route_layer.c
3.84 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
128
129
130
131
132
133
134
#include "route_layer.h"
#include "cuda.h"
#include "blas.h"
#include <stdio.h>
route_layer make_route_layer(int batch, int n, int *input_layers, int *input_sizes)
{
fprintf(stderr,"route ");
route_layer l = {0};
l.type = ROUTE;
l.batch = batch;
l.n = n;
l.input_layers = input_layers;
l.input_sizes = input_sizes;
int i;
int outputs = 0;
for(i = 0; i < n; ++i){
fprintf(stderr," %d", input_layers[i]);
outputs += input_sizes[i];
}
fprintf(stderr, "\n");
l.outputs = outputs;
l.inputs = outputs;
l.delta = calloc(outputs*batch, sizeof(float));
l.output = calloc(outputs*batch, sizeof(float));;
l.forward = forward_route_layer;
l.backward = backward_route_layer;
#ifdef GPU
l.forward_gpu = forward_route_layer_gpu;
l.backward_gpu = backward_route_layer_gpu;
l.delta_gpu = cuda_make_array(l.delta, outputs*batch);
l.output_gpu = cuda_make_array(l.output, outputs*batch);
#endif
return l;
}
void resize_route_layer(route_layer *l, network *net)
{
int i;
layer first = net->layers[l->input_layers[0]];
l->out_w = first.out_w;
l->out_h = first.out_h;
l->out_c = first.out_c;
l->outputs = first.outputs;
l->input_sizes[0] = first.outputs;
for(i = 1; i < l->n; ++i){
int index = l->input_layers[i];
layer next = net->layers[index];
l->outputs += next.outputs;
l->input_sizes[i] = next.outputs;
if(next.out_w == first.out_w && next.out_h == first.out_h){
l->out_c += next.out_c;
}else{
printf("%d %d, %d %d\n", next.out_w, next.out_h, first.out_w, first.out_h);
l->out_h = l->out_w = l->out_c = 0;
}
}
l->inputs = l->outputs;
l->delta = realloc(l->delta, l->outputs*l->batch*sizeof(float));
l->output = realloc(l->output, l->outputs*l->batch*sizeof(float));
#ifdef GPU
cuda_free(l->output_gpu);
cuda_free(l->delta_gpu);
l->output_gpu = cuda_make_array(l->output, l->outputs*l->batch);
l->delta_gpu = cuda_make_array(l->delta, l->outputs*l->batch);
#endif
}
void forward_route_layer(const route_layer l, network net)
{
int i, j;
int offset = 0;
for(i = 0; i < l.n; ++i){
int index = l.input_layers[i];
float *input = net.layers[index].output;
int input_size = l.input_sizes[i];
for(j = 0; j < l.batch; ++j){
copy_cpu(input_size, input + j*input_size, 1, l.output + offset + j*l.outputs, 1);
}
offset += input_size;
}
}
void backward_route_layer(const route_layer l, network net)
{
int i, j;
int offset = 0;
for(i = 0; i < l.n; ++i){
int index = l.input_layers[i];
float *delta = net.layers[index].delta;
int input_size = l.input_sizes[i];
for(j = 0; j < l.batch; ++j){
axpy_cpu(input_size, 1, l.delta + offset + j*l.outputs, 1, delta + j*input_size, 1);
}
offset += input_size;
}
}
#ifdef GPU
void forward_route_layer_gpu(const route_layer l, network net)
{
int i, j;
int offset = 0;
for(i = 0; i < l.n; ++i){
int index = l.input_layers[i];
float *input = net.layers[index].output_gpu;
int input_size = l.input_sizes[i];
for(j = 0; j < l.batch; ++j){
copy_gpu(input_size, input + j*input_size, 1, l.output_gpu + offset + j*l.outputs, 1);
}
offset += input_size;
}
}
void backward_route_layer_gpu(const route_layer l, network net)
{
int i, j;
int offset = 0;
for(i = 0; i < l.n; ++i){
int index = l.input_layers[i];
float *delta = net.layers[index].delta_gpu;
int input_size = l.input_sizes[i];
for(j = 0; j < l.batch; ++j){
axpy_gpu(input_size, 1, l.delta_gpu + offset + j*l.outputs, 1, delta + j*input_size, 1);
}
offset += input_size;
}
}
#endif