Hugging Face's logo

Spaces:
xiang-wuu
/
yolov5
Runtime error

App Files Community
glenn-jocher pre-commit-ci[bot] commited on
Commit
1d0a094
•
1 Parent(s): c4cb7c6

Update tutorial.ipynb (#7715)

Browse files

* Update tutorial.ipynb

* Created using Colaboratory

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Files changed (1) hide show
  1. tutorial.ipynb +403 -385
tutorial.ipynb CHANGED
@@ -6,6 +6,7 @@
6
  "name": "YOLOv5 Tutorial",
7
  "provenance": [],
8
  "collapsed_sections": [],
 
9
  "include_colab_link": true
10
  },
11
  "kernelspec": {
@@ -15,346 +16,346 @@
15
  "accelerator": "GPU",
16
  "widgets": {
17
  "application/vnd.jupyter.widget-state+json": {
18
- "eb95db7cae194218b3fcefb439b6352f": {
19
  "model_module": "@jupyter-widgets/controls",
20
  "model_name": "HBoxModel",
21
  "model_module_version": "1.5.0",
22
  "state": {
23
- "_view_name": "HBoxView",
24
  "_dom_classes": [],
25
- "_model_name": "HBoxModel",
26
- "_view_module": "@jupyter-widgets/controls",
27
  "_model_module_version": "1.5.0",
 
28
  "_view_count": null,
 
29
  "_view_module_version": "1.5.0",
 
30
  "box_style": "",
31
- "layout": "IPY_MODEL_769ecde6f2e64bacb596ce972f8d3d2d",
32
- "_model_module": "@jupyter-widgets/controls",
33
  "children": [
34
- "IPY_MODEL_384a001876054c93b0af45cd1e960bfe",
35
- "IPY_MODEL_dded0aeae74440f7ba2ffa0beb8dd612",
36
- "IPY_MODEL_5296d28be75740b2892ae421bbec3657"
37
- ]
 
38
  }
39
  },
40
- "769ecde6f2e64bacb596ce972f8d3d2d": {
41
- "model_module": "@jupyter-widgets/base",
42
- "model_name": "LayoutModel",
43
- "model_module_version": "1.2.0",
44
- "state": {
45
- "_view_name": "LayoutView",
46
- "grid_template_rows": null,
47
- "right": null,
48
- "justify_content": null,
49
- "_view_module": "@jupyter-widgets/base",
50
- "overflow": null,
51
- "_model_module_version": "1.2.0",
52
- "_view_count": null,
53
- "flex_flow": null,
54
- "width": null,
55
- "min_width": null,
56
- "border": null,
57
- "align_items": null,
58
- "bottom": null,
59
- "_model_module": "@jupyter-widgets/base",
60
- "top": null,
61
- "grid_column": null,
62
- "overflow_y": null,
63
- "overflow_x": null,
64
- "grid_auto_flow": null,
65
- "grid_area": null,
66
- "grid_template_columns": null,
67
- "flex": null,
68
- "_model_name": "LayoutModel",
69
- "justify_items": null,
70
- "grid_row": null,
71
- "max_height": null,
72
- "align_content": null,
73
- "visibility": null,
74
- "align_self": null,
75
- "height": null,
76
- "min_height": null,
77
- "padding": null,
78
- "grid_auto_rows": null,
79
- "grid_gap": null,
80
- "max_width": null,
81
- "order": null,
82
- "_view_module_version": "1.2.0",
83
- "grid_template_areas": null,
84
- "object_position": null,
85
- "object_fit": null,
86
- "grid_auto_columns": null,
87
- "margin": null,
88
- "display": null,
89
- "left": null
90
- }
91
- },
92
- "384a001876054c93b0af45cd1e960bfe": {
93
  "model_module": "@jupyter-widgets/controls",
94
  "model_name": "HTMLModel",
95
  "model_module_version": "1.5.0",
96
  "state": {
97
- "_view_name": "HTMLView",
98
- "style": "IPY_MODEL_9f09facb2a6c4a7096810d327c8b551c",
99
  "_dom_classes": [],
100
- "description": "",
101
- "_model_name": "HTMLModel",
102
- "placeholder": "​",
103
- "_view_module": "@jupyter-widgets/controls",
104
  "_model_module_version": "1.5.0",
105
- "value": "100%",
106
  "_view_count": null,
 
107
  "_view_module_version": "1.5.0",
 
 
108
  "description_tooltip": null,
109
- "_model_module": "@jupyter-widgets/controls",
110
- "layout": "IPY_MODEL_25621cff5d16448cb7260e839fd0f543"
 
 
111
  }
112
  },
113
- "dded0aeae74440f7ba2ffa0beb8dd612": {
114
  "model_module": "@jupyter-widgets/controls",
115
  "model_name": "FloatProgressModel",
116
  "model_module_version": "1.5.0",
117
  "state": {
118
- "_view_name": "ProgressView",
119
- "style": "IPY_MODEL_0ce7164fc0c74bb9a2b5c7037375a727",
120
  "_dom_classes": [],
121
- "description": "",
122
- "_model_name": "FloatProgressModel",
123
- "bar_style": "success",
124
- "max": 818322941,
125
- "_view_module": "@jupyter-widgets/controls",
126
  "_model_module_version": "1.5.0",
127
- "value": 818322941,
128
  "_view_count": null,
 
129
  "_view_module_version": "1.5.0",
130
- "orientation": "horizontal",
131
- "min": 0,
 
132
  "description_tooltip": null,
133
- "_model_module": "@jupyter-widgets/controls",
134
- "layout": "IPY_MODEL_c4c4593c10904cb5b8a5724d60c7e181"
 
 
 
 
135
  }
136
  },
137
- "5296d28be75740b2892ae421bbec3657": {
138
  "model_module": "@jupyter-widgets/controls",
139
  "model_name": "HTMLModel",
140
  "model_module_version": "1.5.0",
141
  "state": {
142
- "_view_name": "HTMLView",
143
- "style": "IPY_MODEL_473371611126476c88d5d42ec7031ed6",
144
  "_dom_classes": [],
145
- "description": "",
146
- "_model_name": "HTMLModel",
147
- "placeholder": "​",
148
- "_view_module": "@jupyter-widgets/controls",
149
  "_model_module_version": "1.5.0",
150
- "value": " 780M/780M [00:11&lt;00:00, 91.9MB/s]",
151
  "_view_count": null,
 
152
  "_view_module_version": "1.5.0",
 
 
153
  "description_tooltip": null,
154
- "_model_module": "@jupyter-widgets/controls",
155
- "layout": "IPY_MODEL_65efdfd0d26c46e79c8c5ff3b77126cc"
 
 
156
  }
157
  },
158
- "9f09facb2a6c4a7096810d327c8b551c": {
159
- "model_module": "@jupyter-widgets/controls",
160
- "model_name": "DescriptionStyleModel",
161
- "model_module_version": "1.5.0",
162
  "state": {
163
- "_view_name": "StyleView",
164
- "_model_name": "DescriptionStyleModel",
165
- "description_width": "",
166
- "_view_module": "@jupyter-widgets/base",
167
- "_model_module_version": "1.5.0",
168
  "_view_count": null,
 
169
  "_view_module_version": "1.2.0",
170
- "_model_module": "@jupyter-widgets/controls"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
171
  }
172
  },
173
- "25621cff5d16448cb7260e839fd0f543": {
174
  "model_module": "@jupyter-widgets/base",
175
  "model_name": "LayoutModel",
176
  "model_module_version": "1.2.0",
177
  "state": {
178
- "_view_name": "LayoutView",
179
- "grid_template_rows": null,
180
- "right": null,
181
- "justify_content": null,
182
- "_view_module": "@jupyter-widgets/base",
183
- "overflow": null,
184
  "_model_module_version": "1.2.0",
 
185
  "_view_count": null,
186
- "flex_flow": null,
187
- "width": null,
188
- "min_width": null,
189
- "border": null,
190
  "align_items": null,
 
 
191
  "bottom": null,
192
- "_model_module": "@jupyter-widgets/base",
193
- "top": null,
194
- "grid_column": null,
195
- "overflow_y": null,
196
- "overflow_x": null,
197
- "grid_auto_flow": null,
198
  "grid_area": null,
 
 
 
 
 
 
 
199
  "grid_template_columns": null,
200
- "flex": null,
201
- "_model_name": "LayoutModel",
 
202
  "justify_items": null,
203
- "grid_row": null,
 
204
  "max_height": null,
205
- "align_content": null,
206
- "visibility": null,
207
- "align_self": null,
208
- "height": null,
209
- "min_height": null,
210
- "padding": null,
211
- "grid_auto_rows": null,
212
- "grid_gap": null,
213
  "max_width": null,
214
- "order": null,
215
- "_view_module_version": "1.2.0",
216
- "grid_template_areas": null,
217
- "object_position": null,
218
  "object_fit": null,
219
- "grid_auto_columns": null,
220
- "margin": null,
221
- "display": null,
222
- "left": null
 
 
 
 
 
 
223
  }
224
  },
225
- "0ce7164fc0c74bb9a2b5c7037375a727": {
226
  "model_module": "@jupyter-widgets/controls",
227
- "model_name": "ProgressStyleModel",
228
  "model_module_version": "1.5.0",
229
  "state": {
230
- "_view_name": "StyleView",
231
- "_model_name": "ProgressStyleModel",
232
- "description_width": "",
233
- "_view_module": "@jupyter-widgets/base",
234
  "_model_module_version": "1.5.0",
 
235
  "_view_count": null,
 
236
  "_view_module_version": "1.2.0",
237
- "bar_color": null,
238
- "_model_module": "@jupyter-widgets/controls"
239
  }
240
  },
241
- "c4c4593c10904cb5b8a5724d60c7e181": {
242
  "model_module": "@jupyter-widgets/base",
243
  "model_name": "LayoutModel",
244
  "model_module_version": "1.2.0",
245
  "state": {
246
- "_view_name": "LayoutView",
247
- "grid_template_rows": null,
248
- "right": null,
249
- "justify_content": null,
250
- "_view_module": "@jupyter-widgets/base",
251
- "overflow": null,
252
  "_model_module_version": "1.2.0",
 
253
  "_view_count": null,
254
- "flex_flow": null,
255
- "width": null,
256
- "min_width": null,
257
- "border": null,
258
  "align_items": null,
 
 
259
  "bottom": null,
260
- "_model_module": "@jupyter-widgets/base",
261
- "top": null,
262
- "grid_column": null,
263
- "overflow_y": null,
264
- "overflow_x": null,
265
- "grid_auto_flow": null,
266
  "grid_area": null,
 
 
 
 
 
 
 
267
  "grid_template_columns": null,
268
- "flex": null,
269
- "_model_name": "LayoutModel",
 
270
  "justify_items": null,
271
- "grid_row": null,
 
272
  "max_height": null,
273
- "align_content": null,
274
- "visibility": null,
275
- "align_self": null,
276
- "height": null,
277
- "min_height": null,
278
- "padding": null,
279
- "grid_auto_rows": null,
280
- "grid_gap": null,
281
  "max_width": null,
282
- "order": null,
283
- "_view_module_version": "1.2.0",
284
- "grid_template_areas": null,
285
- "object_position": null,
286
  "object_fit": null,
287
- "grid_auto_columns": null,
288
- "margin": null,
289
- "display": null,
290
- "left": null
 
 
 
 
 
 
291
  }
292
  },
293
- "473371611126476c88d5d42ec7031ed6": {
294
  "model_module": "@jupyter-widgets/controls",
295
- "model_name": "DescriptionStyleModel",
296
  "model_module_version": "1.5.0",
297
  "state": {
298
- "_view_name": "StyleView",
299
- "_model_name": "DescriptionStyleModel",
300
- "description_width": "",
301
- "_view_module": "@jupyter-widgets/base",
302
  "_model_module_version": "1.5.0",
 
303
  "_view_count": null,
 
304
  "_view_module_version": "1.2.0",
305
- "_model_module": "@jupyter-widgets/controls"
 
 
306
  }
307
  },
308
- "65efdfd0d26c46e79c8c5ff3b77126cc": {
309
  "model_module": "@jupyter-widgets/base",
310
  "model_name": "LayoutModel",
311
  "model_module_version": "1.2.0",
312
  "state": {
313
- "_view_name": "LayoutView",
314
- "grid_template_rows": null,
315
- "right": null,
316
- "justify_content": null,
317
- "_view_module": "@jupyter-widgets/base",
318
- "overflow": null,
319
  "_model_module_version": "1.2.0",
 
320
  "_view_count": null,
321
- "flex_flow": null,
322
- "width": null,
323
- "min_width": null,
324
- "border": null,
325
  "align_items": null,
 
 
326
  "bottom": null,
327
- "_model_module": "@jupyter-widgets/base",
328
- "top": null,
329
- "grid_column": null,
330
- "overflow_y": null,
331
- "overflow_x": null,
332
- "grid_auto_flow": null,
333
  "grid_area": null,
 
 
 
 
 
 
 
334
  "grid_template_columns": null,
335
- "flex": null,
336
- "_model_name": "LayoutModel",
 
337
  "justify_items": null,
338
- "grid_row": null,
 
339
  "max_height": null,
340
- "align_content": null,
341
- "visibility": null,
342
- "align_self": null,
343
- "height": null,
344
- "min_height": null,
345
- "padding": null,
346
- "grid_auto_rows": null,
347
- "grid_gap": null,
348
  "max_width": null,
 
 
 
 
349
  "order": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
350
  "_view_module_version": "1.2.0",
351
- "grid_template_areas": null,
352
- "object_position": null,
353
- "object_fit": null,
354
- "grid_auto_columns": null,
355
- "margin": null,
356
- "display": null,
357
- "left": null
358
  }
359
  }
360
  }
@@ -368,7 +369,7 @@
368
  "colab_type": "text"
369
  },
370
  "source": [
371
- "<a href=\"https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
372
  ]
373
  },
374
  {
@@ -402,7 +403,7 @@
402
  "colab": {
403
  "base_uri": "https://localhost:8080/"
404
  },
405
- "outputId": "3809e5a9-dd41-4577-fe62-5531abf7cca2"
406
  },
407
  "source": [
408
  "!git clone https://github.com/ultralytics/yolov5 # clone\n",
@@ -413,14 +414,20 @@
413
  "import utils\n",
414
  "display = utils.notebook_init() # checks"
415
  ],
416
- "execution_count": null,
417
  "outputs": [
 
 
 
 
 
 
 
418
  {
419
  "output_type": "stream",
420
  "name": "stdout",
421
  "text": [
422
- "YOLOv5 🚀 v6.0-48-g84a8099 torch 1.10.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
423
- "Setup complete ✅ (2 CPUs, 12.7 GB RAM, 42.2/166.8 GB disk)\n"
424
  ]
425
  }
426
  ]
@@ -453,26 +460,29 @@
453
  "colab": {
454
  "base_uri": "https://localhost:8080/"
455
  },
456
- "outputId": "8f7e6588-215d-4ebd-93af-88b871e770a7"
457
  },
458
  "source": [
459
  "!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images\n",
460
  "display.Image(filename='runs/detect/exp/zidane.jpg', width=600)"
461
  ],
462
- "execution_count": null,
463
  "outputs": [
464
  {
465
  "output_type": "stream",
466
  "name": "stdout",
467
  "text": [
468
- "\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov5s.pt'], source=data/images, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False\n",
469
- "YOLOv5 🚀 v6.0-48-g84a8099 torch 1.10.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
 
 
 
470
  "\n",
471
  "Fusing layers... \n",
472
- "Model Summary: 213 layers, 7225885 parameters, 0 gradients\n",
473
- "image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, Done. (0.007s)\n",
474
- "image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 1 tie, Done. (0.007s)\n",
475
- "Speed: 0.5ms pre-process, 6.9ms inference, 1.3ms NMS per image at shape (1, 3, 640, 640)\n",
476
  "Results saved to \u001b[1mruns/detect/exp\u001b[0m\n"
477
  ]
478
  }
@@ -514,41 +524,41 @@
514
  "id": "WQPtK1QYVaD_",
515
  "colab": {
516
  "base_uri": "https://localhost:8080/",
517
- "height": 48,
518
  "referenced_widgets": [
519
- "eb95db7cae194218b3fcefb439b6352f",
520
- "769ecde6f2e64bacb596ce972f8d3d2d",
521
- "384a001876054c93b0af45cd1e960bfe",
522
- "dded0aeae74440f7ba2ffa0beb8dd612",
523
- "5296d28be75740b2892ae421bbec3657",
524
- "9f09facb2a6c4a7096810d327c8b551c",
525
- "25621cff5d16448cb7260e839fd0f543",
526
- "0ce7164fc0c74bb9a2b5c7037375a727",
527
- "c4c4593c10904cb5b8a5724d60c7e181",
528
- "473371611126476c88d5d42ec7031ed6",
529
- "65efdfd0d26c46e79c8c5ff3b77126cc"
530
  ]
531
  },
532
- "outputId": "bcf9a448-1f9b-4a41-ad49-12f181faf05a"
533
  },
534
  "source": [
535
  "# Download COCO val\n",
536
  "torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017val.zip', 'tmp.zip')\n",
537
  "!unzip -q tmp.zip -d ../datasets && rm tmp.zip"
538
  ],
539
- "execution_count": null,
540
  "outputs": [
541
  {
542
  "output_type": "display_data",
543
  "data": {
544
- "application/vnd.jupyter.widget-view+json": {
545
- "model_id": "eb95db7cae194218b3fcefb439b6352f",
546
- "version_minor": 0,
547
- "version_major": 2
548
- },
549
  "text/plain": [
550
  " 0%| | 0.00/780M [00:00<?, ?B/s]"
551
- ]
 
 
 
 
 
552
  },
553
  "metadata": {}
554
  }
@@ -561,58 +571,60 @@
561
  "colab": {
562
  "base_uri": "https://localhost:8080/"
563
  },
564
- "outputId": "74f1dfa9-6b6d-4b36-f67e-bbae243869f9"
565
  },
566
  "source": [
567
  "# Run YOLOv5x on COCO val\n",
568
  "!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half"
569
  ],
570
- "execution_count": null,
571
  "outputs": [
572
  {
573
  "output_type": "stream",
574
  "name": "stdout",
575
  "text": [
576
- "\u001b[34m\u001b[1mval: \u001b[0mdata=/content/yolov5/data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.65, task=val, device=, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True\n",
577
- "YOLOv5 🚀 v6.0-48-g84a8099 torch 1.10.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
578
  "\n",
579
- "Downloading https://github.com/ultralytics/yolov5/releases/download/v6.0/yolov5x.pt to yolov5x.pt...\n",
580
- "100% 166M/166M [00:03<00:00, 54.1MB/s]\n",
581
  "\n",
582
  "Fusing layers... \n",
583
- "Model Summary: 444 layers, 86705005 parameters, 0 gradients\n",
584
- "\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:01<00:00, 2636.64it/s]\n",
585
- "\u001b[34m\u001b[1mval: \u001b[0mNew cache created: ../datasets/coco/val2017.cache\n",
586
- " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [01:12<00:00, 2.17it/s]\n",
587
- " all 5000 36335 0.729 0.63 0.683 0.496\n",
588
- "Speed: 0.1ms pre-process, 4.9ms inference, 1.9ms NMS per image at shape (32, 3, 640, 640)\n",
 
 
589
  "\n",
590
  "Evaluating pycocotools mAP... saving runs/val/exp/yolov5x_predictions.json...\n",
591
  "loading annotations into memory...\n",
592
- "Done (t=0.46s)\n",
593
  "creating index...\n",
594
  "index created!\n",
595
  "Loading and preparing results...\n",
596
- "DONE (t=5.15s)\n",
597
  "creating index...\n",
598
  "index created!\n",
599
  "Running per image evaluation...\n",
600
  "Evaluate annotation type *bbox*\n",
601
- "DONE (t=90.39s).\n",
602
  "Accumulating evaluation results...\n",
603
- "DONE (t=14.54s).\n",
604
- " Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.507\n",
605
- " Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.689\n",
606
- " Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.552\n",
607
- " Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.345\n",
608
- " Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.559\n",
609
- " Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.652\n",
610
- " Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.381\n",
611
- " Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.630\n",
612
- " Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.682\n",
613
- " Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.526\n",
614
- " Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.732\n",
615
- " Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.829\n",
616
  "Results saved to \u001b[1mruns/val/exp\u001b[0m\n"
617
  ]
618
  }
@@ -719,26 +731,31 @@
719
  "colab": {
720
  "base_uri": "https://localhost:8080/"
721
  },
722
- "outputId": "8724d13d-6711-4a12-d96a-1c655e5c3549"
723
  },
724
  "source": [
725
  "# Train YOLOv5s on COCO128 for 3 epochs\n",
726
  "!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache"
727
  ],
728
- "execution_count": null,
729
  "outputs": [
730
  {
731
  "output_type": "stream",
732
  "name": "stdout",
733
  "text": [
734
- "\u001b[34m\u001b[1mtrain: \u001b[0mweights=yolov5s.pt, cfg=, data=coco128.yaml, hyp=data/hyps/hyp.scratch-low.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, adam=False, sync_bn=False, workers=8, project=runs/train, name=exp, exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, patience=100, freeze=0, save_period=-1, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest\n",
735
  "\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov5 ✅\n",
736
- "YOLOv5 🚀 v6.0-48-g84a8099 torch 1.10.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
737
  "\n",
738
- "\u001b[34m\u001b[1mhyperparameters: \u001b[0mlr0=0.01, lrf=0.1, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0\n",
739
  "\u001b[34m\u001b[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)\n",
740
  "\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/\n",
741
  "\n",
 
 
 
 
 
742
  " from n params module arguments \n",
743
  " 0 -1 1 3520 models.common.Conv [3, 32, 6, 2, 2] \n",
744
  " 1 -1 1 18560 models.common.Conv [32, 64, 3, 2] \n",
@@ -765,38 +782,39 @@
765
  " 22 [-1, 10] 1 0 models.common.Concat [1] \n",
766
  " 23 -1 1 1182720 models.common.C3 [512, 512, 1, False] \n",
767
  " 24 [17, 20, 23] 1 229245 models.yolo.Detect [80, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]\n",
768
- "Model Summary: 270 layers, 7235389 parameters, 7235389 gradients, 16.5 GFLOPs\n",
769
  "\n",
770
  "Transferred 349/349 items from yolov5s.pt\n",
771
  "Scaled weight_decay = 0.0005\n",
772
- "\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 57 weight, 60 weight (no decay), 60 bias\n",
773
  "\u001b[34m\u001b[1malbumentations: \u001b[0mversion 1.0.3 required by YOLOv5, but version 0.1.12 is currently installed\n",
774
- "\u001b[34m\u001b[1mtrain: \u001b[0mScanning '../datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<?, ?it/s]\n",
775
- "\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 296.04it/s]\n",
776
- "\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<?, ?it/s]\n",
777
- "\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:01<00:00, 121.58it/s]\n",
778
- "Plotting labels... \n",
 
779
  "\n",
780
- "\u001b[34m\u001b[1mAutoAnchor: \u001b[0mAnalyzing anchors... anchors/target = 4.27, Best Possible Recall (BPR) = 0.9935\n",
781
  "Image sizes 640 train, 640 val\n",
782
- "Using 2 dataloader workers\n",
783
  "Logging results to \u001b[1mruns/train/exp\u001b[0m\n",
784
  "Starting training for 3 epochs...\n",
785
  "\n",
786
  " Epoch gpu_mem box obj cls labels img_size\n",
787
- " 0/2 3.62G 0.04621 0.0711 0.02112 203 640: 100% 8/8 [00:04<00:00, 1.99it/s]\n",
788
- " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.37it/s]\n",
789
- " all 128 929 0.655 0.547 0.622 0.41\n",
790
  "\n",
791
  " Epoch gpu_mem box obj cls labels img_size\n",
792
- " 1/2 5.31G 0.04564 0.06898 0.02116 143 640: 100% 8/8 [00:01<00:00, 4.77it/s]\n",
793
- " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.27it/s]\n",
794
- " all 128 929 0.68 0.554 0.632 0.419\n",
795
  "\n",
796
  " Epoch gpu_mem box obj cls labels img_size\n",
797
- " 2/2 5.31G 0.04487 0.06883 0.01998 253 640: 100% 8/8 [00:01<00:00, 4.91it/s]\n",
798
- " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.30it/s]\n",
799
- " all 128 929 0.71 0.544 0.629 0.423\n",
800
  "\n",
801
  "3 epochs completed in 0.003 hours.\n",
802
  "Optimizer stripped from runs/train/exp/weights/last.pt, 14.9MB\n",
@@ -804,80 +822,80 @@
804
  "\n",
805
  "Validating runs/train/exp/weights/best.pt...\n",
806
  "Fusing layers... \n",
807
- "Model Summary: 213 layers, 7225885 parameters, 0 gradients, 16.5 GFLOPs\n",
808
- " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.04it/s]\n",
809
- " all 128 929 0.71 0.544 0.63 0.423\n",
810
- " person 128 254 0.816 0.669 0.774 0.507\n",
811
- " bicycle 128 6 0.799 0.667 0.614 0.371\n",
812
- " car 128 46 0.803 0.355 0.486 0.209\n",
813
- " motorcycle 128 5 0.704 0.6 0.791 0.583\n",
814
- " airplane 128 6 1 0.795 0.995 0.717\n",
815
- " bus 128 7 0.656 0.714 0.72 0.606\n",
816
- " train 128 3 0.852 1 0.995 0.682\n",
817
- " truck 128 12 0.521 0.25 0.395 0.215\n",
818
- " boat 128 6 0.795 0.333 0.445 0.137\n",
819
- " traffic light 128 14 0.576 0.143 0.24 0.161\n",
820
- " stop sign 128 2 0.636 0.5 0.828 0.713\n",
821
- " bench 128 9 0.972 0.444 0.575 0.25\n",
822
- " bird 128 16 0.939 0.968 0.988 0.645\n",
823
- " cat 128 4 0.984 0.75 0.822 0.694\n",
824
- " dog 128 9 0.888 0.667 0.903 0.54\n",
825
- " horse 128 2 0.689 1 0.995 0.697\n",
826
- " elephant 128 17 0.96 0.882 0.943 0.681\n",
827
- " bear 128 1 0.549 1 0.995 0.995\n",
828
- " zebra 128 4 0.86 1 0.995 0.952\n",
829
- " giraffe 128 9 0.822 0.778 0.905 0.57\n",
830
- " backpack 128 6 1 0.309 0.457 0.195\n",
831
- " umbrella 128 18 0.775 0.576 0.74 0.418\n",
832
- " handbag 128 19 0.628 0.105 0.167 0.111\n",
833
- " tie 128 7 0.96 0.571 0.701 0.441\n",
834
- " suitcase 128 4 1 0.895 0.995 0.621\n",
835
- " frisbee 128 5 0.641 0.8 0.798 0.664\n",
836
- " skis 128 1 0.627 1 0.995 0.497\n",
837
- " snowboard 128 7 0.988 0.714 0.768 0.556\n",
838
- " sports ball 128 6 0.671 0.5 0.579 0.339\n",
839
- " kite 128 10 0.631 0.515 0.598 0.221\n",
840
- " baseball bat 128 4 0.47 0.456 0.277 0.137\n",
841
- " baseball glove 128 7 0.459 0.429 0.334 0.182\n",
842
- " skateboard 128 5 0.7 0.48 0.736 0.548\n",
843
- " tennis racket 128 7 0.559 0.571 0.538 0.315\n",
844
- " bottle 128 18 0.607 0.389 0.484 0.282\n",
845
- " wine glass 128 16 0.722 0.812 0.82 0.385\n",
846
- " cup 128 36 0.881 0.361 0.532 0.312\n",
847
- " fork 128 6 0.384 0.167 0.239 0.191\n",
848
- " knife 128 16 0.908 0.616 0.681 0.443\n",
849
- " spoon 128 22 0.836 0.364 0.536 0.264\n",
850
- " bowl 128 28 0.793 0.536 0.633 0.471\n",
851
- " banana 128 1 0 0 0.142 0.0995\n",
852
- " sandwich 128 2 0 0 0.0951 0.0717\n",
853
- " orange 128 4 1 0 0.67 0.317\n",
854
- " broccoli 128 11 0.345 0.182 0.283 0.243\n",
855
- " carrot 128 24 0.688 0.459 0.612 0.402\n",
856
- " hot dog 128 2 0.424 0.771 0.497 0.473\n",
857
- " pizza 128 5 0.622 1 0.824 0.551\n",
858
- " donut 128 14 0.703 1 0.952 0.853\n",
859
- " cake 128 4 0.733 1 0.945 0.777\n",
860
- " chair 128 35 0.512 0.486 0.488 0.222\n",
861
- " couch 128 6 0.68 0.36 0.746 0.406\n",
862
- " potted plant 128 14 0.797 0.714 0.808 0.482\n",
863
- " bed 128 3 1 0 0.474 0.318\n",
864
- " dining table 128 13 0.852 0.445 0.478 0.315\n",
865
- " toilet 128 2 0.512 0.5 0.554 0.487\n",
866
- " tv 128 2 0.754 1 0.995 0.895\n",
867
- " laptop 128 3 1 0 0.39 0.147\n",
868
- " mouse 128 2 1 0 0.0283 0.0226\n",
869
- " remote 128 8 0.747 0.625 0.636 0.488\n",
870
- " cell phone 128 8 0.555 0.166 0.417 0.222\n",
871
- " microwave 128 3 0.417 1 0.995 0.732\n",
872
- " oven 128 5 0.37 0.4 0.432 0.249\n",
873
- " sink 128 6 0.356 0.167 0.269 0.149\n",
874
- " refrigerator 128 5 0.705 0.8 0.814 0.45\n",
875
- " book 128 29 0.628 0.138 0.298 0.136\n",
876
- " clock 128 9 0.857 0.778 0.893 0.574\n",
877
- " vase 128 2 0.242 1 0.663 0.622\n",
878
- " scissors 128 1 1 0 0.0207 0.00207\n",
879
- " teddy bear 128 21 0.847 0.381 0.622 0.345\n",
880
- " toothbrush 128 5 0.99 0.6 0.662 0.45\n",
881
  "Results saved to \u001b[1mruns/train/exp\u001b[0m\n"
882
  ]
883
  }
 
6
  "name": "YOLOv5 Tutorial",
7
  "provenance": [],
8
  "collapsed_sections": [],
9
+ "machine_shape": "hm",
10
  "include_colab_link": true
11
  },
12
  "kernelspec": {
 
16
  "accelerator": "GPU",
17
  "widgets": {
18
  "application/vnd.jupyter.widget-state+json": {
19
+ "d90eeb56398f458086e3b2b41dbd9fec": {
20
  "model_module": "@jupyter-widgets/controls",
21
  "model_name": "HBoxModel",
22
  "model_module_version": "1.5.0",
23
  "state": {
 
24
  "_dom_classes": [],
25
+ "_model_module": "@jupyter-widgets/controls",
 
26
  "_model_module_version": "1.5.0",
27
+ "_model_name": "HBoxModel",
28
  "_view_count": null,
29
+ "_view_module": "@jupyter-widgets/controls",
30
  "_view_module_version": "1.5.0",
31
+ "_view_name": "HBoxView",
32
  "box_style": "",
 
 
33
  "children": [
34
+ "IPY_MODEL_d91d8347f17349a4987cea29eac0a49c",
35
+ "IPY_MODEL_8f4ffda703ac4348ab7edf1d12a188e1",
36
+ "IPY_MODEL_8c2d91f564de45f8a403386eeeccac27"
37
+ ],
38
+ "layout": "IPY_MODEL_5dd95d3eda8b49f7910620edcdcbdcdc"
39
  }
40
  },
41
+ "d91d8347f17349a4987cea29eac0a49c": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  "model_module": "@jupyter-widgets/controls",
43
  "model_name": "HTMLModel",
44
  "model_module_version": "1.5.0",
45
  "state": {
 
 
46
  "_dom_classes": [],
47
+ "_model_module": "@jupyter-widgets/controls",
 
 
 
48
  "_model_module_version": "1.5.0",
49
+ "_model_name": "HTMLModel",
50
  "_view_count": null,
51
+ "_view_module": "@jupyter-widgets/controls",
52
  "_view_module_version": "1.5.0",
53
+ "_view_name": "HTMLView",
54
+ "description": "",
55
  "description_tooltip": null,
56
+ "layout": "IPY_MODEL_520e5b7e80eb450188261cffbc574d25",
57
+ "placeholder": "​",
58
+ "style": "IPY_MODEL_3cef138c5f7743858bb0f87b65dd3c76",
59
+ "value": "100%"
60
  }
61
  },
62
+ "8f4ffda703ac4348ab7edf1d12a188e1": {
63
  "model_module": "@jupyter-widgets/controls",
64
  "model_name": "FloatProgressModel",
65
  "model_module_version": "1.5.0",
66
  "state": {
 
 
67
  "_dom_classes": [],
68
+ "_model_module": "@jupyter-widgets/controls",
 
 
 
 
69
  "_model_module_version": "1.5.0",
70
+ "_model_name": "FloatProgressModel",
71
  "_view_count": null,
72
+ "_view_module": "@jupyter-widgets/controls",
73
  "_view_module_version": "1.5.0",
74
+ "_view_name": "ProgressView",
75
+ "bar_style": "success",
76
+ "description": "",
77
  "description_tooltip": null,
78
+ "layout": "IPY_MODEL_c3782c6dda80400ba7f8c5345624bf87",
79
+ "max": 818322941,
80
+ "min": 0,
81
+ "orientation": "horizontal",
82
+ "style": "IPY_MODEL_11415bab172a4904b73e29ff60f6fce1",
83
+ "value": 818322941
84
  }
85
  },
86
+ "8c2d91f564de45f8a403386eeeccac27": {
87
  "model_module": "@jupyter-widgets/controls",
88
  "model_name": "HTMLModel",
89
  "model_module_version": "1.5.0",
90
  "state": {
 
 
91
  "_dom_classes": [],
92
+ "_model_module": "@jupyter-widgets/controls",
 
 
 
93
  "_model_module_version": "1.5.0",
94
+ "_model_name": "HTMLModel",
95
  "_view_count": null,
96
+ "_view_module": "@jupyter-widgets/controls",
97
  "_view_module_version": "1.5.0",
98
+ "_view_name": "HTMLView",
99
+ "description": "",
100
  "description_tooltip": null,
101
+ "layout": "IPY_MODEL_eac18040908042dbae67a47d23e95b47",
102
+ "placeholder": "​",
103
+ "style": "IPY_MODEL_e0fc1d6eb478469c9098aa9518d7b358",
104
+ "value": " 780M/780M [01:17&lt;00:00, 17.7MB/s]"
105
  }
106
  },
107
+ "5dd95d3eda8b49f7910620edcdcbdcdc": {
108
+ "model_module": "@jupyter-widgets/base",
109
+ "model_name": "LayoutModel",
110
+ "model_module_version": "1.2.0",
111
  "state": {
112
+ "_model_module": "@jupyter-widgets/base",
113
+ "_model_module_version": "1.2.0",
114
+ "_model_name": "LayoutModel",
 
 
115
  "_view_count": null,
116
+ "_view_module": "@jupyter-widgets/base",
117
  "_view_module_version": "1.2.0",
118
+ "_view_name": "LayoutView",
119
+ "align_content": null,
120
+ "align_items": null,
121
+ "align_self": null,
122
+ "border": null,
123
+ "bottom": null,
124
+ "display": null,
125
+ "flex": null,
126
+ "flex_flow": null,
127
+ "grid_area": null,
128
+ "grid_auto_columns": null,
129
+ "grid_auto_flow": null,
130
+ "grid_auto_rows": null,
131
+ "grid_column": null,
132
+ "grid_gap": null,
133
+ "grid_row": null,
134
+ "grid_template_areas": null,
135
+ "grid_template_columns": null,
136
+ "grid_template_rows": null,
137
+ "height": null,
138
+ "justify_content": null,
139
+ "justify_items": null,
140
+ "left": null,
141
+ "margin": null,
142
+ "max_height": null,
143
+ "max_width": null,
144
+ "min_height": null,
145
+ "min_width": null,
146
+ "object_fit": null,
147
+ "object_position": null,
148
+ "order": null,
149
+ "overflow": null,
150
+ "overflow_x": null,
151
+ "overflow_y": null,
152
+ "padding": null,
153
+ "right": null,
154
+ "top": null,
155
+ "visibility": null,
156
+ "width": null
157
  }
158
  },
159
+ "520e5b7e80eb450188261cffbc574d25": {
160
  "model_module": "@jupyter-widgets/base",
161
  "model_name": "LayoutModel",
162
  "model_module_version": "1.2.0",
163
  "state": {
164
+ "_model_module": "@jupyter-widgets/base",
 
 
 
 
 
165
  "_model_module_version": "1.2.0",
166
+ "_model_name": "LayoutModel",
167
  "_view_count": null,
168
+ "_view_module": "@jupyter-widgets/base",
169
+ "_view_module_version": "1.2.0",
170
+ "_view_name": "LayoutView",
171
+ "align_content": null,
172
  "align_items": null,
173
+ "align_self": null,
174
+ "border": null,
175
  "bottom": null,
176
+ "display": null,
177
+ "flex": null,
178
+ "flex_flow": null,
 
 
 
179
  "grid_area": null,
180
+ "grid_auto_columns": null,
181
+ "grid_auto_flow": null,
182
+ "grid_auto_rows": null,
183
+ "grid_column": null,
184
+ "grid_gap": null,
185
+ "grid_row": null,
186
+ "grid_template_areas": null,
187
  "grid_template_columns": null,
188
+ "grid_template_rows": null,
189
+ "height": null,
190
+ "justify_content": null,
191
  "justify_items": null,
192
+ "left": null,
193
+ "margin": null,
194
  "max_height": null,
 
 
 
 
 
 
 
 
195
  "max_width": null,
196
+ "min_height": null,
197
+ "min_width": null,
 
 
198
  "object_fit": null,
199
+ "object_position": null,
200
+ "order": null,
201
+ "overflow": null,
202
+ "overflow_x": null,
203
+ "overflow_y": null,
204
+ "padding": null,
205
+ "right": null,
206
+ "top": null,
207
+ "visibility": null,
208
+ "width": null
209
  }
210
  },
211
+ "3cef138c5f7743858bb0f87b65dd3c76": {
212
  "model_module": "@jupyter-widgets/controls",
213
+ "model_name": "DescriptionStyleModel",
214
  "model_module_version": "1.5.0",
215
  "state": {
216
+ "_model_module": "@jupyter-widgets/controls",
 
 
 
217
  "_model_module_version": "1.5.0",
218
+ "_model_name": "DescriptionStyleModel",
219
  "_view_count": null,
220
+ "_view_module": "@jupyter-widgets/base",
221
  "_view_module_version": "1.2.0",
222
+ "_view_name": "StyleView",
223
+ "description_width": ""
224
  }
225
  },
226
+ "c3782c6dda80400ba7f8c5345624bf87": {
227
  "model_module": "@jupyter-widgets/base",
228
  "model_name": "LayoutModel",
229
  "model_module_version": "1.2.0",
230
  "state": {
231
+ "_model_module": "@jupyter-widgets/base",
 
 
 
 
 
232
  "_model_module_version": "1.2.0",
233
+ "_model_name": "LayoutModel",
234
  "_view_count": null,
235
+ "_view_module": "@jupyter-widgets/base",
236
+ "_view_module_version": "1.2.0",
237
+ "_view_name": "LayoutView",
238
+ "align_content": null,
239
  "align_items": null,
240
+ "align_self": null,
241
+ "border": null,
242
  "bottom": null,
243
+ "display": null,
244
+ "flex": null,
245
+ "flex_flow": null,
 
 
 
246
  "grid_area": null,
247
+ "grid_auto_columns": null,
248
+ "grid_auto_flow": null,
249
+ "grid_auto_rows": null,
250
+ "grid_column": null,
251
+ "grid_gap": null,
252
+ "grid_row": null,
253
+ "grid_template_areas": null,
254
  "grid_template_columns": null,
255
+ "grid_template_rows": null,
256
+ "height": null,
257
+ "justify_content": null,
258
  "justify_items": null,
259
+ "left": null,
260
+ "margin": null,
261
  "max_height": null,
 
 
 
 
 
 
 
 
262
  "max_width": null,
263
+ "min_height": null,
264
+ "min_width": null,
 
 
265
  "object_fit": null,
266
+ "object_position": null,
267
+ "order": null,
268
+ "overflow": null,
269
+ "overflow_x": null,
270
+ "overflow_y": null,
271
+ "padding": null,
272
+ "right": null,
273
+ "top": null,
274
+ "visibility": null,
275
+ "width": null
276
  }
277
  },
278
+ "11415bab172a4904b73e29ff60f6fce1": {
279
  "model_module": "@jupyter-widgets/controls",
280
+ "model_name": "ProgressStyleModel",
281
  "model_module_version": "1.5.0",
282
  "state": {
283
+ "_model_module": "@jupyter-widgets/controls",
 
 
 
284
  "_model_module_version": "1.5.0",
285
+ "_model_name": "ProgressStyleModel",
286
  "_view_count": null,
287
+ "_view_module": "@jupyter-widgets/base",
288
  "_view_module_version": "1.2.0",
289
+ "_view_name": "StyleView",
290
+ "bar_color": null,
291
+ "description_width": ""
292
  }
293
  },
294
+ "eac18040908042dbae67a47d23e95b47": {
295
  "model_module": "@jupyter-widgets/base",
296
  "model_name": "LayoutModel",
297
  "model_module_version": "1.2.0",
298
  "state": {
299
+ "_model_module": "@jupyter-widgets/base",
 
 
 
 
 
300
  "_model_module_version": "1.2.0",
301
+ "_model_name": "LayoutModel",
302
  "_view_count": null,
303
+ "_view_module": "@jupyter-widgets/base",
304
+ "_view_module_version": "1.2.0",
305
+ "_view_name": "LayoutView",
306
+ "align_content": null,
307
  "align_items": null,
308
+ "align_self": null,
309
+ "border": null,
310
  "bottom": null,
311
+ "display": null,
312
+ "flex": null,
313
+ "flex_flow": null,
 
 
 
314
  "grid_area": null,
315
+ "grid_auto_columns": null,
316
+ "grid_auto_flow": null,
317
+ "grid_auto_rows": null,
318
+ "grid_column": null,
319
+ "grid_gap": null,
320
+ "grid_row": null,
321
+ "grid_template_areas": null,
322
  "grid_template_columns": null,
323
+ "grid_template_rows": null,
324
+ "height": null,
325
+ "justify_content": null,
326
  "justify_items": null,
327
+ "left": null,
328
+ "margin": null,
329
  "max_height": null,
 
 
 
 
 
 
 
 
330
  "max_width": null,
331
+ "min_height": null,
332
+ "min_width": null,
333
+ "object_fit": null,
334
+ "object_position": null,
335
  "order": null,
336
+ "overflow": null,
337
+ "overflow_x": null,
338
+ "overflow_y": null,
339
+ "padding": null,
340
+ "right": null,
341
+ "top": null,
342
+ "visibility": null,
343
+ "width": null
344
+ }
345
+ },
346
+ "e0fc1d6eb478469c9098aa9518d7b358": {
347
+ "model_module": "@jupyter-widgets/controls",
348
+ "model_name": "DescriptionStyleModel",
349
+ "model_module_version": "1.5.0",
350
+ "state": {
351
+ "_model_module": "@jupyter-widgets/controls",
352
+ "_model_module_version": "1.5.0",
353
+ "_model_name": "DescriptionStyleModel",
354
+ "_view_count": null,
355
+ "_view_module": "@jupyter-widgets/base",
356
  "_view_module_version": "1.2.0",
357
+ "_view_name": "StyleView",
358
+ "description_width": ""
 
 
 
 
 
359
  }
360
  }
361
  }
 
369
  "colab_type": "text"
370
  },
371
  "source": [
372
+ "<a href=\"https://colab.research.google.com/github/ultralytics/yolov5/blob/colab/tutorial.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
373
  ]
374
  },
375
  {
 
403
  "colab": {
404
  "base_uri": "https://localhost:8080/"
405
  },
406
+ "outputId": "ebf225bd-e109-4dbd-8561-3b15514ca47c"
407
  },
408
  "source": [
409
  "!git clone https://github.com/ultralytics/yolov5 # clone\n",
 
414
  "import utils\n",
415
  "display = utils.notebook_init() # checks"
416
  ],
417
+ "execution_count": 1,
418
  "outputs": [
419
+ {
420
+ "output_type": "stream",
421
+ "name": "stderr",
422
+ "text": [
423
+ "YOLOv5 🚀 v6.1-174-gc4cb7c6 torch 1.11.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n"
424
+ ]
425
+ },
426
  {
427
  "output_type": "stream",
428
  "name": "stdout",
429
  "text": [
430
+ "Setup complete ✅ (8 CPUs, 51.0 GB RAM, 38.2/166.8 GB disk)\n"
 
431
  ]
432
  }
433
  ]
 
460
  "colab": {
461
  "base_uri": "https://localhost:8080/"
462
  },
463
+ "outputId": "2f43338d-f533-4277-ef9f-b37b565e2702"
464
  },
465
  "source": [
466
  "!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images\n",
467
  "display.Image(filename='runs/detect/exp/zidane.jpg', width=600)"
468
  ],
469
+ "execution_count": 2,
470
  "outputs": [
471
  {
472
  "output_type": "stream",
473
  "name": "stdout",
474
  "text": [
475
+ "\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov5s.pt'], source=data/images, data=data/coco128.yaml, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False\n",
476
+ "YOLOv5 🚀 v6.1-174-gc4cb7c6 torch 1.11.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
477
+ "\n",
478
+ "Downloading https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5s.pt to yolov5s.pt...\n",
479
+ "100% 14.1M/14.1M [00:00<00:00, 220MB/s]\n",
480
  "\n",
481
  "Fusing layers... \n",
482
+ "YOLOv5s summary: 213 layers, 7225885 parameters, 0 gradients\n",
483
+ "image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, Done. (0.012s)\n",
484
+ "image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.013s)\n",
485
+ "Speed: 0.5ms pre-process, 12.5ms inference, 17.3ms NMS per image at shape (1, 3, 640, 640)\n",
486
  "Results saved to \u001b[1mruns/detect/exp\u001b[0m\n"
487
  ]
488
  }
 
524
  "id": "WQPtK1QYVaD_",
525
  "colab": {
526
  "base_uri": "https://localhost:8080/",
527
+ "height": 49,
528
  "referenced_widgets": [
529
+ "d90eeb56398f458086e3b2b41dbd9fec",
530
+ "d91d8347f17349a4987cea29eac0a49c",
531
+ "8f4ffda703ac4348ab7edf1d12a188e1",
532
+ "8c2d91f564de45f8a403386eeeccac27",
533
+ "5dd95d3eda8b49f7910620edcdcbdcdc",
534
+ "520e5b7e80eb450188261cffbc574d25",
535
+ "3cef138c5f7743858bb0f87b65dd3c76",
536
+ "c3782c6dda80400ba7f8c5345624bf87",
537
+ "11415bab172a4904b73e29ff60f6fce1",
538
+ "eac18040908042dbae67a47d23e95b47",
539
+ "e0fc1d6eb478469c9098aa9518d7b358"
540
  ]
541
  },
542
+ "outputId": "26f3c005-cc13-4b7c-8523-844b56a0b0e3"
543
  },
544
  "source": [
545
  "# Download COCO val\n",
546
  "torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017val.zip', 'tmp.zip')\n",
547
  "!unzip -q tmp.zip -d ../datasets && rm tmp.zip"
548
  ],
549
+ "execution_count": 3,
550
  "outputs": [
551
  {
552
  "output_type": "display_data",
553
  "data": {
 
 
 
 
 
554
  "text/plain": [
555
  " 0%| | 0.00/780M [00:00<?, ?B/s]"
556
+ ],
557
+ "application/vnd.jupyter.widget-view+json": {
558
+ "version_major": 2,
559
+ "version_minor": 0,
560
+ "model_id": "d90eeb56398f458086e3b2b41dbd9fec"
561
+ }
562
  },
563
  "metadata": {}
564
  }
 
571
  "colab": {
572
  "base_uri": "https://localhost:8080/"
573
  },
574
+ "outputId": "c73097d6-02a8-43af-9962-ba6500b793ff"
575
  },
576
  "source": [
577
  "# Run YOLOv5x on COCO val\n",
578
  "!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half"
579
  ],
580
+ "execution_count": 4,
581
  "outputs": [
582
  {
583
  "output_type": "stream",
584
  "name": "stdout",
585
  "text": [
586
+ "\u001b[34m\u001b[1mval: \u001b[0mdata=/content/yolov5/data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.65, task=val, device=, workers=8, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True, dnn=False\n",
587
+ "YOLOv5 🚀 v6.1-174-gc4cb7c6 torch 1.11.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
588
  "\n",
589
+ "Downloading https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5x.pt to yolov5x.pt...\n",
590
+ "100% 166M/166M [00:05<00:00, 33.5MB/s]\n",
591
  "\n",
592
  "Fusing layers... \n",
593
+ "YOLOv5x summary: 444 layers, 86705005 parameters, 0 gradients\n",
594
+ "Downloading https://ultralytics.com/assets/Arial.ttf to /root/.config/Ultralytics/Arial.ttf...\n",
595
+ "100% 755k/755k [00:00<00:00, 49.6MB/s]\n",
596
+ "\u001b[34m\u001b[1mval: \u001b[0mScanning '/content/datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupt: 100% 5000/5000 [00:00<00:00, 10667.19it/s]\n",
597
+ "\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /content/datasets/coco/val2017.cache\n",
598
+ " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [00:58<00:00, 2.70it/s]\n",
599
+ " all 5000 36335 0.743 0.626 0.683 0.496\n",
600
+ "Speed: 0.1ms pre-process, 4.8ms inference, 1.2ms NMS per image at shape (32, 3, 640, 640)\n",
601
  "\n",
602
  "Evaluating pycocotools mAP... saving runs/val/exp/yolov5x_predictions.json...\n",
603
  "loading annotations into memory...\n",
604
+ "Done (t=0.38s)\n",
605
  "creating index...\n",
606
  "index created!\n",
607
  "Loading and preparing results...\n",
608
+ "DONE (t=5.42s)\n",
609
  "creating index...\n",
610
  "index created!\n",
611
  "Running per image evaluation...\n",
612
  "Evaluate annotation type *bbox*\n",
613
+ "DONE (t=72.67s).\n",
614
  "Accumulating evaluation results...\n",
615
+ "DONE (t=13.48s).\n",
616
+ " Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.506\n",
617
+ " Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.688\n",
618
+ " Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.549\n",
619
+ " Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.340\n",
620
+ " Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.557\n",
621
+ " Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.651\n",
622
+ " Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.382\n",
623
+ " Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.631\n",
624
+ " Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.684\n",
625
+ " Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.528\n",
626
+ " Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.737\n",
627
+ " Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.833\n",
628
  "Results saved to \u001b[1mruns/val/exp\u001b[0m\n"
629
  ]
630
  }
 
731
  "colab": {
732
  "base_uri": "https://localhost:8080/"
733
  },
734
+ "outputId": "6735ae8b-fd75-4ecd-9d32-71d1881e2481"
735
  },
736
  "source": [
737
  "# Train YOLOv5s on COCO128 for 3 epochs\n",
738
  "!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache"
739
  ],
740
+ "execution_count": 5,
741
  "outputs": [
742
  {
743
  "output_type": "stream",
744
  "name": "stdout",
745
  "text": [
746
+ "\u001b[34m\u001b[1mtrain: \u001b[0mweights=yolov5s.pt, cfg=, data=coco128.yaml, hyp=data/hyps/hyp.scratch-low.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, noplots=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, optimizer=SGD, sync_bn=False, workers=8, project=runs/train, name=exp, exist_ok=False, quad=False, cos_lr=False, label_smoothing=0.0, patience=100, freeze=[0], save_period=-1, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest\n",
747
  "\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov5 ✅\n",
748
+ "YOLOv5 🚀 v6.1-174-gc4cb7c6 torch 1.11.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
749
  "\n",
750
+ "\u001b[34m\u001b[1mhyperparameters: \u001b[0mlr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0\n",
751
  "\u001b[34m\u001b[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)\n",
752
  "\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/\n",
753
  "\n",
754
+ "Dataset not found ⚠, missing paths ['/content/datasets/coco128/images/train2017']\n",
755
+ "Downloading https://ultralytics.com/assets/coco128.zip to coco128.zip...\n",
756
+ "100% 6.66M/6.66M [00:00<00:00, 41.0MB/s]\n",
757
+ "Dataset download success ✅ (0.9s), saved to \u001b[1m/content/datasets\u001b[0m\n",
758
+ "\n",
759
  " from n params module arguments \n",
760
  " 0 -1 1 3520 models.common.Conv [3, 32, 6, 2, 2] \n",
761
  " 1 -1 1 18560 models.common.Conv [32, 64, 3, 2] \n",
 
782
  " 22 [-1, 10] 1 0 models.common.Concat [1] \n",
783
  " 23 -1 1 1182720 models.common.C3 [512, 512, 1, False] \n",
784
  " 24 [17, 20, 23] 1 229245 models.yolo.Detect [80, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]\n",
785
+ "Model summary: 270 layers, 7235389 parameters, 7235389 gradients, 16.5 GFLOPs\n",
786
  "\n",
787
  "Transferred 349/349 items from yolov5s.pt\n",
788
  "Scaled weight_decay = 0.0005\n",
789
+ "\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 57 weight (no decay), 60 weight, 60 bias\n",
790
  "\u001b[34m\u001b[1malbumentations: \u001b[0mversion 1.0.3 required by YOLOv5, but version 0.1.12 is currently installed\n",
791
+ "\u001b[34m\u001b[1mtrain: \u001b[0mScanning '/content/datasets/coco128/labels/train2017' images and labels...128 found, 0 missing, 2 empty, 0 corrupt: 100% 128/128 [00:00<00:00, 405.04it/s]\n",
792
+ "\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /content/datasets/coco128/labels/train2017.cache\n",
793
+ "\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 977.19it/s]\n",
794
+ "\u001b[34m\u001b[1mval: \u001b[0mScanning '/content/datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupt: 100% 128/128 [00:00<?, ?it/s]\n",
795
+ "\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 219.82it/s]\n",
796
+ "Plotting labels to runs/train/exp/labels.jpg... \n",
797
  "\n",
798
+ "\u001b[34m\u001b[1mAutoAnchor: \u001b[0m4.27 anchors/target, 0.994 Best Possible Recall (BPR). Current anchors are a good fit to dataset ✅\n",
799
  "Image sizes 640 train, 640 val\n",
800
+ "Using 8 dataloader workers\n",
801
  "Logging results to \u001b[1mruns/train/exp\u001b[0m\n",
802
  "Starting training for 3 epochs...\n",
803
  "\n",
804
  " Epoch gpu_mem box obj cls labels img_size\n",
805
+ " 0/2 3.72G 0.04609 0.06259 0.01898 260 640: 100% 8/8 [00:03<00:00, 2.30it/s]\n",
806
+ " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 6.54it/s]\n",
807
+ " all 128 929 0.727 0.63 0.717 0.469\n",
808
  "\n",
809
  " Epoch gpu_mem box obj cls labels img_size\n",
810
+ " 1/2 4.57G 0.04466 0.06904 0.01721 210 640: 100% 8/8 [00:00<00:00, 8.54it/s]\n",
811
+ " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 6.79it/s]\n",
812
+ " all 128 929 0.76 0.646 0.746 0.48\n",
813
  "\n",
814
  " Epoch gpu_mem box obj cls labels img_size\n",
815
+ " 2/2 4.57G 0.04489 0.06446 0.01634 269 640: 100% 8/8 [00:00<00:00, 9.18it/s]\n",
816
+ " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 6.04it/s]\n",
817
+ " all 128 929 0.807 0.641 0.76 0.494\n",
818
  "\n",
819
  "3 epochs completed in 0.003 hours.\n",
820
  "Optimizer stripped from runs/train/exp/weights/last.pt, 14.9MB\n",
 
822
  "\n",
823
  "Validating runs/train/exp/weights/best.pt...\n",
824
  "Fusing layers... \n",
825
+ "Model summary: 213 layers, 7225885 parameters, 0 gradients, 16.5 GFLOPs\n",
826
+ " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.31it/s]\n",
827
+ " all 128 929 0.809 0.642 0.76 0.493\n",
828
+ " person 128 254 0.872 0.693 0.82 0.519\n",
829
+ " bicycle 128 6 0.75 0.501 0.623 0.376\n",
830
+ " car 128 46 0.666 0.521 0.557 0.207\n",
831
+ " motorcycle 128 5 1 0.919 0.995 0.678\n",
832
+ " airplane 128 6 0.948 1 0.995 0.751\n",
833
+ " bus 128 7 0.84 0.714 0.723 0.642\n",
834
+ " train 128 3 1 0.631 0.863 0.561\n",
835
+ " truck 128 12 0.638 0.417 0.481 0.241\n",
836
+ " boat 128 6 1 0.299 0.418 0.0863\n",
837
+ " traffic light 128 14 0.637 0.254 0.372 0.225\n",
838
+ " stop sign 128 2 0.812 1 0.995 0.796\n",
839
+ " bench 128 9 0.737 0.444 0.615 0.233\n",
840
+ " bird 128 16 0.965 1 0.995 0.666\n",
841
+ " cat 128 4 0.856 1 0.995 0.797\n",
842
+ " dog 128 9 1 0.65 0.886 0.637\n",
843
+ " horse 128 2 0.822 1 0.995 0.647\n",
844
+ " elephant 128 17 0.963 0.882 0.932 0.69\n",
845
+ " bear 128 1 0.699 1 0.995 0.895\n",
846
+ " zebra 128 4 0.877 1 0.995 0.947\n",
847
+ " giraffe 128 9 0.898 1 0.995 0.644\n",
848
+ " backpack 128 6 0.994 0.667 0.808 0.333\n",
849
+ " umbrella 128 18 0.828 0.667 0.865 0.493\n",
850
+ " handbag 128 19 0.882 0.211 0.357 0.175\n",
851
+ " tie 128 7 0.834 0.719 0.837 0.493\n",
852
+ " suitcase 128 4 0.853 1 0.995 0.522\n",
853
+ " frisbee 128 5 0.706 0.8 0.8 0.74\n",
854
+ " skis 128 1 0.796 1 0.995 0.398\n",
855
+ " snowboard 128 7 0.903 0.714 0.852 0.546\n",
856
+ " sports ball 128 6 0.621 0.667 0.603 0.293\n",
857
+ " kite 128 10 0.846 0.553 0.625 0.259\n",
858
+ " baseball bat 128 4 0.465 0.25 0.384 0.163\n",
859
+ " baseball glove 128 7 0.731 0.429 0.466 0.304\n",
860
+ " skateboard 128 5 1 0.557 0.858 0.49\n",
861
+ " tennis racket 128 7 0.78 0.429 0.635 0.298\n",
862
+ " bottle 128 18 0.55 0.339 0.578 0.283\n",
863
+ " wine glass 128 16 0.7 0.938 0.925 0.499\n",
864
+ " cup 128 36 0.802 0.789 0.844 0.492\n",
865
+ " fork 128 6 1 0.326 0.439 0.302\n",
866
+ " knife 128 16 0.779 0.5 0.68 0.392\n",
867
+ " spoon 128 22 0.821 0.417 0.629 0.338\n",
868
+ " bowl 128 28 0.781 0.607 0.753 0.51\n",
869
+ " banana 128 1 0.923 1 0.995 0.0995\n",
870
+ " sandwich 128 2 1 0 0.606 0.545\n",
871
+ " orange 128 4 0.959 1 0.995 0.691\n",
872
+ " broccoli 128 11 0.483 0.455 0.466 0.337\n",
873
+ " carrot 128 24 0.85 0.542 0.73 0.506\n",
874
+ " hot dog 128 2 0.587 1 0.828 0.712\n",
875
+ " pizza 128 5 0.882 0.8 0.962 0.687\n",
876
+ " donut 128 14 0.702 1 0.981 0.846\n",
877
+ " cake 128 4 0.875 1 0.995 0.858\n",
878
+ " chair 128 35 0.639 0.608 0.624 0.303\n",
879
+ " couch 128 6 1 0.592 0.857 0.539\n",
880
+ " potted plant 128 14 0.76 0.786 0.835 0.471\n",
881
+ " bed 128 3 1 0 0.806 0.557\n",
882
+ " dining table 128 13 0.824 0.362 0.602 0.403\n",
883
+ " toilet 128 2 0.978 1 0.995 0.846\n",
884
+ " tv 128 2 0.702 1 0.995 0.796\n",
885
+ " laptop 128 3 1 0 0.83 0.532\n",
886
+ " mouse 128 2 1 0 0.0931 0.0466\n",
887
+ " remote 128 8 1 0.6 0.659 0.534\n",
888
+ " cell phone 128 8 0.712 0.25 0.439 0.204\n",
889
+ " microwave 128 3 0.811 1 0.995 0.734\n",
890
+ " oven 128 5 0.46 0.4 0.44 0.29\n",
891
+ " sink 128 6 0.359 0.167 0.302 0.211\n",
892
+ " refrigerator 128 5 0.657 0.8 0.804 0.532\n",
893
+ " book 128 29 0.624 0.207 0.298 0.165\n",
894
+ " clock 128 9 0.798 0.889 0.888 0.692\n",
895
+ " vase 128 2 0.495 1 0.995 0.92\n",
896
+ " scissors 128 1 1 0 0.995 0.199\n",
897
+ " teddy bear 128 21 0.871 0.646 0.826 0.527\n",
898
+ " toothbrush 128 5 0.828 1 0.962 0.647\n",
899
  "Results saved to \u001b[1mruns/train/exp\u001b[0m\n"
900
  ]
901
  }