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
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
|
// Adapted from interp.cpp from Caffe util by Pauline Luc
// Originally developed by George Papandreou
#ifndef TH_GENERIC_FILE
#define TH_GENERIC_FILE "generic/SpatialUpSamplingBilinear.c"
#else
static inline void THNN_(SpatialUpSamplingBilinear_shapeCheck)
(THTensor *input, THTensor *gradOutput,
int nBatch, int nChannels,
int inputHeight, int inputWidth,
int outputHeight, int outputWidth) {
THArgCheck(inputHeight > 0 && inputWidth > 0
&& outputHeight > 0 && outputWidth > 0, 2,
"input and output sizes should be greater than 0,"
" but got input (H: %d, W: %d) output (H: %d, W: %d)",
inputHeight, inputWidth, outputHeight, outputWidth);
if (input != NULL) {
THNN_ARGCHECK(input->nDimension == 4, 2, input,
"4D input tensor expected but got: %s");
}
if (gradOutput != NULL) {
THNN_CHECK_DIM_SIZE(gradOutput, 4, 0, nBatch);
THNN_CHECK_DIM_SIZE(gradOutput, 4, 1, nChannels);
THNN_CHECK_DIM_SIZE(gradOutput, 4, 2, outputHeight);
THNN_CHECK_DIM_SIZE(gradOutput, 4, 3, outputWidth);
}
}
void THNN_(SpatialUpSamplingBilinear_updateOutput)(
THNNState *state,
THTensor *input,
THTensor *output,
int outputHeight,
int outputWidth){
int nbatch = THTensor_(size)(input, 0);
int channels = THTensor_(size)(input, 1);
int inputHeight = THTensor_(size)(input, 2);
int inputWidth = THTensor_(size)(input, 3);
THNN_(SpatialUpSamplingBilinear_shapeCheck)
(input, NULL,
nbatch, channels,
inputHeight, inputWidth,
outputHeight, outputWidth);
input = THTensor_(newContiguous)(input);
THTensor_(resize4d)(output,
THTensor_(size)(input, 0),
THTensor_(size)(input, 1),
outputHeight, outputWidth);
THTensor_(zero)(output);
real *idata = THTensor_(data)(input);
real *odata = THTensor_(data)(output);
channels = nbatch * channels;
THAssert(inputHeight > 0 && inputWidth > 0 && outputHeight > 0 && outputWidth > 0);
// special case: just copy
if (inputHeight == outputHeight && inputWidth == outputWidth) {
for (int h2 = 0; h2 < outputHeight; ++h2) {
const int h1 = h2;
for (int w2 = 0; w2 < outputWidth; ++w2) {
const int w1 = w2;
const real* pos1 = &idata[h1 * inputWidth + w1];
real* pos2 = &odata[h2 * outputWidth + w2];
for (int c = 0; c < channels; ++c) {
pos2[0] = pos1[0];
pos1 += inputWidth * inputHeight;
pos2 += outputWidth * outputHeight;
}
}
}
return;
}
const float rheight =(outputHeight > 1) ? (float)(inputHeight - 1)/(outputHeight - 1) : 0.f;
const float rwidth = (outputWidth > 1) ? (float)(inputWidth - 1) / (outputWidth - 1) : 0.f;
for (int h2 = 0; h2 < outputHeight; ++h2) {
const float h1r = rheight * h2;
const int h1 = h1r;
const int h1p = (h1 < inputHeight - 1) ? 1 : 0;
const real h1lambda = h1r - h1;
const real h0lambda = (real)1. - h1lambda;
for (int w2 = 0; w2 < outputWidth; ++w2) {
const float w1r = rwidth * w2;
const int w1 = w1r;
const int w1p = (w1 < inputWidth - 1) ? 1 : 0;
const real w1lambda = w1r - w1;
const real w0lambda = (real)1. - w1lambda;
const real* pos1 = &idata[h1 * inputWidth + w1];
real* pos2 = &odata[h2 * outputWidth + w2];
for (int c = 0; c < channels; ++c) {
pos2[0] = h0lambda * (w0lambda * pos1[0]+ w1lambda * pos1[w1p])
+ h1lambda * (w0lambda * pos1[h1p * inputWidth]
+ w1lambda * pos1[h1p * inputWidth + w1p]);
pos1 += inputWidth * inputHeight;
pos2 += outputWidth * outputHeight;
}
}
}
THTensor_(free)(input);
}
void THNN_(SpatialUpSamplingBilinear_updateGradInput)(
THNNState *state,
THTensor *gradOutput,
THTensor *gradInput,
int nbatch,
int channels,
int inputHeight,
int inputWidth,
int outputHeight,
int outputWidth){
THNN_(SpatialUpSamplingBilinear_shapeCheck)
(NULL, gradOutput,
nbatch, channels,
inputHeight, inputWidth,
outputHeight, outputWidth);
THTensor_(resize4d)(gradInput, nbatch, channels, inputHeight, inputWidth);
THTensor_(zero)(gradInput);
gradOutput = THTensor_(newContiguous)(gradOutput);
real *data1 = THTensor_(data)(gradInput);
real *data2 = THTensor_(data)(gradOutput);
channels = nbatch * channels;
// special case: same-size matching grids
if (inputHeight == outputHeight && inputWidth == outputWidth) {
for (int h2 = 0; h2 < outputHeight; ++h2) {
const int h1 = h2;
for (int w2 = 0; w2 < outputWidth; ++w2) {
const int w1 = w2;
real* pos1 = &data1[h1 * inputWidth + w1];
const real* pos2 = &data2[h2 * outputWidth + w2];
for (int c = 0; c < channels; ++c) {
pos1[0] += pos2[0];
pos1 += inputWidth * inputHeight;
pos2 += outputWidth * outputHeight;
}
}
}
return;
}
const float rheight =(outputHeight > 1) ? (float)(inputHeight - 1)/(outputHeight - 1) : 0.f;
const float rwidth = (outputWidth > 1) ? (float)(inputWidth - 1)/(outputWidth - 1) : 0.f;
for (int h2 = 0; h2 < outputHeight; ++h2) {
const float h1r = rheight * h2;
const int h1 = h1r;
const int h1p = (h1 < inputHeight - 1) ? 1 : 0;
const real h1lambda = h1r - h1;
const real h0lambda = (real)1. - h1lambda;
for (int w2 = 0; w2 < outputWidth; ++w2) {
const float w1r = rwidth * w2;
const int w1 = w1r;
const int w1p = (w1 < inputWidth - 1) ? 1 : 0;
const real w1lambda = w1r - w1;
const real w0lambda = (real)1. - w1lambda;
real* pos1 = &data1[h1 * inputWidth + w1];
const real* pos2 = &data2[h2 * outputWidth + w2];
for (int c = 0; c < channels; ++c) {
pos1[0] += h0lambda * w0lambda * pos2[0];
pos1[w1p] += h0lambda * w1lambda * pos2[0];
pos1[h1p * inputWidth] += h1lambda * w0lambda * pos2[0];
pos1[h1p * inputWidth + w1p] += h1lambda * w1lambda * pos2[0];
pos1 += inputWidth * inputHeight;
pos2 += outputWidth * outputHeight;
}
}
}
THTensor_(free)(gradOutput);
}
#endif
|
