mirrors
/
yolov5
mirror of https://github.com/ultralytics/yolov5.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Created using Colaboratory

pull/9001/head
Glenn Jocher 2022-08-17 16:18:06 +02:00
parent 7c9486e16f
commit fe809b8dad
1 changed files with 152 additions and 152 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

304
tutorial.ipynb vendored
View File

@ -17,7 +17,7 @@
"accelerator": "GPU", "accelerator": "GPU",
"widgets": { "widgets": {
"application/vnd.jupyter.widget-state+json": { "application/vnd.jupyter.widget-state+json": {
"c31d2039ccf74c22b67841f4877d1186": { "57c562894aed45cd9a107d0455e3e3f4": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel", "model_name": "HBoxModel",
"model_module_version": "1.5.0", "model_module_version": "1.5.0",
@ -32,14 +32,14 @@
"_view_name": "HBoxView", "_view_name": "HBoxView",
"box_style": "", "box_style": "",
"children": [ "children": [
"IPY_MODEL_d4bba1727c714d94ad58a72bffa07c4c", "IPY_MODEL_040d53c6cc924350bcb656cd21a7c713",
"IPY_MODEL_9aeff9f1780b45f892422fdc96e56913", "IPY_MODEL_e029890942a74c098408ce5a9a566d51",
"IPY_MODEL_bf55a7c71d074d3fa88b10b997820825" "IPY_MODEL_8fb991c03e434566a4297b6ab9446f89"
], ],
"layout": "IPY_MODEL_d8b66044e2fb4f5b916696834d880c81" "layout": "IPY_MODEL_a9a376923a7742d89fb335db709c7a7e"
} }
}, },
"d4bba1727c714d94ad58a72bffa07c4c": { "040d53c6cc924350bcb656cd21a7c713": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel", "model_name": "HTMLModel",
"model_module_version": "1.5.0", "model_module_version": "1.5.0",
@ -54,13 +54,13 @@
"_view_name": "HTMLView", "_view_name": "HTMLView",
"description": "", "description": "",
"description_tooltip": null, "description_tooltip": null,
"layout": "IPY_MODEL_102e1deda239436fa72751c58202fa0f", "layout": "IPY_MODEL_8b4276ac834c4735bf60ee9b761b9962",
"placeholder": "​", "placeholder": "​",
"style": "IPY_MODEL_4fd4431ced6c42368e18424912b877e4", "style": "IPY_MODEL_52cc8da75b724198856617247541cb1e",
"value": "100%" "value": "100%"
} }
}, },
"9aeff9f1780b45f892422fdc96e56913": { "e029890942a74c098408ce5a9a566d51": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel", "model_name": "FloatProgressModel",
"model_module_version": "1.5.0", "model_module_version": "1.5.0",
@ -76,15 +76,15 @@
"bar_style": "success", "bar_style": "success",
"description": "", "description": "",
"description_tooltip": null, "description_tooltip": null,
"layout": "IPY_MODEL_cdd709c4f40941bea1b2053523c9fac8", "layout": "IPY_MODEL_b6652f46480243c4adf60e6440043d6f",
"max": 818322941, "max": 818322941,
"min": 0, "min": 0,
"orientation": "horizontal", "orientation": "horizontal",
"style": "IPY_MODEL_a1ef2d8de2b741c78ca5d938e2ddbcdf", "style": "IPY_MODEL_e502754177ff4ea8abf82a6e9ac77a4a",
"value": 818322941 "value": 818322941
} }
}, },
"bf55a7c71d074d3fa88b10b997820825": { "8fb991c03e434566a4297b6ab9446f89": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel", "model_name": "HTMLModel",
"model_module_version": "1.5.0", "model_module_version": "1.5.0",
@ -99,13 +99,13 @@
"_view_name": "HTMLView", "_view_name": "HTMLView",
"description": "", "description": "",
"description_tooltip": null, "description_tooltip": null,
"layout": "IPY_MODEL_0dbce99bb6184238842cbec0587d564a", "layout": "IPY_MODEL_447398becdb04836b5ffb5915318db07",
"placeholder": "​", "placeholder": "​",
"style": "IPY_MODEL_91ff5f93f2a24c5790ab29e347965946", "style": "IPY_MODEL_2fddcb27ad4a4caa81ff51111f8d0ed6",
"value": " 780M/780M [01:10<00:00, 10.5MB/s]" "value": " 780M/780M [01:17<00:00, 12.3MB/s]"
} }
}, },
"d8b66044e2fb4f5b916696834d880c81": { "a9a376923a7742d89fb335db709c7a7e": {
"model_module": "@jupyter-widgets/base", "model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel", "model_name": "LayoutModel",
"model_module_version": "1.2.0", "model_module_version": "1.2.0",
@ -157,7 +157,7 @@
"width": null "width": null
} }
}, },
"102e1deda239436fa72751c58202fa0f": { "8b4276ac834c4735bf60ee9b761b9962": {
"model_module": "@jupyter-widgets/base", "model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel", "model_name": "LayoutModel",
"model_module_version": "1.2.0", "model_module_version": "1.2.0",
@ -209,7 +209,7 @@
"width": null "width": null
} }
}, },
"4fd4431ced6c42368e18424912b877e4": { "52cc8da75b724198856617247541cb1e": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel", "model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0", "model_module_version": "1.5.0",
@ -224,7 +224,7 @@
"description_width": "" "description_width": ""
} }
}, },
"cdd709c4f40941bea1b2053523c9fac8": { "b6652f46480243c4adf60e6440043d6f": {
"model_module": "@jupyter-widgets/base", "model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel", "model_name": "LayoutModel",
"model_module_version": "1.2.0", "model_module_version": "1.2.0",
@ -276,7 +276,7 @@
"width": null "width": null
} }
}, },
"a1ef2d8de2b741c78ca5d938e2ddbcdf": { "e502754177ff4ea8abf82a6e9ac77a4a": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel", "model_name": "ProgressStyleModel",
"model_module_version": "1.5.0", "model_module_version": "1.5.0",
@ -292,7 +292,7 @@
"description_width": "" "description_width": ""
} }
}, },
"0dbce99bb6184238842cbec0587d564a": { "447398becdb04836b5ffb5915318db07": {
"model_module": "@jupyter-widgets/base", "model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel", "model_name": "LayoutModel",
"model_module_version": "1.2.0", "model_module_version": "1.2.0",
@ -344,7 +344,7 @@
"width": null "width": null
} }
}, },
"91ff5f93f2a24c5790ab29e347965946": { "2fddcb27ad4a4caa81ff51111f8d0ed6": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel", "model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0", "model_module_version": "1.5.0",
@ -404,7 +404,7 @@
"colab": { "colab": {
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
}, },
"outputId": "185d0979-edcd-4860-e6fb-b8a27dbf5096" "outputId": "e0f693e4-413b-4cc8-ae7e-91537da370b0"
}, },
"source": [ "source": [
"!git clone https://github.com/ultralytics/yolov5 # clone\n", "!git clone https://github.com/ultralytics/yolov5 # clone\n",
@ -415,13 +415,13 @@
"import utils\n", "import utils\n",
"display = utils.notebook_init() # checks" "display = utils.notebook_init() # checks"
], ],
"execution_count": null, "execution_count": 1,
"outputs": [ "outputs": [
{ {
"output_type": "stream", "output_type": "stream",
"name": "stderr", "name": "stderr",
"text": [ "text": [
"YOLOv5 🚀 v6.1-370-g20f1b7e Python-3.7.13 torch-1.12.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n" "YOLOv5 🚀 v6.2-2-g7c9486e Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n"
] ]
}, },
{ {
@ -461,29 +461,29 @@
"colab": { "colab": {
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
}, },
"outputId": "4b13989f-32a4-4ef0-b403-06ff3aac255c" "outputId": "941d625b-01a1-4f1b-dfd2-d9ef1c945715"
}, },
"source": [ "source": [
"!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images\n", "!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)" "# display.Image(filename='runs/detect/exp/zidane.jpg', width=600)"
], ],
"execution_count": null, "execution_count": 2,
"outputs": [ "outputs": [
{ {
"output_type": "stream", "output_type": "stream",
"name": "stdout", "name": "stdout",
"text": [ "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", "\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 🚀 v6.1-370-g20f1b7e Python-3.7.13 torch-1.12.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n", "YOLOv5 🚀 v6.2-2-g7c9486e Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"\n", "\n",
"Downloading https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5s.pt to yolov5s.pt...\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, 53.9MB/s]\n", "100% 14.1M/14.1M [00:00<00:00, 50.5MB/s]\n",
"\n", "\n",
"Fusing layers... \n", "Fusing layers... \n",
"YOLOv5s summary: 213 layers, 7225885 parameters, 0 gradients\n", "YOLOv5s summary: 213 layers, 7225885 parameters, 0 gradients\n",
"image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, Done. (0.016s)\n", "image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, Done. (0.014s)\n",
"image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.021s)\n", "image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.020s)\n",
"Speed: 0.6ms pre-process, 18.6ms inference, 25.0ms NMS per image at shape (1, 3, 640, 640)\n", "Speed: 0.6ms pre-process, 17.0ms inference, 20.2ms NMS per image at shape (1, 3, 640, 640)\n",
"Results saved to \u001b[1mruns/detect/exp\u001b[0m\n" "Results saved to \u001b[1mruns/detect/exp\u001b[0m\n"
] ]
} }
@ -527,27 +527,27 @@
"base_uri": "https://localhost:8080/", "base_uri": "https://localhost:8080/",
"height": 49, "height": 49,
"referenced_widgets": [ "referenced_widgets": [
"c31d2039ccf74c22b67841f4877d1186", "57c562894aed45cd9a107d0455e3e3f4",
"d4bba1727c714d94ad58a72bffa07c4c", "040d53c6cc924350bcb656cd21a7c713",
"9aeff9f1780b45f892422fdc96e56913", "e029890942a74c098408ce5a9a566d51",
"bf55a7c71d074d3fa88b10b997820825", "8fb991c03e434566a4297b6ab9446f89",
"d8b66044e2fb4f5b916696834d880c81", "a9a376923a7742d89fb335db709c7a7e",
"102e1deda239436fa72751c58202fa0f", "8b4276ac834c4735bf60ee9b761b9962",
"4fd4431ced6c42368e18424912b877e4", "52cc8da75b724198856617247541cb1e",
"cdd709c4f40941bea1b2053523c9fac8", "b6652f46480243c4adf60e6440043d6f",
"a1ef2d8de2b741c78ca5d938e2ddbcdf", "e502754177ff4ea8abf82a6e9ac77a4a",
"0dbce99bb6184238842cbec0587d564a", "447398becdb04836b5ffb5915318db07",
"91ff5f93f2a24c5790ab29e347965946" "2fddcb27ad4a4caa81ff51111f8d0ed6"
] ]
}, },
"outputId": "a9004b06-37a6-41ed-a1f2-ac956f3963b3" "outputId": "d593b41a-55e7-48a5-e285-5df449edc8c0"
}, },
"source": [ "source": [
"# Download COCO val\n", "# Download COCO val\n",
"torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017val.zip', 'tmp.zip')\n", "torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017val.zip', 'tmp.zip')\n",
"!unzip -q tmp.zip -d ../datasets && rm tmp.zip" "!unzip -q tmp.zip -d ../datasets && rm tmp.zip"
], ],
"execution_count": null, "execution_count": 3,
"outputs": [ "outputs": [
{ {
"output_type": "display_data", "output_type": "display_data",
@ -558,7 +558,7 @@
"application/vnd.jupyter.widget-view+json": { "application/vnd.jupyter.widget-view+json": {
"version_major": 2, "version_major": 2,
"version_minor": 0, "version_minor": 0,
"model_id": "c31d2039ccf74c22b67841f4877d1186" "model_id": "57c562894aed45cd9a107d0455e3e3f4"
} }
}, },
"metadata": {} "metadata": {}
@ -572,48 +572,48 @@
"colab": { "colab": {
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
}, },
"outputId": "c0f29758-4ec8-4def-893d-0efd6ed5b7f4" "outputId": "701132a6-9ca8-4e1f-c89f-5d38893a6fc4"
}, },
"source": [ "source": [
"# Run YOLOv5x on COCO val\n", "# Run YOLOv5x on COCO val\n",
"!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half" "!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half"
], ],
"execution_count": null, "execution_count": 4,
"outputs": [ "outputs": [
{ {
"output_type": "stream", "output_type": "stream",
"name": "stdout", "name": "stdout",
"text": [ "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", "\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 🚀 v6.1-370-g20f1b7e Python-3.7.13 torch-1.12.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n", "YOLOv5 🚀 v6.2-2-g7c9486e Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"\n", "\n",
"Downloading https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5x.pt to yolov5x.pt...\n", "Downloading https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5x.pt to yolov5x.pt...\n",
"100% 166M/166M [00:35<00:00, 4.97MB/s]\n", "100% 166M/166M [00:11<00:00, 15.1MB/s]\n",
"\n", "\n",
"Fusing layers... \n", "Fusing layers... \n",
"YOLOv5x summary: 444 layers, 86705005 parameters, 0 gradients\n", "YOLOv5x summary: 444 layers, 86705005 parameters, 0 gradients\n",
"Downloading https://ultralytics.com/assets/Arial.ttf to /root/.config/Ultralytics/Arial.ttf...\n", "Downloading https://ultralytics.com/assets/Arial.ttf to /root/.config/Ultralytics/Arial.ttf...\n",
"100% 755k/755k [00:00<00:00, 49.4MB/s]\n", "100% 755k/755k [00:00<00:00, 48.6MB/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, 10716.86it/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, 10889.87it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /content/datasets/coco/val2017.cache\n", "\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /content/datasets/coco/val2017.cache\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [01:08<00:00, 2.28it/s]\n", " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [01:05<00:00, 2.38it/s]\n",
" all 5000 36335 0.743 0.625 0.683 0.504\n", " all 5000 36335 0.743 0.625 0.683 0.504\n",
"Speed: 0.1ms pre-process, 4.6ms inference, 1.2ms NMS per image at shape (32, 3, 640, 640)\n", "Speed: 0.1ms pre-process, 4.7ms inference, 1.0ms NMS per image at shape (32, 3, 640, 640)\n",
"\n", "\n",
"Evaluating pycocotools mAP... saving runs/val/exp/yolov5x_predictions.json...\n", "Evaluating pycocotools mAP... saving runs/val/exp/yolov5x_predictions.json...\n",
"loading annotations into memory...\n", "loading annotations into memory...\n",
"Done (t=0.41s)\n", "Done (t=0.39s)\n",
"creating index...\n", "creating index...\n",
"index created!\n", "index created!\n",
"Loading and preparing results...\n", "Loading and preparing results...\n",
"DONE (t=5.64s)\n", "DONE (t=5.53s)\n",
"creating index...\n", "creating index...\n",
"index created!\n", "index created!\n",
"Running per image evaluation...\n", "Running per image evaluation...\n",
"Evaluate annotation type *bbox*\n", "Evaluate annotation type *bbox*\n",
"DONE (t=72.86s).\n", "DONE (t=73.01s).\n",
"Accumulating evaluation results...\n", "Accumulating evaluation results...\n",
"DONE (t=14.20s).\n", "DONE (t=15.27s).\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.506\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=0.50 | area= all | maxDets=100 ] = 0.688\n",
" Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.549\n", " Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.549\n",
@ -745,13 +745,13 @@
"colab": { "colab": {
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
}, },
"outputId": "bce1b4bd-1a14-4c07-aebd-6c11e91ad24b" "outputId": "50a9318f-d438-41d5-db95-928f1842c057"
}, },
"source": [ "source": [
"# Train YOLOv5s on COCO128 for 3 epochs\n", "# Train YOLOv5s on COCO128 for 3 epochs\n",
"!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache" "!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache"
], ],
"execution_count": null, "execution_count": 5,
"outputs": [ "outputs": [
{ {
"output_type": "stream", "output_type": "stream",
@ -759,17 +759,17 @@
"text": [ "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[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", "\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov5 ✅\n",
"YOLOv5 🚀 v6.1-370-g20f1b7e Python-3.7.13 torch-1.12.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n", "YOLOv5 🚀 v6.2-2-g7c9486e Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"\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[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", "\u001b[34m\u001b[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs in Weights & Biases\n",
"\u001b[34m\u001b[1mClearML: \u001b[0mrun 'pip install clearml' to automatically track, visualize and remotely train YOLOv5 🚀 runs in ClearML\n", "\u001b[34m\u001b[1mClearML: \u001b[0mrun 'pip install clearml' to automatically track, visualize and remotely train YOLOv5 🚀 in ClearML\n",
"\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/\n", "\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/\n",
"\n", "\n",
"Dataset not found ⚠️, missing paths ['/content/datasets/coco128/images/train2017']\n", "Dataset not found ⚠️, missing paths ['/content/datasets/coco128/images/train2017']\n",
"Downloading https://ultralytics.com/assets/coco128.zip to coco128.zip...\n", "Downloading https://ultralytics.com/assets/coco128.zip to coco128.zip...\n",
"100% 6.66M/6.66M [00:00<00:00, 75.2MB/s]\n", "100% 6.66M/6.66M [00:00<00:00, 12.4MB/s]\n",
"Dataset download success ✅ (0.7s), saved to \u001b[1m/content/datasets\u001b[0m\n", "Dataset download success ✅ (1.3s), saved to \u001b[1m/content/datasets\u001b[0m\n",
"\n", "\n",
" from n params module arguments \n", " from n params module arguments \n",
" 0 -1 1 3520 models.common.Conv [3, 32, 6, 2, 2] \n", " 0 -1 1 3520 models.common.Conv [3, 32, 6, 2, 2] \n",
@ -802,12 +802,12 @@
"Transferred 349/349 items from yolov5s.pt\n", "Transferred 349/349 items from yolov5s.pt\n",
"\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n", "\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[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(always_apply=False, p=0.01, blur_limit=(3, 7)), MedianBlur(always_apply=False, p=0.01, blur_limit=(3, 7)), ToGray(always_apply=False, p=0.01), CLAHE(always_apply=False, p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8))\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, 7926.40it/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, 8516.89it/s]\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /content/datasets/coco128/labels/train2017.cache\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, 975.81it/s]\n", "\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 1043.44it/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[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, 258.62it/s]\n", "\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 259.20it/s]\n",
"Plotting labels to runs/train/exp/labels.jpg... \n", "Plotting labels to runs/train/exp/labels.jpg... \n",
"\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", "\u001b[34m\u001b[1mAutoAnchor: \u001b[0m4.27 anchors/target, 0.994 Best Possible Recall (BPR). Current anchors are a good fit to dataset ✅\n",
@ -817,19 +817,19 @@
"Starting training for 3 epochs...\n", "Starting training for 3 epochs...\n",
"\n", "\n",
" Epoch gpu_mem box obj cls labels img_size\n", " Epoch gpu_mem box obj cls labels img_size\n",
" 0/2 3.76G 0.04529 0.06712 0.01835 323 640: 100% 8/8 [00:05<00:00, 1.59it/s]\n", " 0/2 3.76G 0.04529 0.06712 0.01835 323 640: 100% 8/8 [00:04<00:00, 1.83it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.05it/s]\n", " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.21it/s]\n",
" all 128 929 0.806 0.593 0.718 0.472\n", " all 128 929 0.666 0.611 0.684 0.452\n",
"\n", "\n",
" Epoch gpu_mem box obj cls labels img_size\n", " Epoch gpu_mem box obj cls labels img_size\n",
" 1/2 4.79G 0.04244 0.06423 0.01611 236 640: 100% 8/8 [00:00<00:00, 8.11it/s]\n", " 1/2 4.79G 0.04244 0.06423 0.01611 236 640: 100% 8/8 [00:00<00:00, 8.15it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.20it/s]\n", " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.45it/s]\n",
" all 128 929 0.811 0.615 0.74 0.493\n", " all 128 929 0.746 0.626 0.722 0.481\n",
"\n", "\n",
" Epoch gpu_mem box obj cls labels img_size\n", " Epoch gpu_mem box obj cls labels img_size\n",
" 2/2 4.79G 0.04695 0.06875 0.0173 189 640: 100% 8/8 [00:00<00:00, 9.12it/s]\n", " 2/2 4.79G 0.04695 0.06875 0.0173 189 640: 100% 8/8 [00:00<00:00, 8.91it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.24it/s]\n", " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.56it/s]\n",
" all 128 929 0.784 0.634 0.747 0.502\n", " all 128 929 0.774 0.647 0.746 0.499\n",
"\n", "\n",
"3 epochs completed in 0.003 hours.\n", "3 epochs completed in 0.003 hours.\n",
"Optimizer stripped from runs/train/exp/weights/last.pt, 14.9MB\n", "Optimizer stripped from runs/train/exp/weights/last.pt, 14.9MB\n",
@ -838,79 +838,79 @@
"Validating runs/train/exp/weights/best.pt...\n", "Validating runs/train/exp/weights/best.pt...\n",
"Fusing layers... \n", "Fusing layers... \n",
"Model summary: 213 layers, 7225885 parameters, 0 gradients, 16.4 GFLOPs\n", "Model summary: 213 layers, 7225885 parameters, 0 gradients, 16.4 GFLOPs\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.20it/s]\n", " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.22it/s]\n",
" all 128 929 0.781 0.637 0.747 0.502\n", " all 128 929 0.774 0.647 0.746 0.499\n",
" person 128 254 0.872 0.693 0.81 0.534\n", " person 128 254 0.87 0.697 0.806 0.534\n",
" bicycle 128 6 1 0.407 0.68 0.425\n", " bicycle 128 6 0.759 0.528 0.725 0.444\n",
" car 128 46 0.743 0.413 0.581 0.247\n", " car 128 46 0.774 0.413 0.554 0.239\n",
" motorcycle 128 5 1 0.988 0.995 0.692\n", " motorcycle 128 5 0.791 1 0.962 0.595\n",
" airplane 128 6 0.965 1 0.995 0.717\n", " airplane 128 6 0.981 1 0.995 0.689\n",
" bus 128 7 0.706 0.714 0.814 0.697\n", " bus 128 7 0.65 0.714 0.755 0.691\n",
" train 128 3 1 0.582 0.806 0.477\n", " train 128 3 1 0.573 0.995 0.602\n",
" truck 128 12 0.602 0.417 0.495 0.271\n", " truck 128 12 0.613 0.333 0.489 0.263\n",
" boat 128 6 0.961 0.333 0.464 0.224\n", " boat 128 6 0.933 0.333 0.507 0.209\n",
" traffic light 128 14 0.517 0.155 0.364 0.216\n", " traffic light 128 14 0.76 0.228 0.367 0.209\n",
" stop sign 128 2 0.782 1 0.995 0.821\n", " stop sign 128 2 0.821 1 0.995 0.821\n",
" bench 128 9 0.829 0.539 0.701 0.288\n", " bench 128 9 0.824 0.526 0.676 0.31\n",
" bird 128 16 0.924 1 0.995 0.655\n", " bird 128 16 0.974 1 0.995 0.611\n",
" cat 128 4 0.891 1 0.995 0.809\n", " cat 128 4 0.859 1 0.995 0.772\n",
" dog 128 9 1 0.659 0.883 0.604\n", " dog 128 9 1 0.666 0.883 0.647\n",
" horse 128 2 0.808 1 0.995 0.672\n", " horse 128 2 0.84 1 0.995 0.622\n",
" elephant 128 17 0.973 0.882 0.936 0.733\n", " elephant 128 17 0.926 0.882 0.93 0.716\n",
" bear 128 1 0.692 1 0.995 0.995\n", " bear 128 1 0.709 1 0.995 0.995\n",
" zebra 128 4 0.872 1 0.995 0.922\n", " zebra 128 4 0.866 1 0.995 0.922\n",
" giraffe 128 9 0.865 0.889 0.975 0.736\n", " giraffe 128 9 0.777 0.778 0.891 0.705\n",
" backpack 128 6 1 0.547 0.787 0.372\n", " backpack 128 6 0.894 0.5 0.753 0.294\n",
" umbrella 128 18 0.823 0.667 0.889 0.504\n", " umbrella 128 18 0.876 0.783 0.899 0.54\n",
" handbag 128 19 0.516 0.105 0.304 0.153\n", " handbag 128 19 0.799 0.209 0.335 0.179\n",
" tie 128 7 0.696 0.714 0.741 0.482\n", " tie 128 7 0.782 0.714 0.787 0.478\n",
" suitcase 128 4 0.716 1 0.995 0.553\n", " suitcase 128 4 0.658 1 0.945 0.581\n",
" frisbee 128 5 0.715 0.8 0.8 0.71\n", " frisbee 128 5 0.726 0.8 0.76 0.701\n",
" skis 128 1 0.694 1 0.995 0.398\n", " skis 128 1 0.8 1 0.995 0.103\n",
" snowboard 128 7 0.893 0.714 0.855 0.569\n", " snowboard 128 7 0.815 0.714 0.852 0.574\n",
" sports ball 128 6 0.659 0.667 0.602 0.307\n", " sports ball 128 6 0.649 0.667 0.602 0.307\n",
" kite 128 10 0.683 0.434 0.611 0.242\n", " kite 128 10 0.7 0.47 0.546 0.206\n",
" baseball bat 128 4 0.838 0.5 0.55 0.146\n", " baseball bat 128 4 1 0.497 0.544 0.182\n",
" baseball glove 128 7 0.572 0.429 0.463 0.294\n", " baseball glove 128 7 0.598 0.429 0.47 0.31\n",
" skateboard 128 5 0.697 0.6 0.702 0.476\n", " skateboard 128 5 0.851 0.6 0.685 0.495\n",
" tennis racket 128 7 0.62 0.429 0.544 0.29\n", " tennis racket 128 7 0.754 0.429 0.544 0.34\n",
" bottle 128 18 0.591 0.402 0.572 0.295\n", " bottle 128 18 0.564 0.333 0.53 0.264\n",
" wine glass 128 16 0.747 0.921 0.913 0.529\n", " wine glass 128 16 0.715 0.875 0.907 0.528\n",
" cup 128 36 0.824 0.639 0.826 0.535\n", " cup 128 36 0.825 0.639 0.803 0.535\n",
" fork 128 6 1 0.319 0.518 0.353\n", " fork 128 6 1 0.329 0.5 0.384\n",
" knife 128 16 0.768 0.62 0.654 0.374\n", " knife 128 16 0.706 0.625 0.666 0.405\n",
" spoon 128 22 0.824 0.427 0.65 0.382\n", " spoon 128 22 0.836 0.464 0.619 0.379\n",
" bowl 128 28 0.8 0.643 0.726 0.525\n", " bowl 128 28 0.763 0.607 0.717 0.516\n",
" banana 128 1 0.878 1 0.995 0.208\n", " banana 128 1 0.886 1 0.995 0.399\n",
" sandwich 128 2 1 0 0.62 0.546\n", " sandwich 128 2 1 0 0.62 0.546\n",
" orange 128 4 1 0.896 0.995 0.691\n", " orange 128 4 1 0.75 0.995 0.622\n",
" broccoli 128 11 0.586 0.364 0.481 0.349\n", " broccoli 128 11 0.548 0.443 0.467 0.35\n",
" carrot 128 24 0.702 0.589 0.722 0.475\n", " carrot 128 24 0.7 0.585 0.699 0.458\n",
" hot dog 128 2 0.524 1 0.828 0.795\n", " hot dog 128 2 0.502 1 0.995 0.995\n",
" pizza 128 5 0.811 0.865 0.962 0.695\n", " pizza 128 5 0.813 1 0.962 0.747\n",
" donut 128 14 0.653 1 0.964 0.853\n", " donut 128 14 0.662 1 0.96 0.838\n",
" cake 128 4 0.852 1 0.995 0.822\n", " cake 128 4 0.868 1 0.995 0.822\n",
" chair 128 35 0.536 0.571 0.593 0.31\n", " chair 128 35 0.538 0.571 0.594 0.322\n",
" couch 128 6 1 0.63 0.75 0.518\n", " couch 128 6 0.924 0.667 0.828 0.538\n",
" potted plant 128 14 0.775 0.738 0.839 0.478\n", " potted plant 128 14 0.731 0.786 0.824 0.495\n",
" bed 128 3 1 0 0.72 0.423\n", " bed 128 3 0.736 0.333 0.83 0.425\n",
" dining table 128 13 0.817 0.348 0.592 0.381\n", " dining table 128 13 0.624 0.259 0.494 0.336\n",
" toilet 128 2 0.782 1 0.995 0.895\n", " toilet 128 2 0.79 1 0.995 0.846\n",
" tv 128 2 0.711 1 0.995 0.821\n", " tv 128 2 0.574 1 0.995 0.796\n",
" laptop 128 3 1 0 0.789 0.42\n", " laptop 128 3 1 0 0.695 0.367\n",
" mouse 128 2 1 0 0.0798 0.0399\n", " mouse 128 2 1 0 0.173 0.0864\n",
" remote 128 8 1 0.611 0.63 0.549\n", " remote 128 8 1 0.62 0.634 0.557\n",
" cell phone 128 8 0.685 0.375 0.428 0.245\n", " cell phone 128 8 0.612 0.397 0.437 0.221\n",
" microwave 128 3 0.803 1 0.995 0.767\n", " microwave 128 3 0.741 1 0.995 0.766\n",
" oven 128 5 0.42 0.4 0.444 0.306\n", " oven 128 5 0.33 0.4 0.449 0.3\n",
" sink 128 6 0.288 0.167 0.34 0.247\n", " sink 128 6 0.444 0.333 0.331 0.231\n",
" refrigerator 128 5 0.632 0.8 0.805 0.572\n", " refrigerator 128 5 0.561 0.8 0.798 0.546\n",
" book 128 29 0.494 0.207 0.332 0.161\n", " book 128 29 0.635 0.276 0.355 0.164\n",
" clock 128 9 0.791 0.889 0.93 0.75\n", " clock 128 9 0.766 0.889 0.888 0.73\n",
" vase 128 2 0.355 1 0.995 0.895\n", " vase 128 2 0.303 1 0.995 0.895\n",
" scissors 128 1 1 0 0.332 0.0663\n", " scissors 128 1 1 0 0.332 0.0397\n",
" teddy bear 128 21 0.839 0.571 0.767 0.487\n", " teddy bear 128 21 0.842 0.508 0.739 0.499\n",
" toothbrush 128 5 0.829 0.974 0.962 0.644\n", " toothbrush 128 5 0.787 1 0.928 0.59\n",
"Results saved to \u001b[1mruns/train/exp\u001b[0m\n" "Results saved to \u001b[1mruns/train/exp\u001b[0m\n"
] ]
} }