Skip to content

Y
yolov5
提交 46c43b7b authored 作者: Glenn Jocher's avatar Glenn Jocher
浏览文件
操作

Creado con Colaboratory

上级 394131c2
隐藏空白字符变更
内嵌 并排
正在显示 包含 117 行增加 和 121 行删除
tutorial.ipynb
浏览文件 @ 46c43b7b
...@@ -16,7 +16,7 @@ ...@@ -16,7 +16,7 @@
"accelerator": "GPU", "accelerator": "GPU",
"widgets": { "widgets": {
"application/vnd.jupyter.widget-state+json": { "application/vnd.jupyter.widget-state+json": {
"9cb5be61e41144ef9dbc9339c2f46eb1": { "02ac0588602847eea00a0205f87bcce2": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel", "model_name": "HBoxModel",
"state": { "state": {
...@@ -28,15 +28,15 @@ ...@@ -28,15 +28,15 @@
"_view_count": null, "_view_count": null,
"_view_module_version": "1.5.0", "_view_module_version": "1.5.0",
"box_style": "", "box_style": "",
"layout": "IPY_MODEL_a6ba87512fd04622b9948571d330d9c0", "layout": "IPY_MODEL_c472ea49806447a68b5a9221a4ddae85",
"_model_module": "@jupyter-widgets/controls", "_model_module": "@jupyter-widgets/controls",
"children": [ "children": [
"IPY_MODEL_ed1a514c303b49c0a23745f4ff17344b", "IPY_MODEL_091fdf499bd44a80af7281d16da4aa93",
"IPY_MODEL_79edc4bba71748338f58660262c569a9" "IPY_MODEL_c79f69c959de4427ba102a87a9f46d80"
] ]
} }
}, },
"a6ba87512fd04622b9948571d330d9c0": { "c472ea49806447a68b5a9221a4ddae85": {
"model_module": "@jupyter-widgets/base", "model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel", "model_name": "LayoutModel",
"state": { "state": {
...@@ -87,12 +87,12 @@ ...@@ -87,12 +87,12 @@
"left": null "left": null
} }
}, },
"ed1a514c303b49c0a23745f4ff17344b": { "091fdf499bd44a80af7281d16da4aa93": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel", "model_name": "FloatProgressModel",
"state": { "state": {
"_view_name": "ProgressView", "_view_name": "ProgressView",
"style": "IPY_MODEL_cbbf6780f4f048feb2644ed4e3fed9c7", "style": "IPY_MODEL_c42ae5af74a0491187827d0a1fc259bb",
"_dom_classes": [], "_dom_classes": [],
"description": "100%", "description": "100%",
"_model_name": "FloatProgressModel", "_model_name": "FloatProgressModel",
...@@ -107,30 +107,30 @@ ...@@ -107,30 +107,30 @@
"min": 0, "min": 0,
"description_tooltip": null, "description_tooltip": null,
"_model_module": "@jupyter-widgets/controls", "_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_e40fc489500f4e4891025c59b2b1fa8d" "layout": "IPY_MODEL_5a90f72d3a2d46cb9ad915daa3ead8b4"
} }
}, },
"79edc4bba71748338f58660262c569a9": { "c79f69c959de4427ba102a87a9f46d80": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel", "model_name": "HTMLModel",
"state": { "state": {
"_view_name": "HTMLView", "_view_name": "HTMLView",
"style": "IPY_MODEL_191c687c120f4aab9a112697124fe444", "style": "IPY_MODEL_2a7ed6611da34662b10e37fd4f4e4438",
"_dom_classes": [], "_dom_classes": [],
"description": "", "description": "",
"_model_name": "HTMLModel", "_model_name": "HTMLModel",
"placeholder": "​", "placeholder": "​",
"_view_module": "@jupyter-widgets/controls", "_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0", "_model_module_version": "1.5.0",
"value": " 781M/781M [05:01<00:00, 2.71MB/s]", "value": " 781M/781M [00:23<00:00, 35.1MB/s]",
"_view_count": null, "_view_count": null,
"_view_module_version": "1.5.0", "_view_module_version": "1.5.0",
"description_tooltip": null, "description_tooltip": null,
"_model_module": "@jupyter-widgets/controls", "_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_6b21efad6db4407eb253f819f279671a" "layout": "IPY_MODEL_fead0160658445bf9e966daa4481cad0"
} }
}, },
"cbbf6780f4f048feb2644ed4e3fed9c7": { "c42ae5af74a0491187827d0a1fc259bb": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel", "model_name": "ProgressStyleModel",
"state": { "state": {
...@@ -145,7 +145,7 @@ ...@@ -145,7 +145,7 @@
"_model_module": "@jupyter-widgets/controls" "_model_module": "@jupyter-widgets/controls"
} }
}, },
"e40fc489500f4e4891025c59b2b1fa8d": { "5a90f72d3a2d46cb9ad915daa3ead8b4": {
"model_module": "@jupyter-widgets/base", "model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel", "model_name": "LayoutModel",
"state": { "state": {
...@@ -196,7 +196,7 @@ ...@@ -196,7 +196,7 @@
"left": null "left": null
} }
}, },
"191c687c120f4aab9a112697124fe444": { "2a7ed6611da34662b10e37fd4f4e4438": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel", "model_name": "DescriptionStyleModel",
"state": { "state": {
...@@ -210,7 +210,7 @@ ...@@ -210,7 +210,7 @@
"_model_module": "@jupyter-widgets/controls" "_model_module": "@jupyter-widgets/controls"
} }
}, },
"6b21efad6db4407eb253f819f279671a": { "fead0160658445bf9e966daa4481cad0": {
"model_module": "@jupyter-widgets/base", "model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel", "model_name": "LayoutModel",
"state": { "state": {
...@@ -261,7 +261,7 @@ ...@@ -261,7 +261,7 @@
"left": null "left": null
} }
}, },
"b434b178be4b41b3881e237e19f49b45": { "cf1ab9fde7444d3e874fcd407ba8f0f8": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel", "model_name": "HBoxModel",
"state": { "state": {
...@@ -273,15 +273,15 @@ ...@@ -273,15 +273,15 @@
"_view_count": null, "_view_count": null,
"_view_module_version": "1.5.0", "_view_module_version": "1.5.0",
"box_style": "", "box_style": "",
"layout": "IPY_MODEL_72db749d8e3840238e1ceeec58a2cb4c", "layout": "IPY_MODEL_9ee03f9c85f34155b2645e89c9211547",
"_model_module": "@jupyter-widgets/controls", "_model_module": "@jupyter-widgets/controls",
"children": [ "children": [
"IPY_MODEL_4459ef1aa32e422c9f1bc152a2aba7dc", "IPY_MODEL_933ebc451c09490aadf71afbbb3dff2a",
"IPY_MODEL_b658312802194c1d86383e444af6ade4" "IPY_MODEL_8e7c55cbca624432a84fa7ad8f3a4016"
] ]
} }
}, },
"72db749d8e3840238e1ceeec58a2cb4c": { "9ee03f9c85f34155b2645e89c9211547": {
"model_module": "@jupyter-widgets/base", "model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel", "model_name": "LayoutModel",
"state": { "state": {
...@@ -332,12 +332,12 @@ ...@@ -332,12 +332,12 @@
"left": null "left": null
} }
}, },
"4459ef1aa32e422c9f1bc152a2aba7dc": { "933ebc451c09490aadf71afbbb3dff2a": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel", "model_name": "FloatProgressModel",
"state": { "state": {
"_view_name": "ProgressView", "_view_name": "ProgressView",
"style": "IPY_MODEL_e24e99052e1a4f9ea794081fc6c42d80", "style": "IPY_MODEL_dd62d83b35d04a178840772e82bd2f2e",
"_dom_classes": [], "_dom_classes": [],
"description": "100%", "description": "100%",
"_model_name": "FloatProgressModel", "_model_name": "FloatProgressModel",
...@@ -352,30 +352,30 @@ ...@@ -352,30 +352,30 @@
"min": 0, "min": 0,
"description_tooltip": null, "description_tooltip": null,
"_model_module": "@jupyter-widgets/controls", "_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_a08dda95df7441739105f5b59b8ea882" "layout": "IPY_MODEL_d5c4f3d1c8b046e3a163faaa6b3a51ab"
} }
}, },
"b658312802194c1d86383e444af6ade4": { "8e7c55cbca624432a84fa7ad8f3a4016": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel", "model_name": "HTMLModel",
"state": { "state": {
"_view_name": "HTMLView", "_view_name": "HTMLView",
"style": "IPY_MODEL_1abb5618e7134f0eb976857e126fda0d", "style": "IPY_MODEL_78d1da8efb504b03878ca9ce5b404006",
"_dom_classes": [], "_dom_classes": [],
"description": "", "description": "",
"_model_name": "HTMLModel", "_model_name": "HTMLModel",
"placeholder": "​", "placeholder": "​",
"_view_module": "@jupyter-widgets/controls", "_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0", "_model_module_version": "1.5.0",
"value": " 21.1M/21.1M [22:51<00:00, 16.1kB/s]", "value": " 21.1M/21.1M [00:01<00:00, 16.9MB/s]",
"_view_count": null, "_view_count": null,
"_view_module_version": "1.5.0", "_view_module_version": "1.5.0",
"description_tooltip": null, "description_tooltip": null,
"_model_module": "@jupyter-widgets/controls", "_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_67e56da5b8574fc7a715422bdfeaeab4" "layout": "IPY_MODEL_d28208ba1213436a93926a01d99d97ae"
} }
}, },
"e24e99052e1a4f9ea794081fc6c42d80": { "dd62d83b35d04a178840772e82bd2f2e": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel", "model_name": "ProgressStyleModel",
"state": { "state": {
...@@ -390,7 +390,7 @@ ...@@ -390,7 +390,7 @@
"_model_module": "@jupyter-widgets/controls" "_model_module": "@jupyter-widgets/controls"
} }
}, },
"a08dda95df7441739105f5b59b8ea882": { "d5c4f3d1c8b046e3a163faaa6b3a51ab": {
"model_module": "@jupyter-widgets/base", "model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel", "model_name": "LayoutModel",
"state": { "state": {
...@@ -441,7 +441,7 @@ ...@@ -441,7 +441,7 @@
"left": null "left": null
} }
}, },
"1abb5618e7134f0eb976857e126fda0d": { "78d1da8efb504b03878ca9ce5b404006": {
"model_module": "@jupyter-widgets/controls", "model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel", "model_name": "DescriptionStyleModel",
"state": { "state": {
...@@ -455,7 +455,7 @@ ...@@ -455,7 +455,7 @@
"_model_module": "@jupyter-widgets/controls" "_model_module": "@jupyter-widgets/controls"
} }
}, },
"67e56da5b8574fc7a715422bdfeaeab4": { "d28208ba1213436a93926a01d99d97ae": {
"model_module": "@jupyter-widgets/base", "model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel", "model_name": "LayoutModel",
"state": { "state": {
...@@ -547,10 +547,10 @@ ...@@ -547,10 +547,10 @@
"cell_type": "code", "cell_type": "code",
"metadata": { "metadata": {
"id": "wbvMlHd_QwMG", "id": "wbvMlHd_QwMG",
"outputId": "7e5e09a2-892e-4999-9e6c-567ea329eb38",
"colab": { "colab": {
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
} },
"outputId": "888d5c41-00e9-47d8-d230-dded99325bea"
}, },
"source": [ "source": [
"!git clone https://github.com/ultralytics/yolov5 # clone repo\n", "!git clone https://github.com/ultralytics/yolov5 # clone repo\n",
...@@ -563,7 +563,7 @@ ...@@ -563,7 +563,7 @@
"clear_output()\n", "clear_output()\n",
"print('Setup complete. Using torch %s %s' % (torch.__version__, torch.cuda.get_device_properties(0) if torch.cuda.is_available() else 'CPU'))" "print('Setup complete. Using torch %s %s' % (torch.__version__, torch.cuda.get_device_properties(0) if torch.cuda.is_available() else 'CPU'))"
], ],
"execution_count": null, "execution_count": 1,
"outputs": [ "outputs": [
{ {
"output_type": "stream", "output_type": "stream",
...@@ -589,11 +589,11 @@ ...@@ -589,11 +589,11 @@
"cell_type": "code", "cell_type": "code",
"metadata": { "metadata": {
"id": "zR9ZbuQCH7FX", "id": "zR9ZbuQCH7FX",
"outputId": "c9a308f7-2216-4805-8003-eca8dd0dc30d",
"colab": { "colab": {
"base_uri": "https://localhost:8080/", "base_uri": "https://localhost:8080/",
"height": 534 "height": 534
} },
"outputId": "c9a308f7-2216-4805-8003-eca8dd0dc30d"
}, },
"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",
...@@ -668,34 +668,34 @@ ...@@ -668,34 +668,34 @@
"cell_type": "code", "cell_type": "code",
"metadata": { "metadata": {
"id": "WQPtK1QYVaD_", "id": "WQPtK1QYVaD_",
"outputId": "12268ac4-b9eb-44de-b3a7-2bd3e2fea46f",
"colab": { "colab": {
"base_uri": "https://localhost:8080/", "base_uri": "https://localhost:8080/",
"height": 66, "height": 66,
"referenced_widgets": [ "referenced_widgets": [
"9cb5be61e41144ef9dbc9339c2f46eb1", "02ac0588602847eea00a0205f87bcce2",
"a6ba87512fd04622b9948571d330d9c0", "c472ea49806447a68b5a9221a4ddae85",
"ed1a514c303b49c0a23745f4ff17344b", "091fdf499bd44a80af7281d16da4aa93",
"79edc4bba71748338f58660262c569a9", "c79f69c959de4427ba102a87a9f46d80",
"cbbf6780f4f048feb2644ed4e3fed9c7", "c42ae5af74a0491187827d0a1fc259bb",
"e40fc489500f4e4891025c59b2b1fa8d", "5a90f72d3a2d46cb9ad915daa3ead8b4",
"191c687c120f4aab9a112697124fe444", "2a7ed6611da34662b10e37fd4f4e4438",
"6b21efad6db4407eb253f819f279671a" "fead0160658445bf9e966daa4481cad0"
] ]
} },
"outputId": "780d8f5f-766e-4b99-e370-11f9b884c27a"
}, },
"source": [ "source": [
"# Download COCO val2017\n", "# Download COCO val2017\n",
"torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco2017val.zip', 'tmp.zip')\n", "torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco2017val.zip', 'tmp.zip')\n",
"!unzip -q tmp.zip -d ../ && rm tmp.zip" "!unzip -q tmp.zip -d ../ && rm tmp.zip"
], ],
"execution_count": null, "execution_count": 2,
"outputs": [ "outputs": [
{ {
"output_type": "display_data", "output_type": "display_data",
"data": { "data": {
"application/vnd.jupyter.widget-view+json": { "application/vnd.jupyter.widget-view+json": {
"model_id": "9cb5be61e41144ef9dbc9339c2f46eb1", "model_id": "02ac0588602847eea00a0205f87bcce2",
"version_minor": 0, "version_minor": 0,
"version_major": 2 "version_major": 2
}, },
...@@ -720,47 +720,47 @@ ...@@ -720,47 +720,47 @@
"cell_type": "code", "cell_type": "code",
"metadata": { "metadata": {
"id": "X58w8JLpMnjH", "id": "X58w8JLpMnjH",
"outputId": "30601131-102c-4702-fc13-572cc6087330",
"colab": { "colab": {
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
} },
"outputId": "013935a5-ba81-4810-b723-0cb01cf7bc79"
}, },
"source": [ "source": [
"# Run YOLOv5x on COCO val2017\n", "# Run YOLOv5x on COCO val2017\n",
"!python test.py --weights yolov5x.pt --data coco.yaml --img 640" "!python test.py --weights yolov5x.pt --data coco.yaml --img 640"
], ],
"execution_count": null, "execution_count": 3,
"outputs": [ "outputs": [
{ {
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Namespace(augment=False, batch_size=32, conf_thres=0.001, data='./data/coco.yaml', device='', img_size=640, iou_thres=0.65, save_conf=False, save_dir='runs/test', save_json=True, save_txt=False, single_cls=False, task='val', verbose=False, weights=['yolov5x.pt'])\n", "Namespace(augment=False, batch_size=32, conf_thres=0.001, data='./data/coco.yaml', device='', exist_ok=False, img_size=640, iou_thres=0.65, name='exp', project='runs/test', save_conf=False, save_json=True, save_txt=False, single_cls=False, task='val', verbose=False, weights=['yolov5x.pt'])\n",
"Using torch 1.7.0+cu101 CUDA:0 (Tesla V100-SXM2-16GB, 16130MB)\n", "Using torch 1.7.0+cu101 CUDA:0 (Tesla V100-SXM2-16GB, 16130MB)\n",
"\n", "\n",
"Downloading https://github.com/ultralytics/yolov5/releases/download/v3.1/yolov5x.pt to yolov5x.pt...\n", "Downloading https://github.com/ultralytics/yolov5/releases/download/v3.1/yolov5x.pt to yolov5x.pt...\n",
"100% 170M/170M [00:05<00:00, 32.2MB/s]\n", "100% 170M/170M [00:05<00:00, 32.6MB/s]\n",
"\n", "\n",
"Fusing layers... \n", "Fusing layers... \n",
"Model Summary: 284 layers, 8.89222e+07 parameters, 0 gradients\n", "Model Summary: 484 layers, 88922205 parameters, 0 gradients\n",
"Scanning labels ../coco/labels/val2017.cache (4952 found, 0 missing, 48 empty, 0 duplicate, for 5000 images): 5000it [00:00, 16239.02it/s]\n", "Scanning labels ../coco/labels/val2017.cache (4952 found, 0 missing, 48 empty, 0 duplicate, for 5000 images): 5000it [00:00, 14785.71it/s]\n",
" Class Images Targets P R mAP@.5 mAP@.5:.95: 100% 157/157 [01:22<00:00, 1.89it/s]\n", " Class Images Targets P R mAP@.5 mAP@.5:.95: 100% 157/157 [01:30<00:00, 1.74it/s]\n",
" all 5e+03 3.63e+04 0.409 0.754 0.672 0.483\n", " all 5e+03 3.63e+04 0.409 0.754 0.672 0.484\n",
"Speed: 5.9/2.0/7.9 ms inference/NMS/total per 640x640 image at batch-size 32\n", "Speed: 5.9/2.1/7.9 ms inference/NMS/total per 640x640 image at batch-size 32\n",
"\n", "\n",
"COCO mAP with pycocotools... saving runs/test/detections_val2017_yolov5x_results.json...\n", "Evaluating pycocotools mAP... saving runs/test/exp/yolov5x_predictions.json...\n",
"loading annotations into memory...\n", "loading annotations into memory...\n",
"Done (t=0.73s)\n", "Done (t=0.43s)\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=4.48s)\n", "DONE (t=4.67s)\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=86.55s).\n", "DONE (t=92.11s).\n",
"Accumulating evaluation results...\n", "Accumulating evaluation results...\n",
"DONE (t=13.15s).\n", "DONE (t=13.24s).\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.492\n", " Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.492\n",
" Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.676\n", " Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.676\n",
" Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.534\n", " Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.534\n",
...@@ -773,7 +773,7 @@ ...@@ -773,7 +773,7 @@
" Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.493\n", " Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.493\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.723\n", " Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.723\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.812\n", " Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.812\n",
"Results saved to runs/test\n" "Results saved to runs/test/exp\n"
], ],
"name": "stdout" "name": "stdout"
} }
...@@ -831,34 +831,34 @@ ...@@ -831,34 +831,34 @@
"cell_type": "code", "cell_type": "code",
"metadata": { "metadata": {
"id": "Knxi2ncxWffW", "id": "Knxi2ncxWffW",
"outputId": "8c237907-6c62-4273-ce27-d5035fc6f5ac",
"colab": { "colab": {
"base_uri": "https://localhost:8080/", "base_uri": "https://localhost:8080/",
"height": 66, "height": 66,
"referenced_widgets": [ "referenced_widgets": [
"b434b178be4b41b3881e237e19f49b45", "cf1ab9fde7444d3e874fcd407ba8f0f8",
"72db749d8e3840238e1ceeec58a2cb4c", "9ee03f9c85f34155b2645e89c9211547",
"4459ef1aa32e422c9f1bc152a2aba7dc", "933ebc451c09490aadf71afbbb3dff2a",
"b658312802194c1d86383e444af6ade4", "8e7c55cbca624432a84fa7ad8f3a4016",
"e24e99052e1a4f9ea794081fc6c42d80", "dd62d83b35d04a178840772e82bd2f2e",
"a08dda95df7441739105f5b59b8ea882", "d5c4f3d1c8b046e3a163faaa6b3a51ab",
"1abb5618e7134f0eb976857e126fda0d", "78d1da8efb504b03878ca9ce5b404006",
"67e56da5b8574fc7a715422bdfeaeab4" "d28208ba1213436a93926a01d99d97ae"
] ]
} },
"outputId": "59f9a94b-21e1-4626-f36a-a8e1b1e5c8f6"
}, },
"source": [ "source": [
"# Download COCO128\n", "# Download COCO128\n",
"torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip', 'tmp.zip')\n", "torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip', 'tmp.zip')\n",
"!unzip -q tmp.zip -d ../ && rm tmp.zip" "!unzip -q tmp.zip -d ../ && rm tmp.zip"
], ],
"execution_count": null, "execution_count": 4,
"outputs": [ "outputs": [
{ {
"output_type": "display_data", "output_type": "display_data",
"data": { "data": {
"application/vnd.jupyter.widget-view+json": { "application/vnd.jupyter.widget-view+json": {
"model_id": "b434b178be4b41b3881e237e19f49b45", "model_id": "cf1ab9fde7444d3e874fcd407ba8f0f8",
"version_minor": 0, "version_minor": 0,
"version_major": 2 "version_major": 2
}, },
...@@ -907,27 +907,29 @@ ...@@ -907,27 +907,29 @@
"cell_type": "code", "cell_type": "code",
"metadata": { "metadata": {
"id": "1NcFxRcFdJ_O", "id": "1NcFxRcFdJ_O",
"outputId": "a98e611d-979b-4e8c-d61c-8e219958ed33",
"colab": { "colab": {
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
} },
"outputId": "138f2d1d-364c-405a-cf13-ea91a2aff915"
}, },
"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 --nosave --cache" "!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --nosave --cache"
], ],
"execution_count": null, "execution_count": 5,
"outputs": [ "outputs": [
{ {
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Using torch 1.7.0+cu101 CUDA:0 (Tesla V100-SXM2-16GB, 16130MB)\n", "Using torch 1.7.0+cu101 CUDA:0 (Tesla V100-SXM2-16GB, 16130MB)\n",
"\n", "\n",
"Namespace(adam=False, batch_size=16, bucket='', cache_images=True, cfg='', data='./data/coco128.yaml', device='', epochs=3, evolve=False, global_rank=-1, hyp='data/hyp.scratch.yaml', image_weights=False, img_size=[640, 640], local_rank=-1, log_imgs=10, logdir='runs/', multi_scale=False, name='', noautoanchor=False, nosave=True, notest=False, rect=False, resume=False, single_cls=False, sync_bn=False, total_batch_size=16, weights='yolov5s.pt', workers=8, world_size=1)\n", "Namespace(adam=False, batch_size=16, bucket='', cache_images=True, cfg='', data='./data/coco128.yaml', device='', epochs=3, evolve=False, exist_ok=False, global_rank=-1, hyp='data/hyp.scratch.yaml', image_weights=False, img_size=[640, 640], local_rank=-1, log_imgs=16, multi_scale=False, name='exp', noautoanchor=False, nosave=True, notest=False, project='runs/train', rect=False, resume=False, save_dir='runs/train/exp', single_cls=False, sync_bn=False, total_batch_size=16, weights='yolov5s.pt', workers=8, world_size=1)\n",
"Start Tensorboard with \"tensorboard --logdir runs/\", view at http://localhost:6006/\n", "Start Tensorboard with \"tensorboard --logdir runs/train\", view at http://localhost:6006/\n",
"2020-11-05 16:39:40.555423: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1\n", "2020-11-20 11:45:17.042357: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1\n",
"Install Weights & Biases for experiment logging via 'pip install wandb' (recommended)\n",
"Hyperparameters {'lr0': 0.01, 'lrf': 0.2, '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}\n", "Hyperparameters {'lr0': 0.01, 'lrf': 0.2, '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}\n",
"Downloading https://github.com/ultralytics/yolov5/releases/download/v3.1/yolov5s.pt to yolov5s.pt...\n",
"100% 14.5M/14.5M [00:01<00:00, 14.8MB/s]\n",
"\n",
"\n", "\n",
" from n params module arguments \n", " from n params module arguments \n",
" 0 -1 1 3520 models.common.Focus [3, 32, 3] \n", " 0 -1 1 3520 models.common.Focus [3, 32, 3] \n",
...@@ -955,15 +957,15 @@ ...@@ -955,15 +957,15 @@
" 22 [-1, 10] 1 0 models.common.Concat [1] \n", " 22 [-1, 10] 1 0 models.common.Concat [1] \n",
" 23 -1 1 1248768 models.common.BottleneckCSP [512, 512, 1, False] \n", " 23 -1 1 1248768 models.common.BottleneckCSP [512, 512, 1, False] \n",
" 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", " 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",
"Model Summary: 191 layers, 7.46816e+06 parameters, 7.46816e+06 gradients\n", "Model Summary: 283 layers, 7468157 parameters, 7468157 gradients\n",
"\n", "\n",
"Transferred 370/370 items from yolov5s.pt\n", "Transferred 370/370 items from yolov5s.pt\n",
"Optimizer groups: 62 .bias, 70 conv.weight, 59 other\n", "Optimizer groups: 62 .bias, 70 conv.weight, 59 other\n",
"Scanning images: 100% 128/128 [00:00<00:00, 5375.86it/s]\n", "Scanning images: 100% 128/128 [00:00<00:00, 5395.63it/s]\n",
"Scanning labels ../coco128/labels/train2017.cache (126 found, 0 missing, 2 empty, 0 duplicate, for 128 images): 128it [00:00, 15114.61it/s]\n", "Scanning labels ../coco128/labels/train2017.cache (126 found, 0 missing, 2 empty, 0 duplicate, for 128 images): 128it [00:00, 13972.28it/s]\n",
"Caching images (0.1GB): 100% 128/128 [00:00<00:00, 141.99it/s]\n", "Caching images (0.1GB): 100% 128/128 [00:00<00:00, 173.55it/s]\n",
"Scanning labels ../coco128/labels/train2017.cache (126 found, 0 missing, 2 empty, 0 duplicate, for 128 images): 128it [00:00, 12572.50it/s]\n", "Scanning labels ../coco128/labels/train2017.cache (126 found, 0 missing, 2 empty, 0 duplicate, for 128 images): 128it [00:00, 8693.98it/s]\n",
"Caching images (0.1GB): 100% 128/128 [00:01<00:00, 79.68it/s] \n", "Caching images (0.1GB): 100% 128/128 [00:00<00:00, 133.30it/s]\n",
"NumExpr defaulting to 2 threads.\n", "NumExpr defaulting to 2 threads.\n",
"\n", "\n",
"Analyzing anchors... anchors/target = 4.26, Best Possible Recall (BPR) = 0.9946\n", "Analyzing anchors... anchors/target = 4.26, Best Possible Recall (BPR) = 0.9946\n",
...@@ -973,22 +975,21 @@ ...@@ -973,22 +975,21 @@
"Starting training for 3 epochs...\n", "Starting training for 3 epochs...\n",
"\n", "\n",
" Epoch gpu_mem box obj cls total targets img_size\n", " Epoch gpu_mem box obj cls total targets img_size\n",
" 0/2 3.22G 0.04202 0.06746 0.01503 0.1245 194 640: 100% 8/8 [00:03<00:00, 2.51it/s]\n", " 0/2 5.24G 0.04202 0.06745 0.01503 0.1245 194 640: 100% 8/8 [00:03<00:00, 2.01it/s]\n",
" Class Images Targets P R mAP@.5 mAP@.5:.95: 100% 8/8 [00:03<00:00, 2.42it/s]\n", " Class Images Targets P R mAP@.5 mAP@.5:.95: 100% 8/8 [00:03<00:00, 2.40it/s]\n",
" all 128 929 0.405 0.762 0.701 0.449\n", " all 128 929 0.404 0.758 0.701 0.45\n",
"\n", "\n",
" Epoch gpu_mem box obj cls total targets img_size\n", " Epoch gpu_mem box obj cls total targets img_size\n",
" 1/2 3.17G 0.04461 0.05873 0.01689 0.1202 142 640: 100% 8/8 [00:01<00:00, 4.14it/s]\n", " 1/2 5.12G 0.04461 0.05874 0.0169 0.1202 142 640: 100% 8/8 [00:01<00:00, 4.14it/s]\n",
" Class Images Targets P R mAP@.5 mAP@.5:.95: 100% 8/8 [00:01<00:00, 6.49it/s]\n", " Class Images Targets P R mAP@.5 mAP@.5:.95: 100% 8/8 [00:01<00:00, 5.75it/s]\n",
" all 128 929 0.402 0.772 0.703 0.452\n", " all 128 929 0.403 0.772 0.703 0.453\n",
"\n", "\n",
" Epoch gpu_mem box obj cls total targets img_size\n", " Epoch gpu_mem box obj cls total targets img_size\n",
" 2/2 3.17G 0.04445 0.06545 0.01666 0.1266 149 640: 100% 8/8 [00:01<00:00, 4.33it/s]\n", " 2/2 5.12G 0.04445 0.06545 0.01667 0.1266 149 640: 100% 8/8 [00:01<00:00, 4.15it/s]\n",
" Class Images Targets P R mAP@.5 mAP@.5:.95: 100% 8/8 [00:02<00:00, 2.78it/s]\n", " Class Images Targets P R mAP@.5 mAP@.5:.95: 100% 8/8 [00:06<00:00, 1.18it/s]\n",
" all 128 929 0.395 0.766 0.701 0.455\n", " all 128 929 0.395 0.767 0.702 0.452\n",
"Optimizer stripped from runs/train/exp/weights/last.pt, 15.2MB\n", "Optimizer stripped from runs/train/exp/weights/last.pt, 15.2MB\n",
"Optimizer stripped from runs/train/exp/weights/best.pt, 15.2MB\n", "3 epochs completed in 0.006 hours.\n",
"3 epochs completed in 0.005 hours.\n",
"\n" "\n"
], ],
"name": "stdout" "name": "stdout"
...@@ -1140,10 +1141,9 @@ ...@@ -1140,10 +1141,9 @@
"id": "mcKoSIK2WSzj" "id": "mcKoSIK2WSzj"
}, },
"source": [ "source": [
"# Test all models\n", "# Test all\n",
"%%shell\n", "%%shell\n",
"for x in s m l x\n", "for x in s m l x; do\n",
"do\n",
" python test.py --weights yolov5$x.pt --data coco.yaml --img 640\n", " python test.py --weights yolov5$x.pt --data coco.yaml --img 640\n",
"done" "done"
], ],
...@@ -1156,26 +1156,22 @@ ...@@ -1156,26 +1156,22 @@
"id": "FGH0ZjkGjejy" "id": "FGH0ZjkGjejy"
}, },
"source": [ "source": [
"# Run unit tests\n", "# Unit tests\n",
"%%shell\n", "%%shell\n",
"# git clone https://github.com/ultralytics/yolov5\n", "export PYTHONPATH=\"$PWD\" # to run *.py. files in subdirectories\n",
"# cd yolov5\n",
"pip install -qr requirements.txt onnx\n",
"\n", "\n",
"export PYTHONPATH=\"$PWD\" # to run *.py. files in subdirectories\n", "for m in yolov5s; do # models\n",
"for x in yolov5s #yolov5m yolov5l yolov5x # models\n", " python train.py --weights $m.pt --epochs 3 --img 320 --device 0 # train pretrained\n",
"do\n", " python train.py --cfg $m.yaml --epochs 3 --img 320 --device 0 # train scratch\n",
" rm -rf runs\n", " for d in 0 cpu; do # devices\n",
" python train.py --weights $x.pt --cfg $x.yaml --epochs 3 --img 320 --device 0 # train\n", " python detect.py --weights $m.pt --device $d # detect official\n",
" for di in 0 cpu # inference devices\n", " python detect.py --weights runs/train/exp/weights/best.pt --device $d # detect custom\n",
" do\n", " python test.py --weights $m.pt --device $d # test official\n",
" python detect.py --weights $x.pt --device $di # detect official\n", " python test.py --weights runs/train/exp/weights/best.pt --device $d # test custom\n",
" python detect.py --weights runs/train/exp/weights/last.pt --device $di # detect custom\n",
" python test.py --weights $x.pt --device $di # test official\n",
" python test.py --weights runs/train/exp/weights/last.pt --device $di # test custom\n",
" done\n", " done\n",
" python models/yolo.py --cfg $x.yaml # inspect\n", " python hubconf.py # hub\n",
" python models/export.py --weights $x.pt --img 640 --batch 1 # export\n", " python models/yolo.py --cfg $m.yaml # inspect\n",
" python models/export.py --weights $m.pt --img 640 --batch 1 # export\n",
"done" "done"
], ],
"execution_count": null, "execution_count": null,
......
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