shortcut_layer.c
2.87 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
#include "shortcut_layer.h"
#include "cuda.h"
#include "blas.h"
#include "activations.h"
#include <stdio.h>
#include <assert.h>
layer make_shortcut_layer(int batch, int index, int w, int h, int c, int w2, int h2, int c2)
{
fprintf(stderr, "res %3d %4d x%4d x%4d -> %4d x%4d x%4d\n",index, w2,h2,c2, w,h,c);
layer l = {0};
l.type = SHORTCUT;
l.batch = batch;
l.w = w2;
l.h = h2;
l.c = c2;
l.out_w = w;
l.out_h = h;
l.out_c = c;
l.outputs = w*h*c;
l.inputs = l.outputs;
l.index = index;
l.delta = calloc(l.outputs*batch, sizeof(float));
l.output = calloc(l.outputs*batch, sizeof(float));;
l.forward = forward_shortcut_layer;
l.backward = backward_shortcut_layer;
#ifdef GPU
l.forward_gpu = forward_shortcut_layer_gpu;
l.backward_gpu = backward_shortcut_layer_gpu;
l.delta_gpu = cuda_make_array(l.delta, l.outputs*batch);
l.output_gpu = cuda_make_array(l.output, l.outputs*batch);
#endif
return l;
}
void resize_shortcut_layer(layer *l, int w, int h)
{
assert(l->w == l->out_w);
assert(l->h == l->out_h);
l->w = l->out_w = w;
l->h = l->out_h = h;
l->outputs = w*h*l->out_c;
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_shortcut_layer(const layer l, network net)
{
copy_cpu(l.outputs*l.batch, net.input, 1, l.output, 1);
shortcut_cpu(l.batch, l.w, l.h, l.c, net.layers[l.index].output, l.out_w, l.out_h, l.out_c, l.alpha, l.beta, l.output);
activate_array(l.output, l.outputs*l.batch, l.activation);
}
void backward_shortcut_layer(const layer l, network net)
{
gradient_array(l.output, l.outputs*l.batch, l.activation, l.delta);
axpy_cpu(l.outputs*l.batch, l.alpha, l.delta, 1, net.delta, 1);
shortcut_cpu(l.batch, l.out_w, l.out_h, l.out_c, l.delta, l.w, l.h, l.c, 1, l.beta, net.layers[l.index].delta);
}
#ifdef GPU
void forward_shortcut_layer_gpu(const layer l, network net)
{
copy_gpu(l.outputs*l.batch, net.input_gpu, 1, l.output_gpu, 1);
shortcut_gpu(l.batch, l.w, l.h, l.c, net.layers[l.index].output_gpu, l.out_w, l.out_h, l.out_c, l.alpha, l.beta, l.output_gpu);
activate_array_gpu(l.output_gpu, l.outputs*l.batch, l.activation);
}
void backward_shortcut_layer_gpu(const layer l, network net)
{
gradient_array_gpu(l.output_gpu, l.outputs*l.batch, l.activation, l.delta_gpu);
axpy_gpu(l.outputs*l.batch, l.alpha, l.delta_gpu, 1, net.delta_gpu, 1);
shortcut_gpu(l.batch, l.out_w, l.out_h, l.out_c, l.delta_gpu, l.w, l.h, l.c, 1, l.beta, net.layers[l.index].delta_gpu);
}
#endif