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
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
|
#ifndef TH_GENERIC_FILE
#define TH_GENERIC_FILE "generic/SpatialMaxUnpooling.c"
#else
static void THNN_(SpatialMaxUnpooling_updateOutput_frame)(real *input_p, real *output_p,
THIndex_t *ind_p,
int nslices,
int iwidth, int iheight,
int owidth, int oheight)
{
int k;
int has_error = 0;
THIndex_t error_index;
#pragma omp parallel for private(k)
for (k = 0; k < nslices; k++)
{
real *output_p_k = output_p + k*owidth*oheight;
real *input_p_k = input_p + k*iwidth*iheight;
THIndex_t *ind_p_k = ind_p + k*iwidth*iheight;
int i, j;
THIndex_t maxp;
for(i = 0; i < iheight; i++)
{
for(j = 0; j < iwidth; j++)
{
maxp = ind_p_k[i*iwidth + j] - TH_INDEX_BASE; /* retrieve position of max */
if(maxp<0 || maxp>=owidth*oheight){
#pragma omp critical
{
has_error = 1;
error_index = maxp;
}
} else {
output_p_k[maxp] = input_p_k[i*iwidth + j]; /* update output */
}
}
}
}
if (has_error) {
THError("found an invalid max index %ld (output volumes are of size %dx%d)",
error_index, oheight, owidth);
}
}
void THNN_(SpatialMaxUnpooling_updateOutput)(
THNNState *state,
THTensor *input,
THTensor *output,
THIndexTensor *indices,
int owidth, int oheight)
{
int dimw = 2;
int dimh = 1;
int nbatch = 1;
int nslices;
int iheight;
int iwidth;
real *input_data;
real *output_data;
THIndex_t *indices_data;
THNN_ARGCHECK(input->nDimension == 3 || input->nDimension == 4, 2, input,
"3D or 4D (batch mode) tensor expected for input, but got: %s");
THNN_CHECK_SHAPE_INDICES(input, indices);
if (input->nDimension == 4)
{
nbatch = input->size[0];
dimw++;
dimh++;
}
/* sizes */
nslices = input->size[dimh-1];
iheight = input->size[dimh];
iwidth = input->size[dimw];
/* get contiguous input and indices */
input = THTensor_(newContiguous)(input);
indices = THIndexTensor_(newContiguous)(indices);
/* resize output */
if (input->nDimension == 3)
{
THTensor_(resize3d)(output, nslices, oheight, owidth);
THTensor_(zero)(output);
input_data = THTensor_(data)(input);
output_data = THTensor_(data)(output);
indices_data = THIndexTensor_(data)(indices);
THNN_(SpatialMaxUnpooling_updateOutput_frame)(input_data, output_data,
indices_data,
nslices,
iwidth, iheight,
owidth, oheight);
}
else
{
int p;
THTensor_(resize4d)(output, nbatch, nslices, oheight, owidth);
THTensor_(zero)(output);
input_data = THTensor_(data)(input);
output_data = THTensor_(data)(output);
indices_data = THIndexTensor_(data)(indices);
for (p = 0; p < nbatch; p++)
{
THNN_(SpatialMaxUnpooling_updateOutput_frame)(
input_data+p*nslices*iwidth*iheight,
output_data+p*nslices*owidth*oheight,
indices_data+p*nslices*iwidth*iheight,
nslices,
iwidth, iheight,
owidth, oheight);
}
}
/* cleanup */
THTensor_(free)(input);
THIndexTensor_(free)(indices);
}
static void THNN_(SpatialMaxUnpooling_updateGradInput_frame)(real *gradInput_p, real *gradOutput_p,
THIndex_t *ind_p,
int nslices,
int iwidth, int iheight,
int owidth, int oheight)
{
int k;
#pragma omp parallel for private(k)
for (k = 0; k < nslices; k++)
{
real *gradInput_p_k = gradInput_p + k*iwidth*iheight;
real *gradOutput_p_k = gradOutput_p + k*owidth*oheight;
THIndex_t *ind_p_k = ind_p + k*iwidth*iheight;
int i, j;
THIndex_t maxp;
for(i = 0; i < iheight; i++)
{
for(j = 0; j < iwidth; j++)
{
maxp = ind_p_k[i*iwidth + j] - TH_INDEX_BASE; /* retrieve position of max */
if(maxp < 0 || maxp >= owidth * oheight) {
THError("invalid max index %ld, owidth= %d, oheight= %d", maxp, owidth, oheight);
}
gradInput_p_k[i*iwidth + j] = gradOutput_p_k[maxp]; /* update gradient */
}
}
}
}
void THNN_(SpatialMaxUnpooling_updateGradInput)(
THNNState *state,
THTensor *input,
THTensor *gradOutput,
THTensor *gradInput,
THIndexTensor *indices,
int owidth, int oheight)
{
int dimw = 2;
int dimh = 1;
int nbatch = 1;
int nslices;
int iheight;
int iwidth;
real *gradInput_data;
real *gradOutput_data;
THIndex_t *indices_data;
THNN_CHECK_SHAPE_INDICES(input, indices);
/* get contiguous gradOutput and indices */
gradOutput = THTensor_(newContiguous)(gradOutput);
indices = THIndexTensor_(newContiguous)(indices);
/* resize */
THTensor_(resizeAs)(gradInput, input);
THTensor_(zero)(gradInput);
if (input->nDimension == 4) {
nbatch = input->size[0];
dimw++;
dimh++;
}
/* sizes */
nslices = input->size[dimh-1];
iheight = input->size[dimh];
iwidth = input->size[dimw];
if(owidth!=gradOutput->size[dimw] || oheight!=gradOutput->size[dimh]){
THError("Inconsistent gradOutput size. oheight= %d, owidth= %d, gradOutput: %dx%d",
oheight, owidth, gradOutput->size[dimh], gradOutput->size[dimw]);
}
/* get raw pointers */
gradInput_data = THTensor_(data)(gradInput);
gradOutput_data = THTensor_(data)(gradOutput);
indices_data = THIndexTensor_(data)(indices);
/* backprop */
if (input->nDimension == 3)
{
THNN_(SpatialMaxUnpooling_updateGradInput_frame)(gradInput_data, gradOutput_data,
indices_data,
nslices,
iwidth, iheight,
owidth, oheight);
}
else
{
int p;
for (p = 0; p < nbatch; p++)
{
THNN_(SpatialMaxUnpooling_updateGradInput_frame)(gradInput_data+p*nslices*iwidth*iheight, gradOutput_data+p*nslices*owidth*oheight,
indices_data+p*nslices*iwidth*iheight,
nslices,
iwidth, iheight,
owidth, oheight);
}
}
/* cleanup */
THTensor_(free)(gradOutput);
THIndexTensor_(free)(indices);
}
#endif
|
