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
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
| #include "yolo.h"
#include <opencv2/core/core.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <iostream>
static float fast_exp(float x)
{
union {
uint32_t i;
float f;
} v{};
v.i = (1 << 23) * (1.4426950409 * x + 126.93490512f);
return v.f;
}
static float sigmoid(float x)
{
return 1.0f / (1.0f + fast_exp(-x));
}
static float intersection_area(const Object& a, const Object& b)
{
cv::Rect_<float> inter = a.rect & b.rect;
return inter.area();
}
static void qsort_descent_inplace(std::vector<Object>& faceobjects, int left, int right)
{
int i = left;
int j = right;
float p = faceobjects[(left + right) / 2].prob;
while (i <= j)
{
while (faceobjects[i].prob > p)
i++;
while (faceobjects[j].prob < p)
j--;
if (i <= j)
{
std::swap(faceobjects[i], faceobjects[j]);
i++;
j--;
}
}
{
{
if (left < j) qsort_descent_inplace(faceobjects, left, j);
}
{
if (i < right) qsort_descent_inplace(faceobjects, i, right);
}
}
}
static void qsort_descent_inplace(std::vector<Object>& faceobjects)
{
if (faceobjects.empty())
return;
qsort_descent_inplace(faceobjects, 0, faceobjects.size() - 1);
}
static void nms_sorted_bboxes(const std::vector<Object>& faceobjects, std::vector<int>& picked, float nms_threshold)
{
picked.clear();
const int n = faceobjects.size();
std::vector<float> areas(n);
for (int i = 0; i < n; i++)
{
areas[i] = faceobjects[i].rect.width * faceobjects[i].rect.height;
}
for (int i = 0; i < n; i++)
{
const Object& a = faceobjects[i];
int keep = 1;
for (int j = 0; j < (int)picked.size(); j++)
{
const Object& b = faceobjects[picked[j]];
float inter_area = intersection_area(a, b);
float union_area = areas[i] + areas[picked[j]] - inter_area;
if (inter_area / union_area > nms_threshold)
keep = 0;
}
if (keep)
picked.push_back(i);
}
}
static void generate_grids_and_stride(const int target_w, const int target_h, std::vector<int>& strides, std::vector<GridAndStride>& grid_strides)
{
for (int i = 0; i < (int)strides.size(); i++)
{
int stride = strides[i];
int num_grid_w = target_w / stride;
int num_grid_h = target_h / stride;
for (int g1 = 0; g1 < num_grid_h; g1++)
{
for (int g0 = 0; g0 < num_grid_w; g0++)
{
GridAndStride gs;
gs.grid0 = g0;
gs.grid1 = g1;
gs.stride = stride;
grid_strides.push_back(gs);
}
}
}
}
static void generate_proposals(std::vector<GridAndStride> grid_strides, const ncnn::Mat& pred, float prob_threshold, std::vector<Object>& objects)
{
const int num_points = grid_strides.size();
const int num_class = 80;
const int reg_max_1 = 16;
for (int i = 0; i < num_points; i++)
{
const float* scores = pred.row(i) + 4 * reg_max_1;
int label = -1;
float score = -FLT_MAX;
for (int k = 0; k < num_class; k++)
{
float confidence = scores[k];
if (confidence > score)
{
label = k;
score = confidence;
}
}
float box_prob = sigmoid(score);
if (box_prob >= prob_threshold)
{
ncnn::Mat bbox_pred(reg_max_1, 4, (void*)pred.row(i));
{
ncnn::Layer* softmax = ncnn::create_layer("Softmax");
ncnn::ParamDict pd;
pd.set(0, 1);
pd.set(1, 1);
softmax->load_param(pd);
ncnn::Option opt;
opt.num_threads = 1;
opt.use_packing_layout = false;
softmax->create_pipeline(opt);
softmax->forward_inplace(bbox_pred, opt);
softmax->destroy_pipeline(opt);
delete softmax;
}
float pred_ltrb[4];
for (int k = 0; k < 4; k++)
{
float dis = 0.f;
const float* dis_after_sm = bbox_pred.row(k);
for (int l = 0; l < reg_max_1; l++)
{
dis += l * dis_after_sm[l];
}
pred_ltrb[k] = dis * grid_strides[i].stride;
}
float pb_cx = (grid_strides[i].grid0 + 0.5f) * grid_strides[i].stride;
float pb_cy = (grid_strides[i].grid1 + 0.5f) * grid_strides[i].stride;
float x0 = pb_cx - pred_ltrb[0];
float y0 = pb_cy - pred_ltrb[1];
float x1 = pb_cx + pred_ltrb[2];
float y1 = pb_cy + pred_ltrb[3];
Object obj;
obj.rect.x = x0;
obj.rect.y = y0;
obj.rect.width = x1 - x0;
obj.rect.height = y1 - y0;
obj.label = label;
obj.prob = box_prob;
objects.push_back(obj);
}
}
}
Yolo::Yolo()
{
blob_pool_allocator.set_size_compare_ratio(0.f);
workspace_pool_allocator.set_size_compare_ratio(0.f);
}
int Yolo::load(int _target_size, const float* _mean_vals, const float* _norm_vals, bool use_gpu)
{
;
yolo.opt = ncnn::Option();
yolo.load_param("yolov8n-op11.param");
yolo.load_model("yolov8n-op11.bin");
target_size = _target_size;
mean_vals[0] = _mean_vals[0];
mean_vals[1] = _mean_vals[1];
mean_vals[2] = _mean_vals[2];
norm_vals[0] = _norm_vals[0];
norm_vals[1] = _norm_vals[1];
norm_vals[2] = _norm_vals[2];
return 0;
}
int Yolo::detect(const cv::Mat& rgb, std::vector<Object>& objects, float prob_threshold, float nms_threshold)
{
int width = rgb.cols;
int height = rgb.rows;
int w = width;
int h = height;
float scale = 1.f;
if (w > h)
{
scale = (float)target_size / w;
w = target_size;
h = h * scale;
}
else
{
scale = (float)target_size / h;
h = target_size;
w = w * scale;
}
ncnn::Mat in = ncnn::Mat::from_pixels_resize(rgb.data, ncnn::Mat::PIXEL_RGB2BGR, width, height, w, h);
int wpad = (w + 31) / 32 * 32 - w;
int hpad = (h + 31) / 32 * 32 - h;
ncnn::Mat in_pad;
ncnn::copy_make_border(in, in_pad, hpad / 2, hpad - hpad / 2, wpad / 2, wpad - wpad / 2, ncnn::BORDER_CONSTANT, 0.f);
in_pad.substract_mean_normalize(0, norm_vals);
ncnn::Extractor ex = yolo.create_extractor();
ex.input("images", in_pad);
std::vector<Object> proposals;
ncnn::Mat out;
ex.extract("output0", out);
std::cout << "---------YES, " << out.dims << " width," << out.w << " height," << out.h << " , " << out.c << std::endl;
std::vector<int> strides = { 8, 16, 32 };
std::vector<GridAndStride> grid_strides;
generate_grids_and_stride(in_pad.w, in_pad.h, strides, grid_strides);
generate_proposals(grid_strides, out, prob_threshold, proposals);
qsort_descent_inplace(proposals);
std::vector<int> picked;
nms_sorted_bboxes(proposals, picked, nms_threshold);
int count = picked.size();
objects.resize(count);
for (int i = 0; i < count; i++)
{
objects[i] = proposals[picked[i]];
float x0 = (objects[i].rect.x - (wpad / 2)) / scale;
float y0 = (objects[i].rect.y - (hpad / 2)) / scale;
float x1 = (objects[i].rect.x + objects[i].rect.width - (wpad / 2)) / scale;
float y1 = (objects[i].rect.y + objects[i].rect.height - (hpad / 2)) / scale;
x0 = std::max(std::min(x0, (float)(width - 1)), 0.f);
y0 = std::max(std::min(y0, (float)(height - 1)), 0.f);
x1 = std::max(std::min(x1, (float)(width - 1)), 0.f);
y1 = std::max(std::min(y1, (float)(height - 1)), 0.f);
objects[i].rect.x = x0;
objects[i].rect.y = y0;
objects[i].rect.width = x1 - x0;
objects[i].rect.height = y1 - y0;
}
struct
{
bool operator()(const Object& a, const Object& b) const
{
return a.rect.area() > b.rect.area();
}
} objects_area_greater;
std::sort(objects.begin(), objects.end(), objects_area_greater);
return 0;
}
int Yolo::draw(cv::Mat& rgb, const std::vector<Object>& objects)
{
static const char* class_names[] = {
"person", "bicycle", "car", "motorcycle", "airplane", "bus", "train", "truck", "boat", "traffic light",
"fire hydrant", "stop sign", "parking meter", "bench", "bird", "cat", "dog", "horse", "sheep", "cow",
"elephant", "bear", "zebra", "giraffe", "backpack", "umbrella", "handbag", "tie", "suitcase", "frisbee",
"skis", "snowboard", "sports ball", "kite", "baseball bat", "baseball glove", "skateboard", "surfboard",
"tennis racket", "bottle", "wine glass", "cup", "fork", "knife", "spoon", "bowl", "banana", "apple",
"sandwich", "orange", "broccoli", "carrot", "hot dog", "pizza", "donut", "cake", "chair", "couch",
"potted plant", "bed", "dining table", "toilet", "tv", "laptop", "mouse", "remote", "keyboard", "cell phone",
"microwave", "oven", "toaster", "sink", "refrigerator", "book", "clock", "vase", "scissors", "teddy bear",
"hair drier", "toothbrush"
};
static const unsigned char colors[81][3] = {
{56, 0, 255},
{226, 255, 0},
{0, 94, 255},
{0, 37, 255},
{0, 255, 94},
{255, 226, 0},
{0, 18, 255},
{255, 151, 0},
{170, 0, 255},
{0, 255, 56},
{255, 0, 75},
{0, 75, 255},
{0, 255, 169},
{255, 0, 207},
{75, 255, 0},
{207, 0, 255},
{37, 0, 255},
{0, 207, 255},
{94, 0, 255},
{0, 255, 113},
{255, 18, 0},
{255, 0, 56},
{18, 0, 255},
{0, 255, 226},
{170, 255, 0},
{255, 0, 245},
{151, 255, 0},
{132, 255, 0},
{75, 0, 255},
{151, 0, 255},
{0, 151, 255},
{132, 0, 255},
{0, 255, 245},
{255, 132, 0},
{226, 0, 255},
{255, 37, 0},
{207, 255, 0},
{0, 255, 207},
{94, 255, 0},
{0, 226, 255},
{56, 255, 0},
{255, 94, 0},
{255, 113, 0},
{0, 132, 255},
{255, 0, 132},
{255, 170, 0},
{255, 0, 188},
{113, 255, 0},
{245, 0, 255},
{113, 0, 255},
{255, 188, 0},
{0, 113, 255},
{255, 0, 0},
{0, 56, 255},
{255, 0, 113},
{0, 255, 188},
{255, 0, 94},
{255, 0, 18},
{18, 255, 0},
{0, 255, 132},
{0, 188, 255},
{0, 245, 255},
{0, 169, 255},
{37, 255, 0},
{255, 0, 151},
{188, 0, 255},
{0, 255, 37},
{0, 255, 0},
{255, 0, 170},
{255, 0, 37},
{255, 75, 0},
{0, 0, 255},
{255, 207, 0},
{255, 0, 226},
{255, 245, 0},
{188, 255, 0},
{0, 255, 18},
{0, 255, 75},
{0, 255, 151},
{255, 56, 0},
{245, 255, 0}
};
int color_index = 0;
for (size_t i = 0; i < objects.size(); i++)
{
const Object& obj = objects[i];
const unsigned char* color = colors[color_index % 19];
color_index++;
cv::Scalar cc(color[0], color[1], color[2]);
cv::rectangle(rgb, obj.rect, cc, 2);
char text[256];
sprintf_s(text, "%s %.1f%%", class_names[obj.label], obj.prob * 100);
int baseLine = 0;
cv::Size label_size = cv::getTextSize(text, cv::FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
int x = obj.rect.x;
int y = obj.rect.y - label_size.height - baseLine;
if (y < 0)
y = 0;
if (x + label_size.width > rgb.cols)
x = rgb.cols - label_size.width;
cv::rectangle(rgb, cv::Rect(cv::Point(x, y), cv::Size(label_size.width, label_size.height + baseLine)), cc, -1);
cv::Scalar textcc = (color[0] + color[1] + color[2] >= 381) ? cv::Scalar(0, 0, 0) : cv::Scalar(255, 255, 255);
cv::putText(rgb, text, cv::Point(x, y + label_size.height), cv::FONT_HERSHEY_SIMPLEX, 0.5, textcc, 1);
}
cv::imshow("image", rgb);
cv::waitKey(0);
return 0;
}
|
对应的类别标签也要修改，大概370的位置
