detection_layer.c
9.96 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
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
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
#include "detection_layer.h"
#include "activations.h"
#include "softmax_layer.h"
#include "blas.h"
#include "box.h"
#include "cuda.h"
#include "utils.h"
#include <stdio.h>
#include <assert.h>
#include <string.h>
#include <stdlib.h>
detection_layer make_detection_layer(int batch, int inputs, int n, int side, int classes, int coords, int rescore)
{
detection_layer l = {0};
l.type = DETECTION;
l.n = n;
l.batch = batch;
l.inputs = inputs;
l.classes = classes;
l.coords = coords;
l.rescore = rescore;
l.side = side;
l.w = side;
l.h = side;
assert(side*side*((1 + l.coords)*l.n + l.classes) == inputs);
l.cost = calloc(1, sizeof(float));
l.outputs = l.inputs;
l.truths = l.side*l.side*(1+l.coords+l.classes);
l.output = calloc(batch*l.outputs, sizeof(float));
l.delta = calloc(batch*l.outputs, sizeof(float));
l.forward = forward_detection_layer;
l.backward = backward_detection_layer;
#ifdef GPU
l.forward_gpu = forward_detection_layer_gpu;
l.backward_gpu = backward_detection_layer_gpu;
l.output_gpu = cuda_make_array(l.output, batch*l.outputs);
l.delta_gpu = cuda_make_array(l.delta, batch*l.outputs);
#endif
fprintf(stderr, "Detection Layer\n");
srand(0);
return l;
}
void forward_detection_layer(const detection_layer l, network net)
{
int locations = l.side*l.side;
int i,j;
memcpy(l.output, net.input, l.outputs*l.batch*sizeof(float));
//if(l.reorg) reorg(l.output, l.w*l.h, size*l.n, l.batch, 1);
int b;
if (l.softmax){
for(b = 0; b < l.batch; ++b){
int index = b*l.inputs;
for (i = 0; i < locations; ++i) {
int offset = i*l.classes;
softmax(l.output + index + offset, l.classes, 1, 1,
l.output + index + offset);
}
}
}
if(net.train){
float avg_iou = 0;
float avg_cat = 0;
float avg_allcat = 0;
float avg_obj = 0;
float avg_anyobj = 0;
int count = 0;
*(l.cost) = 0;
int size = l.inputs * l.batch;
memset(l.delta, 0, size * sizeof(float));
for (b = 0; b < l.batch; ++b){
int index = b*l.inputs;
for (i = 0; i < locations; ++i) {
int truth_index = (b*locations + i)*(1+l.coords+l.classes);
int is_obj = net.truth[truth_index];
for (j = 0; j < l.n; ++j) {
int p_index = index + locations*l.classes + i*l.n + j;
l.delta[p_index] = l.noobject_scale*(0 - l.output[p_index]);
*(l.cost) += l.noobject_scale*pow(l.output[p_index], 2);
avg_anyobj += l.output[p_index];
}
int best_index = -1;
float best_iou = 0;
float best_rmse = 20;
if (!is_obj){
continue;
}
int class_index = index + i*l.classes;
for(j = 0; j < l.classes; ++j) {
l.delta[class_index+j] = l.class_scale * (net.truth[truth_index+1+j] - l.output[class_index+j]);
*(l.cost) += l.class_scale * pow(net.truth[truth_index+1+j] - l.output[class_index+j], 2);
if(net.truth[truth_index + 1 + j]) avg_cat += l.output[class_index+j];
avg_allcat += l.output[class_index+j];
}
box truth = float_to_box(net.truth + truth_index + 1 + l.classes, 1);
truth.x /= l.side;
truth.y /= l.side;
for(j = 0; j < l.n; ++j){
int box_index = index + locations*(l.classes + l.n) + (i*l.n + j) * l.coords;
box out = float_to_box(l.output + box_index, 1);
out.x /= l.side;
out.y /= l.side;
if (l.sqrt){
out.w = out.w*out.w;
out.h = out.h*out.h;
}
float iou = box_iou(out, truth);
//iou = 0;
float rmse = box_rmse(out, truth);
if(best_iou > 0 || iou > 0){
if(iou > best_iou){
best_iou = iou;
best_index = j;
}
}else{
if(rmse < best_rmse){
best_rmse = rmse;
best_index = j;
}
}
}
if(l.forced){
if(truth.w*truth.h < .1){
best_index = 1;
}else{
best_index = 0;
}
}
if(l.random && *(net.seen) < 64000){
best_index = rand()%l.n;
}
int box_index = index + locations*(l.classes + l.n) + (i*l.n + best_index) * l.coords;
int tbox_index = truth_index + 1 + l.classes;
box out = float_to_box(l.output + box_index, 1);
out.x /= l.side;
out.y /= l.side;
if (l.sqrt) {
out.w = out.w*out.w;
out.h = out.h*out.h;
}
float iou = box_iou(out, truth);
//printf("%d,", best_index);
int p_index = index + locations*l.classes + i*l.n + best_index;
*(l.cost) -= l.noobject_scale * pow(l.output[p_index], 2);
*(l.cost) += l.object_scale * pow(1-l.output[p_index], 2);
avg_obj += l.output[p_index];
l.delta[p_index] = l.object_scale * (1.-l.output[p_index]);
if(l.rescore){
l.delta[p_index] = l.object_scale * (iou - l.output[p_index]);
}
l.delta[box_index+0] = l.coord_scale*(net.truth[tbox_index + 0] - l.output[box_index + 0]);
l.delta[box_index+1] = l.coord_scale*(net.truth[tbox_index + 1] - l.output[box_index + 1]);
l.delta[box_index+2] = l.coord_scale*(net.truth[tbox_index + 2] - l.output[box_index + 2]);
l.delta[box_index+3] = l.coord_scale*(net.truth[tbox_index + 3] - l.output[box_index + 3]);
if(l.sqrt){
l.delta[box_index+2] = l.coord_scale*(sqrt(net.truth[tbox_index + 2]) - l.output[box_index + 2]);
l.delta[box_index+3] = l.coord_scale*(sqrt(net.truth[tbox_index + 3]) - l.output[box_index + 3]);
}
*(l.cost) += pow(1-iou, 2);
avg_iou += iou;
++count;
}
}
if(0){
float *costs = calloc(l.batch*locations*l.n, sizeof(float));
for (b = 0; b < l.batch; ++b) {
int index = b*l.inputs;
for (i = 0; i < locations; ++i) {
for (j = 0; j < l.n; ++j) {
int p_index = index + locations*l.classes + i*l.n + j;
costs[b*locations*l.n + i*l.n + j] = l.delta[p_index]*l.delta[p_index];
}
}
}
int indexes[100];
top_k(costs, l.batch*locations*l.n, 100, indexes);
float cutoff = costs[indexes[99]];
for (b = 0; b < l.batch; ++b) {
int index = b*l.inputs;
for (i = 0; i < locations; ++i) {
for (j = 0; j < l.n; ++j) {
int p_index = index + locations*l.classes + i*l.n + j;
if (l.delta[p_index]*l.delta[p_index] < cutoff) l.delta[p_index] = 0;
}
}
}
free(costs);
}
*(l.cost) = pow(mag_array(l.delta, l.outputs * l.batch), 2);
printf("Detection Avg IOU: %f, Pos Cat: %f, All Cat: %f, Pos Obj: %f, Any Obj: %f, count: %d\n", avg_iou/count, avg_cat/count, avg_allcat/(count*l.classes), avg_obj/count, avg_anyobj/(l.batch*locations*l.n), count);
//if(l.reorg) reorg(l.delta, l.w*l.h, size*l.n, l.batch, 0);
}
}
void backward_detection_layer(const detection_layer l, network net)
{
axpy_cpu(l.batch*l.inputs, 1, l.delta, 1, net.delta, 1);
}
void get_detection_detections(layer l, int w, int h, float thresh, detection *dets)
{
int i,j,n;
float *predictions = l.output;
//int per_cell = 5*num+classes;
for (i = 0; i < l.side*l.side; ++i){
int row = i / l.side;
int col = i % l.side;
for(n = 0; n < l.n; ++n){
int index = i*l.n + n;
int p_index = l.side*l.side*l.classes + i*l.n + n;
float scale = predictions[p_index];
int box_index = l.side*l.side*(l.classes + l.n) + (i*l.n + n)*4;
box b;
b.x = (predictions[box_index + 0] + col) / l.side * w;
b.y = (predictions[box_index + 1] + row) / l.side * h;
b.w = pow(predictions[box_index + 2], (l.sqrt?2:1)) * w;
b.h = pow(predictions[box_index + 3], (l.sqrt?2:1)) * h;
dets[index].bbox = b;
dets[index].objectness = scale;
for(j = 0; j < l.classes; ++j){
int class_index = i*l.classes;
float prob = scale*predictions[class_index+j];
dets[index].prob[j] = (prob > thresh) ? prob : 0;
}
}
}
}
#ifdef GPU
void forward_detection_layer_gpu(const detection_layer l, network net)
{
if(!net.train){
copy_gpu(l.batch*l.inputs, net.input_gpu, 1, l.output_gpu, 1);
return;
}
cuda_pull_array(net.input_gpu, net.input, l.batch*l.inputs);
forward_detection_layer(l, net);
cuda_push_array(l.output_gpu, l.output, l.batch*l.outputs);
cuda_push_array(l.delta_gpu, l.delta, l.batch*l.inputs);
}
void backward_detection_layer_gpu(detection_layer l, network net)
{
axpy_gpu(l.batch*l.inputs, 1, l.delta_gpu, 1, net.delta_gpu, 1);
//copy_gpu(l.batch*l.inputs, l.delta_gpu, 1, net.delta_gpu, 1);
}
#endif