
RELU(dense2[d2]);
}
/* ------------- *
* Output layer *
* ------------- */
float output = output_bias;
for (unsigned int d2 = 0; d2 < DENSE2_NUM; d2++) {
output += dense2[d2]*output_weights[d2];
}
// 2*(clamped Pade approximant of logistic function) - 1
output = (12.0+output+50.0*output/(output*output+10.0))/12.0 - 1.0;
if (output > 1.0) {
return 1.0;
}
else if (output < -1.0) {
return -1.0;
}
return output;
}
|
