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
|
#ifndef TH_GENERIC_FILE
#define TH_GENERIC_FILE "generic/SparseLinear.c"
#else
static int nn_(SparseLinear_updateOutput)(lua_State *L)
{
long i;
THTensor * input = luaT_checkudata(L, 2, torch_(Tensor_id));
THTensor * weight = luaT_getfieldcheckudata(L, 1, "weight", torch_(Tensor_id));
THTensor * bias = luaT_getfieldcheckudata(L, 1, "bias", torch_(Tensor_id));
THTensor * output = luaT_getfieldcheckudata(L, 1, "output", torch_(Tensor_id));
long dim = weight->size[0]; /* number of weights.. */
THTensor_(copy)(output, bias);
for(i = 0; i < input->size[1]; i++)
{
long offset = (long)(THTensor_(get2d)(input, 0, i))-1;
if(offset >= 0 && offset < dim) /* make sure indices are in bounds.. */
{
real val = THTensor_(get2d)(input, 1, i);
THBlas_(axpy)(output->size[0],
val,
THTensor_(data)(weight)+offset*weight->stride[0],
weight->stride[1],
THTensor_(data)(output),
output->stride[0]);
}
else
luaL_error(L, "index out of bound");
}
return 1;
}
static int nn_(SparseLinear_accGradParameters)(lua_State *L)
{
long i;
THTensor * input = luaT_checkudata(L, 2, torch_(Tensor_id));
THTensor * gradOutput = luaT_checkudata(L, 3, torch_(Tensor_id));
real scale = luaL_optnumber(L, 4, 1);
THTensor * weight = luaT_getfieldcheckudata(L, 1, "weight", torch_(Tensor_id));
THTensor * gradBias = luaT_getfieldcheckudata(L, 1, "gradBias", torch_(Tensor_id));
THTensor * gradWeight = luaT_getfieldcheckudata(L, 1, "gradWeight", torch_(Tensor_id));
THTensor * lastInput = luaT_getfieldcheckudata(L, 1, "lastInput", torch_(Tensor_id));
real weightDecay = luaT_getfieldchecknumber(L, 1, "weightDecay");
long dim = gradWeight->size[0]; /* number of weights.. */
for(i = 0; i < input->size[1]; i++)
{
long offset = (long)(THTensor_(get2d)(input, 0, i))-1;
if(offset >= 0 && offset < dim) /* make sure indices are in bounds.. */
{
real val = scale*THTensor_(get2d)(input, 1, i);
THBlas_(scal)(gradOutput->size[0],
0,
THTensor_(data)(gradWeight)+offset*gradWeight->stride[0],
gradWeight->stride[1]); /* zero */
THBlas_(axpy)(gradOutput->size[0],
val,
THTensor_(data)(gradOutput),
gradOutput->stride[0],
THTensor_(data)(gradWeight)+offset*gradWeight->stride[0],
gradWeight->stride[1]);
}
else
luaL_error(L, "index out of bound");
}
THTensor_(cadd)(gradBias, gradBias, 1, gradOutput);
if(weightDecay != 0)
THTensor_(cadd)(gradWeight, gradWeight, weightDecay, weight);
THTensor_(resizeAs)(lastInput, input);
THTensor_(copy)(lastInput, input);
return 0;
}
int nn_(SparseLinear_updateParameters)(lua_State *L)
{
long i;
real learningRate = luaL_checknumber(L, 2);
THTensor * weight = luaT_getfieldcheckudata(L, 1, "weight", torch_(Tensor_id));
THTensor * bias = luaT_getfieldcheckudata(L, 1, "bias", torch_(Tensor_id));
THTensor * gradBias = luaT_getfieldcheckudata(L, 1, "gradBias", torch_(Tensor_id));
THTensor * gradWeight = luaT_getfieldcheckudata(L, 1, "gradWeight", torch_(Tensor_id));
THTensor * lastInput = luaT_getfieldcheckudata(L, 1, "lastInput", torch_(Tensor_id));
long dim = weight->size[0]; /* number of weights.. */
THTensor_(cadd)(bias, bias, -learningRate, gradBias);
for(i = 0; i < lastInput->size[1]; i++)
{
long offset = (long)(THTensor_(get2d)(lastInput, 0, i))-1;
if(offset >= 0 && offset < dim) /* make sure indices are in bounds.. */
{
THBlas_(axpy)(bias->size[0],
-learningRate,
THTensor_(data)(gradWeight)+offset*gradWeight->stride[0],
gradWeight->stride[1],
THTensor_(data)(weight)+offset*weight->stride[0],
weight->stride[1]);
}
else
luaL_error(L, "index out of bound");
}
return 0;
}
static const struct luaL_Reg nn_(SparseLinear__) [] = {
{"SparseLinear_updateOutput", nn_(SparseLinear_updateOutput)},
{"SparseLinear_accGradParameters", nn_(SparseLinear_accGradParameters)},
{"SparseLinear_updateParameters", nn_(SparseLinear_updateParameters)},
{NULL, NULL}
};
void nn_(SparseLinear_init)(lua_State *L)
{
luaT_pushmetaclass(L, torch_(Tensor_id));
luaT_registeratname(L, nn_(SparseLinear__), "nn");
lua_pop(L,1);
}
#endif
|
