maxpool_layer.c
3.89 KB
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
#include "maxpool_layer.h"
#include "cuda.h"
#include <stdio.h>
image get_maxpool_image(maxpool_layer l)
{
int h = l.out_h;
int w = l.out_w;
int c = l.c;
return float_to_image(w,h,c,l.output);
}
image get_maxpool_delta(maxpool_layer l)
{
int h = l.out_h;
int w = l.out_w;
int c = l.c;
return float_to_image(w,h,c,l.delta);
}
maxpool_layer make_maxpool_layer(int batch, int h, int w, int c, int size, int stride, int padding)
{
maxpool_layer l = {0};
l.type = MAXPOOL;
l.batch = batch;
l.h = h;
l.w = w;
l.c = c;
l.pad = padding;
l.out_w = (w + padding - size)/stride + 1;
l.out_h = (h + padding - size)/stride + 1;
l.out_c = c;
l.outputs = l.out_h * l.out_w * l.out_c;
l.inputs = h*w*c;
l.size = size;
l.stride = stride;
int output_size = l.out_h * l.out_w * l.out_c * batch;
l.indexes = calloc(output_size, sizeof(int));
l.output = calloc(output_size, sizeof(float));
l.delta = calloc(output_size, sizeof(float));
l.forward = forward_maxpool_layer;
l.backward = backward_maxpool_layer;
#ifdef GPU
l.forward_gpu = forward_maxpool_layer_gpu;
l.backward_gpu = backward_maxpool_layer_gpu;
l.indexes_gpu = cuda_make_int_array(0, output_size);
l.output_gpu = cuda_make_array(l.output, output_size);
l.delta_gpu = cuda_make_array(l.delta, output_size);
#endif
fprintf(stderr, "max %d x %d / %d %4d x%4d x%4d -> %4d x%4d x%4d\n", size, size, stride, w, h, c, l.out_w, l.out_h, l.out_c);
return l;
}
void resize_maxpool_layer(maxpool_layer *l, int w, int h)
{
l->h = h;
l->w = w;
l->inputs = h*w*l->c;
l->out_w = (w + l->pad - l->size)/l->stride + 1;
l->out_h = (h + l->pad - l->size)/l->stride + 1;
l->outputs = l->out_w * l->out_h * l->c;
int output_size = l->outputs * l->batch;
l->indexes = realloc(l->indexes, output_size * sizeof(int));
l->output = realloc(l->output, output_size * sizeof(float));
l->delta = realloc(l->delta, output_size * sizeof(float));
#ifdef GPU
cuda_free((float *)l->indexes_gpu);
cuda_free(l->output_gpu);
cuda_free(l->delta_gpu);
l->indexes_gpu = cuda_make_int_array(0, output_size);
l->output_gpu = cuda_make_array(l->output, output_size);
l->delta_gpu = cuda_make_array(l->delta, output_size);
#endif
}
void forward_maxpool_layer(const maxpool_layer l, network net)
{
int b,i,j,k,m,n;
int w_offset = -l.pad/2;
int h_offset = -l.pad/2;
int h = l.out_h;
int w = l.out_w;
int c = l.c;
for(b = 0; b < l.batch; ++b){
for(k = 0; k < c; ++k){
for(i = 0; i < h; ++i){
for(j = 0; j < w; ++j){
int out_index = j + w*(i + h*(k + c*b));
float max = -FLT_MAX;
int max_i = -1;
for(n = 0; n < l.size; ++n){
for(m = 0; m < l.size; ++m){
int cur_h = h_offset + i*l.stride + n;
int cur_w = w_offset + j*l.stride + m;
int index = cur_w + l.w*(cur_h + l.h*(k + b*l.c));
int valid = (cur_h >= 0 && cur_h < l.h &&
cur_w >= 0 && cur_w < l.w);
float val = (valid != 0) ? net.input[index] : -FLT_MAX;
max_i = (val > max) ? index : max_i;
max = (val > max) ? val : max;
}
}
l.output[out_index] = max;
l.indexes[out_index] = max_i;
}
}
}
}
}
void backward_maxpool_layer(const maxpool_layer l, network net)
{
int i;
int h = l.out_h;
int w = l.out_w;
int c = l.c;
for(i = 0; i < h*w*c*l.batch; ++i){
int index = l.indexes[i];
net.delta[index] += l.delta[i];
}
}