thesergiu commited on
Commit
f449550
1 Parent(s): dbe1e43

Yolo v7 weights and cfg

Browse files
Files changed (4) hide show
  1. .gitattributes +1 -0
  2. coco.names +80 -0
  3. yolov7.cfg +1024 -0
  4. yolov7.weights +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ yolov7.weights filter=lfs diff=lfs merge=lfs -text
coco.names ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ person
2
+ bicycle
3
+ car
4
+ motorbike
5
+ aeroplane
6
+ bus
7
+ train
8
+ truck
9
+ boat
10
+ traffic light
11
+ fire hydrant
12
+ stop sign
13
+ parking meter
14
+ bench
15
+ bird
16
+ cat
17
+ dog
18
+ horse
19
+ sheep
20
+ cow
21
+ elephant
22
+ bear
23
+ zebra
24
+ giraffe
25
+ backpack
26
+ umbrella
27
+ handbag
28
+ tie
29
+ suitcase
30
+ frisbee
31
+ skis
32
+ snowboard
33
+ sports ball
34
+ kite
35
+ baseball bat
36
+ baseball glove
37
+ skateboard
38
+ surfboard
39
+ tennis racket
40
+ bottle
41
+ wine glass
42
+ cup
43
+ fork
44
+ knife
45
+ spoon
46
+ bowl
47
+ banana
48
+ apple
49
+ sandwich
50
+ orange
51
+ broccoli
52
+ carrot
53
+ hot dog
54
+ pizza
55
+ donut
56
+ cake
57
+ chair
58
+ sofa
59
+ pottedplant
60
+ bed
61
+ diningtable
62
+ toilet
63
+ tvmonitor
64
+ laptop
65
+ mouse
66
+ remote
67
+ keyboard
68
+ cell phone
69
+ microwave
70
+ oven
71
+ toaster
72
+ sink
73
+ refrigerator
74
+ book
75
+ clock
76
+ vase
77
+ scissors
78
+ teddy bear
79
+ hair drier
80
+ toothbrush
yolov7.cfg ADDED
@@ -0,0 +1,1024 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [net]
2
+ # Testing
3
+ #batch=1
4
+ #subdivisions=1
5
+ # Training
6
+ batch=8
7
+ subdivisions=1
8
+ width=640
9
+ height=640
10
+ channels=3
11
+ momentum=0.9
12
+ decay=0.0005
13
+ angle=0
14
+ saturation = 1.5
15
+ exposure = 1.5
16
+ hue=.1
17
+
18
+ learning_rate=0.00261
19
+ burn_in=1000
20
+
21
+ max_batches = 2000200
22
+ policy=steps
23
+ steps=1600000,1800000
24
+ scales=.1,.1
25
+
26
+ # 0
27
+ [convolutional]
28
+ batch_normalize=1
29
+ filters=32
30
+ size=3
31
+ stride=1
32
+ pad=1
33
+ activation=swish
34
+
35
+
36
+ # 1
37
+ [convolutional]
38
+ batch_normalize=1
39
+ filters=64
40
+ size=3
41
+ stride=2
42
+ pad=1
43
+ activation=swish
44
+
45
+ [convolutional]
46
+ batch_normalize=1
47
+ filters=64
48
+ size=3
49
+ stride=1
50
+ pad=1
51
+ activation=swish
52
+
53
+
54
+ # 3
55
+ [convolutional]
56
+ batch_normalize=1
57
+ filters=128
58
+ size=3
59
+ stride=2
60
+ pad=1
61
+ activation=swish
62
+
63
+ [convolutional]
64
+ batch_normalize=1
65
+ filters=64
66
+ size=1
67
+ stride=1
68
+ pad=1
69
+ activation=swish
70
+
71
+ [route]
72
+ layers=-2
73
+
74
+ [convolutional]
75
+ batch_normalize=1
76
+ filters=64
77
+ size=1
78
+ stride=1
79
+ pad=1
80
+ activation=swish
81
+
82
+ [convolutional]
83
+ batch_normalize=1
84
+ filters=64
85
+ size=3
86
+ stride=1
87
+ pad=1
88
+ activation=swish
89
+
90
+ [convolutional]
91
+ batch_normalize=1
92
+ filters=64
93
+ size=3
94
+ stride=1
95
+ pad=1
96
+ activation=swish
97
+
98
+ [convolutional]
99
+ batch_normalize=1
100
+ filters=64
101
+ size=3
102
+ stride=1
103
+ pad=1
104
+ activation=swish
105
+
106
+ [convolutional]
107
+ batch_normalize=1
108
+ filters=64
109
+ size=3
110
+ stride=1
111
+ pad=1
112
+ activation=swish
113
+
114
+ [route]
115
+ layers = -1,-3,-5,-7
116
+
117
+ # 12
118
+ [convolutional]
119
+ batch_normalize=1
120
+ filters=256
121
+ size=1
122
+ stride=1
123
+ pad=1
124
+ activation=swish
125
+
126
+
127
+ [maxpool]
128
+ size=2
129
+ stride=2
130
+
131
+ [convolutional]
132
+ batch_normalize=1
133
+ filters=128
134
+ size=1
135
+ stride=1
136
+ pad=1
137
+ activation=swish
138
+
139
+ [route]
140
+ layers=-3
141
+
142
+ [convolutional]
143
+ batch_normalize=1
144
+ filters=128
145
+ size=1
146
+ stride=1
147
+ pad=1
148
+ activation=swish
149
+
150
+ [convolutional]
151
+ batch_normalize=1
152
+ filters=128
153
+ size=3
154
+ stride=2
155
+ pad=1
156
+ activation=swish
157
+
158
+ # 18
159
+ [route]
160
+ layers = -1,-4
161
+
162
+ [convolutional]
163
+ batch_normalize=1
164
+ filters=128
165
+ size=1
166
+ stride=1
167
+ pad=1
168
+ activation=swish
169
+
170
+ [route]
171
+ layers=-2
172
+
173
+ [convolutional]
174
+ batch_normalize=1
175
+ filters=128
176
+ size=1
177
+ stride=1
178
+ pad=1
179
+ activation=swish
180
+
181
+ [convolutional]
182
+ batch_normalize=1
183
+ filters=128
184
+ size=3
185
+ stride=1
186
+ pad=1
187
+ activation=swish
188
+
189
+ [convolutional]
190
+ batch_normalize=1
191
+ filters=128
192
+ size=3
193
+ stride=1
194
+ pad=1
195
+ activation=swish
196
+
197
+ [convolutional]
198
+ batch_normalize=1
199
+ filters=128
200
+ size=3
201
+ stride=1
202
+ pad=1
203
+ activation=swish
204
+
205
+ [convolutional]
206
+ batch_normalize=1
207
+ filters=128
208
+ size=3
209
+ stride=1
210
+ pad=1
211
+ activation=swish
212
+
213
+ [route]
214
+ layers = -1,-3,-5,-7
215
+
216
+ # 27
217
+ [convolutional]
218
+ batch_normalize=1
219
+ filters=512
220
+ size=1
221
+ stride=1
222
+ pad=1
223
+ activation=swish
224
+
225
+
226
+ [maxpool]
227
+ size=2
228
+ stride=2
229
+
230
+ [convolutional]
231
+ batch_normalize=1
232
+ filters=256
233
+ size=1
234
+ stride=1
235
+ pad=1
236
+ activation=swish
237
+
238
+ [route]
239
+ layers=-3
240
+
241
+ [convolutional]
242
+ batch_normalize=1
243
+ filters=256
244
+ size=1
245
+ stride=1
246
+ pad=1
247
+ activation=swish
248
+
249
+ [convolutional]
250
+ batch_normalize=1
251
+ filters=256
252
+ size=3
253
+ stride=2
254
+ pad=1
255
+ activation=swish
256
+
257
+ # 33
258
+ [route]
259
+ layers = -1,-4
260
+
261
+ [convolutional]
262
+ batch_normalize=1
263
+ filters=256
264
+ size=1
265
+ stride=1
266
+ pad=1
267
+ activation=swish
268
+
269
+ [route]
270
+ layers=-2
271
+
272
+ [convolutional]
273
+ batch_normalize=1
274
+ filters=256
275
+ size=1
276
+ stride=1
277
+ pad=1
278
+ activation=swish
279
+
280
+ [convolutional]
281
+ batch_normalize=1
282
+ filters=256
283
+ size=3
284
+ stride=1
285
+ pad=1
286
+ activation=swish
287
+
288
+ [convolutional]
289
+ batch_normalize=1
290
+ filters=256
291
+ size=3
292
+ stride=1
293
+ pad=1
294
+ activation=swish
295
+
296
+ [convolutional]
297
+ batch_normalize=1
298
+ filters=256
299
+ size=3
300
+ stride=1
301
+ pad=1
302
+ activation=swish
303
+
304
+ [convolutional]
305
+ batch_normalize=1
306
+ filters=256
307
+ size=3
308
+ stride=1
309
+ pad=1
310
+ activation=swish
311
+
312
+ [route]
313
+ layers = -1,-3,-5,-7
314
+
315
+ # 42
316
+ [convolutional]
317
+ batch_normalize=1
318
+ filters=1024
319
+ size=1
320
+ stride=1
321
+ pad=1
322
+ activation=swish
323
+
324
+
325
+ [maxpool]
326
+ size=2
327
+ stride=2
328
+
329
+ [convolutional]
330
+ batch_normalize=1
331
+ filters=512
332
+ size=1
333
+ stride=1
334
+ pad=1
335
+ activation=swish
336
+
337
+ [route]
338
+ layers=-3
339
+
340
+ [convolutional]
341
+ batch_normalize=1
342
+ filters=512
343
+ size=1
344
+ stride=1
345
+ pad=1
346
+ activation=swish
347
+
348
+ [convolutional]
349
+ batch_normalize=1
350
+ filters=512
351
+ size=3
352
+ stride=2
353
+ pad=1
354
+ activation=swish
355
+
356
+ # 48
357
+ [route]
358
+ layers = -1,-4
359
+
360
+ [convolutional]
361
+ batch_normalize=1
362
+ filters=256
363
+ size=1
364
+ stride=1
365
+ pad=1
366
+ activation=swish
367
+
368
+ [route]
369
+ layers=-2
370
+
371
+ [convolutional]
372
+ batch_normalize=1
373
+ filters=256
374
+ size=1
375
+ stride=1
376
+ pad=1
377
+ activation=swish
378
+
379
+ [convolutional]
380
+ batch_normalize=1
381
+ filters=256
382
+ size=3
383
+ stride=1
384
+ pad=1
385
+ activation=swish
386
+
387
+ [convolutional]
388
+ batch_normalize=1
389
+ filters=256
390
+ size=3
391
+ stride=1
392
+ pad=1
393
+ activation=swish
394
+
395
+ [convolutional]
396
+ batch_normalize=1
397
+ filters=256
398
+ size=3
399
+ stride=1
400
+ pad=1
401
+ activation=swish
402
+
403
+ [convolutional]
404
+ batch_normalize=1
405
+ filters=256
406
+ size=3
407
+ stride=1
408
+ pad=1
409
+ activation=swish
410
+
411
+ [route]
412
+ layers = -1,-3,-5,-7
413
+
414
+ # 57
415
+ [convolutional]
416
+ batch_normalize=1
417
+ filters=1024
418
+ size=1
419
+ stride=1
420
+ pad=1
421
+ activation=swish
422
+
423
+ ##################################
424
+
425
+ ### SPPCSP ###
426
+ [convolutional]
427
+ batch_normalize=1
428
+ filters=512
429
+ size=1
430
+ stride=1
431
+ pad=1
432
+ activation=swish
433
+
434
+ [route]
435
+ layers = -2
436
+
437
+ [convolutional]
438
+ batch_normalize=1
439
+ filters=512
440
+ size=1
441
+ stride=1
442
+ pad=1
443
+ activation=swish
444
+
445
+ [convolutional]
446
+ batch_normalize=1
447
+ size=3
448
+ stride=1
449
+ pad=1
450
+ filters=512
451
+ activation=swish
452
+
453
+ [convolutional]
454
+ batch_normalize=1
455
+ filters=512
456
+ size=1
457
+ stride=1
458
+ pad=1
459
+ activation=swish
460
+
461
+ ### SPP ###
462
+ [maxpool]
463
+ stride=1
464
+ size=5
465
+
466
+ [route]
467
+ layers=-2
468
+
469
+ [maxpool]
470
+ stride=1
471
+ size=9
472
+
473
+ [route]
474
+ layers=-4
475
+
476
+ [maxpool]
477
+ stride=1
478
+ size=13
479
+
480
+ [route]
481
+ layers=-6,-5,-3,-1
482
+ ### End SPP ###
483
+
484
+ [convolutional]
485
+ batch_normalize=1
486
+ filters=512
487
+ size=1
488
+ stride=1
489
+ pad=1
490
+ activation=swish
491
+
492
+ [convolutional]
493
+ batch_normalize=1
494
+ size=3
495
+ stride=1
496
+ pad=1
497
+ filters=512
498
+ activation=swish
499
+
500
+ [route]
501
+ layers = -1, -13
502
+
503
+ # 72
504
+ [convolutional]
505
+ batch_normalize=1
506
+ filters=512
507
+ size=1
508
+ stride=1
509
+ pad=1
510
+ activation=swish
511
+ ### End SPPCSP ###
512
+
513
+
514
+ [convolutional]
515
+ batch_normalize=1
516
+ filters=256
517
+ size=1
518
+ stride=1
519
+ pad=1
520
+ activation=swish
521
+
522
+ [upsample]
523
+ stride=2
524
+
525
+ [route]
526
+ layers = 42
527
+
528
+ [convolutional]
529
+ batch_normalize=1
530
+ filters=256
531
+ size=1
532
+ stride=1
533
+ pad=1
534
+ activation=swish
535
+
536
+ [route]
537
+ layers = -1,-3
538
+
539
+
540
+ [convolutional]
541
+ batch_normalize=1
542
+ filters=256
543
+ size=1
544
+ stride=1
545
+ pad=1
546
+ activation=swish
547
+
548
+ [route]
549
+ layers=-2
550
+
551
+ [convolutional]
552
+ batch_normalize=1
553
+ filters=256
554
+ size=1
555
+ stride=1
556
+ pad=1
557
+ activation=swish
558
+
559
+ [convolutional]
560
+ batch_normalize=1
561
+ filters=128
562
+ size=3
563
+ stride=1
564
+ pad=1
565
+ activation=swish
566
+
567
+ [convolutional]
568
+ batch_normalize=1
569
+ filters=128
570
+ size=3
571
+ stride=1
572
+ pad=1
573
+ activation=swish
574
+
575
+ [convolutional]
576
+ batch_normalize=1
577
+ filters=128
578
+ size=3
579
+ stride=1
580
+ pad=1
581
+ activation=swish
582
+
583
+ [convolutional]
584
+ batch_normalize=1
585
+ filters=128
586
+ size=3
587
+ stride=1
588
+ pad=1
589
+ activation=swish
590
+
591
+ [route]
592
+ layers = -1,-2,-3,-4,-5,-7
593
+
594
+ # 86
595
+ [convolutional]
596
+ batch_normalize=1
597
+ filters=256
598
+ size=1
599
+ stride=1
600
+ pad=1
601
+ activation=swish
602
+
603
+
604
+ [convolutional]
605
+ batch_normalize=1
606
+ filters=128
607
+ size=1
608
+ stride=1
609
+ pad=1
610
+ activation=swish
611
+
612
+ [upsample]
613
+ stride=2
614
+
615
+ [route]
616
+ layers = 27
617
+
618
+ [convolutional]
619
+ batch_normalize=1
620
+ filters=128
621
+ size=1
622
+ stride=1
623
+ pad=1
624
+ activation=swish
625
+
626
+ [route]
627
+ layers = -1,-3
628
+
629
+
630
+ [convolutional]
631
+ batch_normalize=1
632
+ filters=128
633
+ size=1
634
+ stride=1
635
+ pad=1
636
+ activation=swish
637
+
638
+ [route]
639
+ layers=-2
640
+
641
+ [convolutional]
642
+ batch_normalize=1
643
+ filters=128
644
+ size=1
645
+ stride=1
646
+ pad=1
647
+ activation=swish
648
+
649
+ [convolutional]
650
+ batch_normalize=1
651
+ filters=64
652
+ size=3
653
+ stride=1
654
+ pad=1
655
+ activation=swish
656
+
657
+ [convolutional]
658
+ batch_normalize=1
659
+ filters=64
660
+ size=3
661
+ stride=1
662
+ pad=1
663
+ activation=swish
664
+
665
+ [convolutional]
666
+ batch_normalize=1
667
+ filters=64
668
+ size=3
669
+ stride=1
670
+ pad=1
671
+ activation=swish
672
+
673
+ [convolutional]
674
+ batch_normalize=1
675
+ filters=64
676
+ size=3
677
+ stride=1
678
+ pad=1
679
+ activation=swish
680
+
681
+ [route]
682
+ layers = -1,-2,-3,-4,-5,-7
683
+
684
+ # 100
685
+ [convolutional]
686
+ batch_normalize=1
687
+ filters=128
688
+ size=1
689
+ stride=1
690
+ pad=1
691
+ activation=swish
692
+
693
+
694
+ [maxpool]
695
+ size=2
696
+ stride=2
697
+
698
+ [convolutional]
699
+ batch_normalize=1
700
+ filters=128
701
+ size=1
702
+ stride=1
703
+ pad=1
704
+ activation=swish
705
+
706
+ [route]
707
+ layers=-3
708
+
709
+ [convolutional]
710
+ batch_normalize=1
711
+ filters=128
712
+ size=1
713
+ stride=1
714
+ pad=1
715
+ activation=swish
716
+
717
+ [convolutional]
718
+ batch_normalize=1
719
+ filters=128
720
+ size=3
721
+ stride=2
722
+ pad=1
723
+ activation=swish
724
+
725
+ [route]
726
+ layers = -1,-4,86
727
+
728
+
729
+ [convolutional]
730
+ batch_normalize=1
731
+ filters=256
732
+ size=1
733
+ stride=1
734
+ pad=1
735
+ activation=swish
736
+
737
+ [route]
738
+ layers=-2
739
+
740
+ [convolutional]
741
+ batch_normalize=1
742
+ filters=256
743
+ size=1
744
+ stride=1
745
+ pad=1
746
+ activation=swish
747
+
748
+ [convolutional]
749
+ batch_normalize=1
750
+ filters=128
751
+ size=3
752
+ stride=1
753
+ pad=1
754
+ activation=swish
755
+
756
+ [convolutional]
757
+ batch_normalize=1
758
+ filters=128
759
+ size=3
760
+ stride=1
761
+ pad=1
762
+ activation=swish
763
+
764
+ [convolutional]
765
+ batch_normalize=1
766
+ filters=128
767
+ size=3
768
+ stride=1
769
+ pad=1
770
+ activation=swish
771
+
772
+ [convolutional]
773
+ batch_normalize=1
774
+ filters=128
775
+ size=3
776
+ stride=1
777
+ pad=1
778
+ activation=swish
779
+
780
+ [route]
781
+ layers = -1,-2,-3,-4,-5,-7
782
+
783
+ # 115
784
+ [convolutional]
785
+ batch_normalize=1
786
+ filters=256
787
+ size=1
788
+ stride=1
789
+ pad=1
790
+ activation=swish
791
+
792
+
793
+ [maxpool]
794
+ size=2
795
+ stride=2
796
+
797
+ [convolutional]
798
+ batch_normalize=1
799
+ filters=256
800
+ size=1
801
+ stride=1
802
+ pad=1
803
+ activation=swish
804
+
805
+ [route]
806
+ layers=-3
807
+
808
+ [convolutional]
809
+ batch_normalize=1
810
+ filters=256
811
+ size=1
812
+ stride=1
813
+ pad=1
814
+ activation=swish
815
+
816
+ [convolutional]
817
+ batch_normalize=1
818
+ filters=256
819
+ size=3
820
+ stride=2
821
+ pad=1
822
+ activation=swish
823
+
824
+ [route]
825
+ layers = -1,-4,72
826
+
827
+
828
+ [convolutional]
829
+ batch_normalize=1
830
+ filters=512
831
+ size=1
832
+ stride=1
833
+ pad=1
834
+ activation=swish
835
+
836
+ [route]
837
+ layers=-2
838
+
839
+ [convolutional]
840
+ batch_normalize=1
841
+ filters=512
842
+ size=1
843
+ stride=1
844
+ pad=1
845
+ activation=swish
846
+
847
+ [convolutional]
848
+ batch_normalize=1
849
+ filters=256
850
+ size=3
851
+ stride=1
852
+ pad=1
853
+ activation=swish
854
+
855
+ [convolutional]
856
+ batch_normalize=1
857
+ filters=256
858
+ size=3
859
+ stride=1
860
+ pad=1
861
+ activation=swish
862
+
863
+ [convolutional]
864
+ batch_normalize=1
865
+ filters=256
866
+ size=3
867
+ stride=1
868
+ pad=1
869
+ activation=swish
870
+
871
+ [convolutional]
872
+ batch_normalize=1
873
+ filters=256
874
+ size=3
875
+ stride=1
876
+ pad=1
877
+ activation=swish
878
+
879
+ [route]
880
+ layers = -1,-2,-3,-4,-5,-7
881
+
882
+ # 130
883
+ [convolutional]
884
+ batch_normalize=1
885
+ filters=512
886
+ size=1
887
+ stride=1
888
+ pad=1
889
+ activation=swish
890
+
891
+ #############################
892
+
893
+ # ============ End of Neck ============ #
894
+
895
+ # ============ Head ============ #
896
+
897
+
898
+ # P3
899
+ [route]
900
+ layers = 100
901
+
902
+ [convolutional]
903
+ batch_normalize=1
904
+ size=3
905
+ stride=1
906
+ pad=1
907
+ filters=256
908
+ activation=swish
909
+
910
+ [convolutional]
911
+ size=1
912
+ stride=1
913
+ pad=1
914
+ filters=255
915
+ #activation=linear
916
+ activation=logistic
917
+
918
+ [yolo]
919
+ mask = 0,1,2
920
+ anchors = 12,16, 19,36, 40,28, 36,75, 76,55, 72,146, 142,110, 192,243, 459,401
921
+ classes=80
922
+ num=9
923
+ jitter=.1
924
+ scale_x_y = 2.0
925
+ objectness_smooth=1
926
+ ignore_thresh = .7
927
+ truth_thresh = 1
928
+ #random=1
929
+ resize=1.5
930
+ iou_thresh=0.2
931
+ iou_normalizer=0.05
932
+ cls_normalizer=0.5
933
+ obj_normalizer=1.0
934
+ iou_loss=ciou
935
+ nms_kind=diounms
936
+ beta_nms=0.6
937
+ new_coords=1
938
+ max_delta=2
939
+
940
+
941
+ # P4
942
+ [route]
943
+ layers = 115
944
+
945
+ [convolutional]
946
+ batch_normalize=1
947
+ size=3
948
+ stride=1
949
+ pad=1
950
+ filters=512
951
+ activation=swish
952
+
953
+ [convolutional]
954
+ size=1
955
+ stride=1
956
+ pad=1
957
+ filters=255
958
+ #activation=linear
959
+ activation=logistic
960
+
961
+ [yolo]
962
+ mask = 3,4,5
963
+ anchors = 12,16, 19,36, 40,28, 36,75, 76,55, 72,146, 142,110, 192,243, 459,401
964
+ classes=80
965
+ num=9
966
+ jitter=.1
967
+ scale_x_y = 2.0
968
+ objectness_smooth=1
969
+ ignore_thresh = .7
970
+ truth_thresh = 1
971
+ #random=1
972
+ resize=1.5
973
+ iou_thresh=0.2
974
+ iou_normalizer=0.05
975
+ cls_normalizer=0.5
976
+ obj_normalizer=1.0
977
+ iou_loss=ciou
978
+ nms_kind=diounms
979
+ beta_nms=0.6
980
+ new_coords=1
981
+ max_delta=2
982
+
983
+
984
+ # P5
985
+ [route]
986
+ layers = 130
987
+
988
+ [convolutional]
989
+ batch_normalize=1
990
+ size=3
991
+ stride=1
992
+ pad=1
993
+ filters=1024
994
+ activation=swish
995
+
996
+ [convolutional]
997
+ size=1
998
+ stride=1
999
+ pad=1
1000
+ filters=255
1001
+ #activation=linear
1002
+ activation=logistic
1003
+
1004
+ [yolo]
1005
+ mask = 6,7,8
1006
+ anchors = 12,16, 19,36, 40,28, 36,75, 76,55, 72,146, 142,110, 192,243, 459,401
1007
+ classes=80
1008
+ num=9
1009
+ jitter=.1
1010
+ scale_x_y = 2.0
1011
+ objectness_smooth=1
1012
+ ignore_thresh = .7
1013
+ truth_thresh = 1
1014
+ #random=1
1015
+ resize=1.5
1016
+ iou_thresh=0.2
1017
+ iou_normalizer=0.05
1018
+ cls_normalizer=0.5
1019
+ obj_normalizer=1.0
1020
+ iou_loss=ciou
1021
+ nms_kind=diounms
1022
+ beta_nms=0.6
1023
+ new_coords=1
1024
+ max_delta=2
yolov7.weights ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ecf7ca13ec5039ec7b79b0f25b156fda5eaf819d6c2bb6828ba55fe4f928332
3
+ size 147898248