Skip to content

Y
yolov5
提交 f2b8f3fe authored 作者: Glenn Jocher's avatar Glenn Jocher
浏览文件
操作

Created using Colaboratory

上级 30e674b1
显示空白字符变更
内嵌 并排
正在显示 包含 218 行增加 和 256 行删除
tutorial.ipynb
浏览文件 @ f2b8f3fe
......@@ -16,121 +16,110 @@
"accelerator": "GPU",
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"da0946bcefd9414fa282977f7f609e36": {
"9b8caa3522fc4cbab31e13b5dfc7808d": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"model_module_version": "2.0.0",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_7838c0af44244ccc906c413cea0989d7",
"IPY_MODEL_309ea78b3e814198b4080beb878d5329",
"IPY_MODEL_b2d1d998e5db4ca1a36280902e1647c7"
"IPY_MODEL_574140e4c4bc48c9a171541a02cd0211",
"IPY_MODEL_35e03ce5090346c9ae602891470fc555",
"IPY_MODEL_c942c208e72d46568b476bb0f2d75496"
],
"layout": "IPY_MODEL_e7d7f56c77884717ba122f1d603c0852",
"tabbable": null,
"tooltip": null
"layout": "IPY_MODEL_65881db1db8a4e9c930fab9172d45143"
}
},
"7838c0af44244ccc906c413cea0989d7": {
"574140e4c4bc48c9a171541a02cd0211": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "2.0.0",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_abf60d6b8ea847f9bb358ae2b045458b",
"description_tooltip": null,
"layout": "IPY_MODEL_60b913d755b34d638478e30705a2dde1",
"placeholder": "​",
"style": "IPY_MODEL_379196a2761b4a29aca8ef088dc60c10",
"tabbable": null,
"tooltip": null,
"style": "IPY_MODEL_0856bea36ec148b68522ff9c9eb258d8",
"value": "100%"
}
},
"309ea78b3e814198b4080beb878d5329": {
"35e03ce5090346c9ae602891470fc555": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "2.0.0",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_52b546a356e54174a95049b30cb52c81",
"description_tooltip": null,
"layout": "IPY_MODEL_76879f6f2aa54637a7a07faeea2bd684",
"max": 818322941,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_0889e134327e4aa0a8719d03a0d6941b",
"tabbable": null,
"tooltip": null,
"style": "IPY_MODEL_0ace3934ec6f4d36a1b3a9e086390926",
"value": 818322941
}
},
"b2d1d998e5db4ca1a36280902e1647c7": {
"c942c208e72d46568b476bb0f2d75496": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "2.0.0",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_30f22a3e42d24f10ad9851f40a6703f3",
"description_tooltip": null,
"layout": "IPY_MODEL_d6b7a2243e0c4beca714d99dceec23d6",
"placeholder": "​",
"style": "IPY_MODEL_648b3512bb7d4ccca5d75af36c133e92",
"tabbable": null,
"tooltip": null,
"value": " 780M/780M [01:31<00:00, 12.3MB/s]"
"style": "IPY_MODEL_5966ba6e6f114d8c9d8d1d6b1bd4f4c7",
"value": " 780M/780M [02:19<00:00, 6.24MB/s]"
}
},
"e7d7f56c77884717ba122f1d603c0852": {
"65881db1db8a4e9c930fab9172d45143": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "2.0.0",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
......@@ -158,6 +147,8 @@
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
......@@ -165,25 +156,22 @@
"width": null
}
},
"abf60d6b8ea847f9bb358ae2b045458b": {
"60b913d755b34d638478e30705a2dde1": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "2.0.0",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
......@@ -211,6 +199,8 @@
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
......@@ -218,43 +208,37 @@
"width": null
}
},
"379196a2761b4a29aca8ef088dc60c10": {
"0856bea36ec148b68522ff9c9eb258d8": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLStyleModel",
"model_module_version": "2.0.0",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
"description_width": ""
}
},
"52b546a356e54174a95049b30cb52c81": {
"76879f6f2aa54637a7a07faeea2bd684": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "2.0.0",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
......@@ -282,6 +266,8 @@
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
......@@ -289,41 +275,38 @@
"width": null
}
},
"0889e134327e4aa0a8719d03a0d6941b": {
"0ace3934ec6f4d36a1b3a9e086390926": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "2.0.0",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"30f22a3e42d24f10ad9851f40a6703f3": {
"d6b7a2243e0c4beca714d99dceec23d6": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "2.0.0",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
......@@ -351,6 +334,8 @@
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
......@@ -358,22 +343,19 @@
"width": null
}
},
"648b3512bb7d4ccca5d75af36c133e92": {
"5966ba6e6f114d8c9d8d1d6b1bd4f4c7": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLStyleModel",
"model_module_version": "2.0.0",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
"description_width": ""
}
}
}
......@@ -420,7 +402,7 @@
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "4200fd6f-c6f5-4505-a4f9-a918f3ed1f86"
"outputId": "0f9ee467-cea4-48e8-9050-7a76ae1b6141"
},
"source": [
"!git clone https://github.com/ultralytics/yolov5 # clone\n",
......@@ -431,13 +413,13 @@
"import utils\n",
"display = utils.notebook_init() # checks"
],
"execution_count": null,
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"YOLOv5 🚀 v6.2-41-g8665d55 Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n"
"YOLOv5 🚀 v6.2-56-g30e674b Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n"
]
},
{
......@@ -477,29 +459,29 @@
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "1af15107-bcd1-4e8f-b5bd-0ee1a737e051"
"outputId": "60647b99-e8d4-402c-f444-331bf6746da4"
},
"source": [
"!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images\n",
"# display.Image(filename='runs/detect/exp/zidane.jpg', width=600)"
],
"execution_count": null,
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\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",
"YOLOv5 🚀 v6.2-41-g8665d55 Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"YOLOv5 🚀 v6.2-56-g30e674b Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"\n",
"Downloading https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5s.pt to yolov5s.pt...\n",
"100% 14.1M/14.1M [00:00<00:00, 41.7MB/s]\n",
"100% 14.1M/14.1M [00:00<00:00, 27.8MB/s]\n",
"\n",
"Fusing layers... \n",
"YOLOv5s summary: 213 layers, 7225885 parameters, 0 gradients\n",
"image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, 14.5ms\n",
"image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, 18.9ms\n",
"Speed: 0.5ms pre-process, 16.7ms inference, 21.4ms NMS per image at shape (1, 3, 640, 640)\n",
"image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, 14.8ms\n",
"image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, 20.1ms\n",
"Speed: 0.6ms pre-process, 17.4ms inference, 21.6ms NMS per image at shape (1, 3, 640, 640)\n",
"Results saved to \u001b[1mruns/detect/exp\u001b[0m\n"
]
}
......@@ -531,29 +513,29 @@
"id": "WQPtK1QYVaD_",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 17,
"height": 49,
"referenced_widgets": [
"da0946bcefd9414fa282977f7f609e36",
"7838c0af44244ccc906c413cea0989d7",
"309ea78b3e814198b4080beb878d5329",
"b2d1d998e5db4ca1a36280902e1647c7",
"e7d7f56c77884717ba122f1d603c0852",
"abf60d6b8ea847f9bb358ae2b045458b",
"379196a2761b4a29aca8ef088dc60c10",
"52b546a356e54174a95049b30cb52c81",
"0889e134327e4aa0a8719d03a0d6941b",
"30f22a3e42d24f10ad9851f40a6703f3",
"648b3512bb7d4ccca5d75af36c133e92"
"9b8caa3522fc4cbab31e13b5dfc7808d",
"574140e4c4bc48c9a171541a02cd0211",
"35e03ce5090346c9ae602891470fc555",
"c942c208e72d46568b476bb0f2d75496",
"65881db1db8a4e9c930fab9172d45143",
"60b913d755b34d638478e30705a2dde1",
"0856bea36ec148b68522ff9c9eb258d8",
"76879f6f2aa54637a7a07faeea2bd684",
"0ace3934ec6f4d36a1b3a9e086390926",
"d6b7a2243e0c4beca714d99dceec23d6",
"5966ba6e6f114d8c9d8d1d6b1bd4f4c7"
]
},
"outputId": "5f129105-eca5-4f33-fb1d-981255f814ad"
"outputId": "102dabed-bc31-42fe-9133-d9ce28a2c01e"
},
"source": [
"# Download COCO val\n",
"torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017val.zip', 'tmp.zip') # download (780M - 5000 images)\n",
"!unzip -q tmp.zip -d ../datasets && rm tmp.zip # unzip"
],
"execution_count": null,
"execution_count": 3,
"outputs": [
{
"output_type": "display_data",
......@@ -564,24 +546,7 @@
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "da0946bcefd9414fa282977f7f609e36"
},
"application/json": {
"n": 0,
"total": 818322941,
"elapsed": 0.020366430282592773,
"ncols": null,
"nrows": null,
"prefix": "",
"ascii": false,
"unit": "B",
"unit_scale": true,
"rate": null,
"bar_format": null,
"postfix": null,
"unit_divisor": 1024,
"initial": 0,
"colour": null
"model_id": "9b8caa3522fc4cbab31e13b5dfc7808d"
}
},
"metadata": {}
......@@ -595,60 +560,57 @@
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "40d5d000-abee-46a0-c07d-1066e1662e01"
"outputId": "daf60b1b-b098-4657-c863-584f4c9cf078"
},
"source": [
"# Validate YOLOv5x on COCO val\n",
"!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half"
"# Validate YOLOv5s on COCO val\n",
"!python val.py --weights yolov5s.pt --data coco.yaml --img 640 --half"
],
"execution_count": null,
"execution_count": 4,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\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",
"YOLOv5 🚀 v6.2-41-g8665d55 Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"\n",
"Downloading https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5x.pt to yolov5x.pt...\n",
"100% 166M/166M [00:10<00:00, 16.6MB/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mdata=/content/yolov5/data/coco.yaml, weights=['yolov5s.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.6, 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",
"YOLOv5 🚀 v6.2-56-g30e674b Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"\n",
"Fusing layers... \n",
"YOLOv5x summary: 444 layers, 86705005 parameters, 0 gradients\n",
"YOLOv5s summary: 213 layers, 7225885 parameters, 0 gradients\n",
"Downloading https://ultralytics.com/assets/Arial.ttf to /root/.config/Ultralytics/Arial.ttf...\n",
"100% 755k/755k [00:00<00:00, 1.39MB/s]\n",
"\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, 10506.48it/s]\n",
"100% 755k/755k [00:00<00:00, 52.7MB/s]\n",
"\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, 10509.20it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /content/datasets/coco/val2017.cache\n",
" Class Images Instances P R mAP@.5 mAP@.5:.95: 100% 157/157 [01:06<00:00, 2.36it/s]\n",
" all 5000 36335 0.743 0.625 0.683 0.504\n",
"Speed: 0.1ms pre-process, 4.6ms inference, 1.1ms NMS per image at shape (32, 3, 640, 640)\n",
" Class Images Instances P R mAP@.5 mAP@.5:.95: 100% 157/157 [00:50<00:00, 3.10it/s]\n",
" all 5000 36335 0.67 0.521 0.566 0.371\n",
"Speed: 0.1ms pre-process, 1.0ms inference, 1.5ms NMS per image at shape (32, 3, 640, 640)\n",
"\n",
"Evaluating pycocotools mAP... saving runs/val/exp/yolov5x_predictions.json...\n",
"Evaluating pycocotools mAP... saving runs/val/exp/yolov5s_predictions.json...\n",
"loading annotations into memory...\n",
"Done (t=0.38s)\n",
"Done (t=0.81s)\n",
"creating index...\n",
"index created!\n",
"Loading and preparing results...\n",
"DONE (t=5.49s)\n",
"DONE (t=5.62s)\n",
"creating index...\n",
"index created!\n",
"Running per image evaluation...\n",
"Evaluate annotation type *bbox*\n",
"DONE (t=72.10s).\n",
"DONE (t=77.03s).\n",
"Accumulating evaluation results...\n",
"DONE (t=13.94s).\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.506\n",
" Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.688\n",
" Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.549\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.340\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.558\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.651\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.382\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.631\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.684\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.528\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.737\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.833\n",
"DONE (t=14.63s).\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.374\n",
" Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.572\n",
" Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.402\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.211\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.423\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.489\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.311\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.516\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.566\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.378\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.625\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.724\n",
"Results saved to \u001b[1mruns/val/exp\u001b[0m\n"
]
}
......@@ -715,13 +677,13 @@
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "f0ce0354-7f50-4546-f3f9-672b4b522d59"
"outputId": "baa6d4be-3379-4aab-844a-d5a5396c0e49"
},
"source": [
"# Train YOLOv5s on COCO128 for 3 epochs\n",
"!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache"
],
"execution_count": null,
"execution_count": 5,
"outputs": [
{
"output_type": "stream",
......@@ -729,7 +691,7 @@
"text": [
"\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, seed=0, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest\n",
"\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov5 ✅\n",
"YOLOv5 🚀 v6.2-41-g8665d55 Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"YOLOv5 🚀 v6.2-56-g30e674b Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"\n",
"\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",
"\u001b[34m\u001b[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs in Weights & Biases\n",
......@@ -738,8 +700,8 @@
"\n",
"Dataset not found ⚠️, missing paths ['/content/datasets/coco128/images/train2017']\n",
"Downloading https://ultralytics.com/assets/coco128.zip to coco128.zip...\n",
"100% 6.66M/6.66M [00:00<00:00, 76.7MB/s]\n",
"Dataset download success ✅ (0.5s), saved to \u001b[1m/content/datasets\u001b[0m\n",
"100% 6.66M/6.66M [00:00<00:00, 41.1MB/s]\n",
"Dataset download success ✅ (0.8s), saved to \u001b[1m/content/datasets\u001b[0m\n",
"\n",
" from n params module arguments \n",
" 0 -1 1 3520 models.common.Conv [3, 32, 6, 2, 2] \n",
......@@ -773,11 +735,11 @@
"\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n",
"\u001b[34m\u001b[1moptimizer:\u001b[0m SGD(lr=0.01) with parameter groups 57 weight(decay=0.0), 60 weight(decay=0.0005), 60 bias\n",
"\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01), CLAHE(p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8))\n",
"\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, 7984.87it/s]\n",
"\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, 9659.25it/s]\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /content/datasets/coco128/labels/train2017.cache\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 1018.19it/s]\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 951.31it/s]\n",
"\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",
"\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 246.87it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 274.67it/s]\n",
"\n",
"\u001b[34m\u001b[1mAutoAnchor: \u001b[0m4.27 anchors/target, 0.994 Best Possible Recall (BPR). Current anchors are a good fit to dataset ✅\n",
"Plotting labels to runs/train/exp/labels.jpg... \n",
......@@ -787,19 +749,19 @@
"Starting training for 3 epochs...\n",
"\n",
" Epoch GPU_mem box_loss obj_loss cls_loss Instances Size\n",
" 0/2 3.77G 0.04529 0.06712 0.01835 323 640: 100% 8/8 [00:04<00:00, 1.96it/s]\n",
" Class Images Instances P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.12it/s]\n",
" all 128 929 0.647 0.611 0.68 0.449\n",
" 0/2 3.44G 0.04529 0.06712 0.01835 323 640: 100% 8/8 [00:04<00:00, 1.71it/s]\n",
" Class Images Instances P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.02it/s]\n",
" all 128 929 0.666 0.611 0.684 0.452\n",
"\n",
" Epoch GPU_mem box_loss obj_loss cls_loss Instances Size\n",
" 1/2 4.79G 0.04244 0.06423 0.01611 236 640: 100% 8/8 [00:00<00:00, 8.08it/s]\n",
" Class Images Instances P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.43it/s]\n",
" all 128 929 0.737 0.623 0.72 0.482\n",
" 1/2 4.46G 0.04244 0.06423 0.01611 236 640: 100% 8/8 [00:01<00:00, 7.91it/s]\n",
" Class Images Instances P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.19it/s]\n",
" all 128 929 0.746 0.626 0.722 0.481\n",
"\n",
" Epoch GPU_mem box_loss obj_loss cls_loss Instances Size\n",
" 2/2 4.79G 0.04695 0.06875 0.0173 189 640: 100% 8/8 [00:00<00:00, 8.87it/s]\n",
" Class Images Instances P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.57it/s]\n",
" all 128 929 0.76 0.631 0.733 0.497\n",
" 2/2 4.46G 0.04695 0.06875 0.0173 189 640: 100% 8/8 [00:00<00:00, 8.05it/s]\n",
" Class Images Instances P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.29it/s]\n",
" all 128 929 0.774 0.647 0.746 0.499\n",
"\n",
"3 epochs completed in 0.003 hours.\n",
"Optimizer stripped from runs/train/exp/weights/last.pt, 14.9MB\n",
......@@ -808,79 +770,79 @@
"Validating runs/train/exp/weights/best.pt...\n",
"Fusing layers... \n",
"Model summary: 213 layers, 7225885 parameters, 0 gradients, 16.4 GFLOPs\n",
" Class Images Instances P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.25it/s]\n",
" all 128 929 0.76 0.631 0.733 0.497\n",
" person 128 254 0.872 0.699 0.807 0.533\n",
" bicycle 128 6 0.761 0.536 0.725 0.444\n",
" car 128 46 0.771 0.413 0.553 0.242\n",
" motorcycle 128 5 0.795 1 0.928 0.592\n",
" airplane 128 6 0.983 1 0.995 0.689\n",
" bus 128 7 0.648 0.714 0.755 0.691\n",
" train 128 3 1 0.586 0.995 0.603\n",
" truck 128 12 0.616 0.333 0.482 0.259\n",
" boat 128 6 0.921 0.333 0.524 0.211\n",
" traffic light 128 14 0.76 0.229 0.374 0.21\n",
" stop sign 128 2 0.824 1 0.995 0.821\n",
" bench 128 9 0.822 0.519 0.674 0.316\n",
" bird 128 16 0.973 1 0.995 0.6\n",
" cat 128 4 0.861 1 0.995 0.772\n",
" dog 128 9 1 0.666 0.88 0.645\n",
" horse 128 2 0.845 1 0.995 0.622\n",
" elephant 128 17 0.923 0.882 0.93 0.716\n",
" bear 128 1 0.71 1 0.995 0.995\n",
" Class Images Instances P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.21it/s]\n",
" all 128 929 0.774 0.647 0.746 0.499\n",
" person 128 254 0.87 0.697 0.806 0.534\n",
" bicycle 128 6 0.759 0.528 0.725 0.444\n",
" car 128 46 0.774 0.413 0.554 0.239\n",
" motorcycle 128 5 0.791 1 0.962 0.595\n",
" airplane 128 6 0.981 1 0.995 0.689\n",
" bus 128 7 0.65 0.714 0.755 0.691\n",
" train 128 3 1 0.573 0.995 0.602\n",
" truck 128 12 0.613 0.333 0.489 0.263\n",
" boat 128 6 0.933 0.333 0.507 0.209\n",
" traffic light 128 14 0.76 0.228 0.367 0.209\n",
" stop sign 128 2 0.821 1 0.995 0.821\n",
" bench 128 9 0.824 0.526 0.676 0.31\n",
" bird 128 16 0.974 1 0.995 0.611\n",
" cat 128 4 0.859 1 0.995 0.772\n",
" dog 128 9 1 0.666 0.883 0.647\n",
" horse 128 2 0.84 1 0.995 0.622\n",
" elephant 128 17 0.926 0.882 0.93 0.716\n",
" bear 128 1 0.709 1 0.995 0.995\n",
" zebra 128 4 0.866 1 0.995 0.922\n",
" giraffe 128 9 0.771 0.752 0.891 0.705\n",
" backpack 128 6 0.888 0.5 0.753 0.294\n",
" umbrella 128 18 0.876 0.784 0.899 0.539\n",
" handbag 128 19 0.8 0.21 0.335 0.181\n",
" tie 128 7 0.798 0.714 0.787 0.478\n",
" suitcase 128 4 0.662 1 0.945 0.581\n",
" frisbee 128 5 0.727 0.8 0.759 0.701\n",
" skis 128 1 0 0 0.0585 0.0139\n",
" snowboard 128 7 0.807 0.714 0.853 0.591\n",
" giraffe 128 9 0.777 0.778 0.891 0.705\n",
" backpack 128 6 0.894 0.5 0.753 0.294\n",
" umbrella 128 18 0.876 0.783 0.899 0.54\n",
" handbag 128 19 0.799 0.209 0.335 0.179\n",
" tie 128 7 0.782 0.714 0.787 0.478\n",
" suitcase 128 4 0.658 1 0.945 0.581\n",
" frisbee 128 5 0.726 0.8 0.76 0.701\n",
" skis 128 1 0.8 1 0.995 0.103\n",
" snowboard 128 7 0.815 0.714 0.852 0.574\n",
" sports ball 128 6 0.649 0.667 0.602 0.307\n",
" kite 128 10 0.7 0.47 0.543 0.212\n",
" baseball bat 128 4 1 0.496 0.544 0.208\n",
" baseball glove 128 7 0.619 0.429 0.47 0.313\n",
" skateboard 128 5 0.847 0.6 0.712 0.496\n",
" tennis racket 128 7 0.757 0.429 0.544 0.34\n",
" bottle 128 18 0.546 0.334 0.53 0.259\n",
" wine glass 128 16 0.716 0.875 0.907 0.528\n",
" cup 128 36 0.826 0.639 0.802 0.538\n",
" fork 128 6 1 0.329 0.496 0.364\n",
" knife 128 16 0.706 0.625 0.604 0.382\n",
" spoon 128 22 0.837 0.467 0.618 0.38\n",
" bowl 128 28 0.757 0.607 0.714 0.519\n",
" banana 128 1 0.889 1 0.995 0.399\n",
" sandwich 128 2 1 0 0.638 0.56\n",
" orange 128 4 1 0.663 0.945 0.592\n",
" broccoli 128 11 0.545 0.437 0.471 0.351\n",
" carrot 128 24 0.701 0.585 0.697 0.454\n",
" hot dog 128 2 0.501 1 0.995 0.995\n",
" pizza 128 5 0.809 1 0.962 0.747\n",
" donut 128 14 0.66 1 0.96 0.837\n",
" cake 128 4 0.871 1 0.995 0.822\n",
" chair 128 35 0.536 0.561 0.595 0.325\n",
" couch 128 6 0.931 0.667 0.828 0.539\n",
" potted plant 128 14 0.733 0.786 0.823 0.495\n",
" bed 128 3 0.691 0.333 0.83 0.422\n",
" dining table 128 13 0.621 0.255 0.513 0.34\n",
" toilet 128 2 0.797 1 0.995 0.846\n",
" tv 128 2 0.57 1 0.995 0.796\n",
" laptop 128 3 1 0 0.694 0.316\n",
" mouse 128 2 1 0 0.172 0.0862\n",
" remote 128 8 1 0.62 0.634 0.551\n",
" cell phone 128 8 0.591 0.375 0.425 0.216\n",
" microwave 128 3 0.736 1 0.995 0.766\n",
" oven 128 5 0.333 0.4 0.438 0.299\n",
" sink 128 6 0.427 0.333 0.329 0.23\n",
" refrigerator 128 5 0.559 0.8 0.798 0.565\n",
" book 128 29 0.558 0.241 0.307 0.155\n",
" clock 128 9 0.761 0.889 0.888 0.711\n",
" vase 128 2 0.287 1 0.995 0.895\n",
" scissors 128 1 1 0 0.497 0.0574\n",
" teddy bear 128 21 0.838 0.493 0.745 0.509\n",
" toothbrush 128 5 0.789 1 0.928 0.59\n",
" kite 128 10 0.7 0.47 0.546 0.206\n",
" baseball bat 128 4 1 0.497 0.544 0.182\n",
" baseball glove 128 7 0.598 0.429 0.47 0.31\n",
" skateboard 128 5 0.851 0.6 0.685 0.495\n",
" tennis racket 128 7 0.754 0.429 0.544 0.34\n",
" bottle 128 18 0.564 0.333 0.53 0.264\n",
" wine glass 128 16 0.715 0.875 0.907 0.528\n",
" cup 128 36 0.825 0.639 0.803 0.535\n",
" fork 128 6 1 0.329 0.5 0.384\n",
" knife 128 16 0.706 0.625 0.666 0.405\n",
" spoon 128 22 0.836 0.464 0.619 0.379\n",
" bowl 128 28 0.763 0.607 0.717 0.516\n",
" banana 128 1 0.886 1 0.995 0.399\n",
" sandwich 128 2 1 0 0.62 0.546\n",
" orange 128 4 1 0.75 0.995 0.622\n",
" broccoli 128 11 0.548 0.443 0.467 0.35\n",
" carrot 128 24 0.7 0.585 0.699 0.458\n",
" hot dog 128 2 0.502 1 0.995 0.995\n",
" pizza 128 5 0.813 1 0.962 0.747\n",
" donut 128 14 0.662 1 0.96 0.838\n",
" cake 128 4 0.868 1 0.995 0.822\n",
" chair 128 35 0.538 0.571 0.594 0.322\n",
" couch 128 6 0.924 0.667 0.828 0.538\n",
" potted plant 128 14 0.731 0.786 0.824 0.495\n",
" bed 128 3 0.736 0.333 0.83 0.425\n",
" dining table 128 13 0.624 0.259 0.494 0.336\n",
" toilet 128 2 0.79 1 0.995 0.846\n",
" tv 128 2 0.574 1 0.995 0.796\n",
" laptop 128 3 1 0 0.695 0.367\n",
" mouse 128 2 1 0 0.173 0.0864\n",
" remote 128 8 1 0.62 0.634 0.557\n",
" cell phone 128 8 0.612 0.397 0.437 0.221\n",
" microwave 128 3 0.741 1 0.995 0.766\n",
" oven 128 5 0.33 0.4 0.449 0.3\n",
" sink 128 6 0.444 0.333 0.331 0.231\n",
" refrigerator 128 5 0.561 0.8 0.798 0.546\n",
" book 128 29 0.635 0.276 0.355 0.164\n",
" clock 128 9 0.766 0.889 0.888 0.73\n",
" vase 128 2 0.303 1 0.995 0.895\n",
" scissors 128 1 1 0 0.332 0.0397\n",
" teddy bear 128 21 0.842 0.508 0.739 0.499\n",
" toothbrush 128 5 0.787 1 0.928 0.59\n",
"Results saved to \u001b[1mruns/train/exp\u001b[0m\n"
]
}
......
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论