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
|
#ifndef TH_GENERIC_FILE
#define TH_GENERIC_FILE "generic/RReLU.c"
#else
void THNN_(RReLU_updateOutput)(
THNNState *state,
THTensor *input,
THTensor *output,
THTensor *noise,
accreal lower_,
accreal upper_,
bool train,
bool inplace,
THGenerator *generator)
{
real lower = TH_CONVERT_ACCREAL_TO_REAL(lower_);
real upper = TH_CONVERT_ACCREAL_TO_REAL(upper_);
if (train)
{
// get default random generator
THTensor_(resizeAs)(noise, input);
if (inplace)
{
TH_TENSOR_APPLY2(real, input, real, noise,
if (*input_data <= 0)
{
const real r = (real)THRandom_uniform(generator, lower, upper);
*input_data = (*input_data) * r;
*noise_data = r;
}
else
{
*noise_data = 1;
}
);
THTensor_(set)(output, input);
}
else
{
THTensor_(resizeAs)(output, input);
TH_TENSOR_APPLY3(real, input, real, output, real, noise,
if (*input_data <= 0)
{
const real r = (real)THRandom_uniform(generator, lower, upper);
*output_data = (*input_data) * r;
*noise_data = r;
}
else
{
*output_data = *input_data;
*noise_data = 1;
}
);
}
}
else
{
const real negSlope = (lower + upper) / 2;
if (inplace)
{
TH_TENSOR_APPLY(real, input,
if (*input_data <= 0)
{
*input_data = *input_data * negSlope;
}
);
THTensor_(set)(output, input);
}
else
{
THTensor_(resizeAs)(output, input);
TH_TENSOR_APPLY2(real, input, real, output,
const real r = (*input_data) <= 0 ? negSlope : 1;
*output_data = *input_data * r;
);
}
}
}
void THNN_(RReLU_updateGradInput)(
THNNState *state,
THTensor *input,
THTensor *gradOutput,
THTensor *gradInput,
THTensor *noise,
accreal lower_,
accreal upper_,
bool train,
bool inplace)
{
real lower = TH_CONVERT_ACCREAL_TO_REAL(lower_);
real upper = TH_CONVERT_ACCREAL_TO_REAL(upper_);
THNN_CHECK_NELEMENT(input, gradOutput);
if (train && upper - lower > 1E-6) // e.g. if upper == lower, RReLU behaves like LeakyReLU
{
// multiply the gradient by the noise tensor
if (inplace)
{
THTensor_(cmul)(gradOutput, gradOutput, noise);
THTensor_(set)(gradInput, gradOutput);
}
else
{
THTensor_(resizeAs)(gradInput, input);
THTensor_(cmul)(gradInput, gradOutput, noise);
}
}
else
{
// use constant factor for negative input values
const real negSlope = (lower + upper) / 2;
if (inplace)
{
TH_TENSOR_APPLY2(real, gradOutput, real, input,
if (*input_data <= 0)
{
*gradOutput_data = (*gradOutput_data) * negSlope;
}
);
THTensor_(set)(gradInput, gradOutput);
}
else
{
THTensor_(resizeAs)(gradInput, input);
TH_TENSOR_APPLY3(real, gradInput, real, gradOutput, real, input,
*gradInput_data = (*input_data) <= 0 ? (*gradOutput_data) * negSlope : (*gradOutput_data);
);
}
}
}
#endif
|
