Skip to content

Y
yolov5
提交 2ecaa96c authored 作者: Glenn Jocher's avatar Glenn Jocher
浏览文件
操作

Created using Colaboratory

上级 00516151
隐藏空白字符变更
内嵌 并排
正在显示 包含 68 行增加 和 67 行删除
tutorial.ipynb
浏览文件 @ 2ecaa96c
......@@ -14,7 +14,7 @@
"accelerator": "GPU",
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"13e0e8b77bf54b25b8893f0b4164315f": {
"300b4d5355ef4967bd5246afeef6eef5": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"model_module_version": "1.5.0",
......@@ -29,14 +29,14 @@
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_48037f2f7fea4012b9b341f6aee75297",
"IPY_MODEL_3f3b925287274893baf5ed7bb0cf6635",
"IPY_MODEL_c44bdca7c9784b20ba2146250ee744d6"
"IPY_MODEL_84e6829bb88845a8a4f42700b8496925",
"IPY_MODEL_c038e52d41bf4d5b9602930c3d074087",
"IPY_MODEL_2667604641764341b0bc8c6afea438fd"
],
"layout": "IPY_MODEL_5b0ed23cd32c4c7d8d9467b7425684ad"
"layout": "IPY_MODEL_98b3a4806ed14102b0d75e6c571d6134"
}
},
"48037f2f7fea4012b9b341f6aee75297": {
"84e6829bb88845a8a4f42700b8496925": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
......@@ -51,13 +51,13 @@
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_1e10b4db5d644cb78bd6e005bb34038a",
"layout": "IPY_MODEL_c66a77395e42424d904699edcbb67291",
"placeholder": "​",
"style": "IPY_MODEL_a58728093ecb4eafb826bee11a84c549",
"style": "IPY_MODEL_c4bbc15bf853439399dbcf1d40a5a407",
"value": "100%"
}
},
"3f3b925287274893baf5ed7bb0cf6635": {
"c038e52d41bf4d5b9602930c3d074087": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
......@@ -73,15 +73,15 @@
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_9ce169fe4b8543c0b26d745daa230f18",
"layout": "IPY_MODEL_0aaabfac395b43afbdd6d752c502bbf6",
"max": 818322941,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_d5da01aca8fb400c96e76f44c9403581",
"style": "IPY_MODEL_3786d970492b4aa38f886f2572fd958c",
"value": 818322941
}
},
"c44bdca7c9784b20ba2146250ee744d6": {
"2667604641764341b0bc8c6afea438fd": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
......@@ -96,13 +96,13 @@
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_98cbaa572fdd4c42975f52015672b3a5",
"layout": "IPY_MODEL_b86d0f2d7be74cebbcaa884b53123eeb",
"placeholder": "​",
"style": "IPY_MODEL_a636aa81f5cc453099c9e552f0986e63",
"value": " 780M/780M [01:27<00:00, 6.98MB/s]"
"style": "IPY_MODEL_fa7b1497925a457f89286a71f073f416",
"value": " 780M/780M [00:57<00:00, 10.1MB/s]"
}
},
"5b0ed23cd32c4c7d8d9467b7425684ad": {
"98b3a4806ed14102b0d75e6c571d6134": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
......@@ -154,7 +154,7 @@
"width": null
}
},
"1e10b4db5d644cb78bd6e005bb34038a": {
"c66a77395e42424d904699edcbb67291": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
......@@ -206,7 +206,7 @@
"width": null
}
},
"a58728093ecb4eafb826bee11a84c549": {
"c4bbc15bf853439399dbcf1d40a5a407": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
......@@ -221,7 +221,7 @@
"description_width": ""
}
},
"9ce169fe4b8543c0b26d745daa230f18": {
"0aaabfac395b43afbdd6d752c502bbf6": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
......@@ -273,7 +273,7 @@
"width": null
}
},
"d5da01aca8fb400c96e76f44c9403581": {
"3786d970492b4aa38f886f2572fd958c": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
......@@ -289,7 +289,7 @@
"description_width": ""
}
},
"98cbaa572fdd4c42975f52015672b3a5": {
"b86d0f2d7be74cebbcaa884b53123eeb": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
......@@ -341,7 +341,7 @@
"width": null
}
},
"a636aa81f5cc453099c9e552f0986e63": {
"fa7b1497925a457f89286a71f073f416": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
......@@ -401,7 +401,7 @@
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "bcb6db4a-fc21-4258-9b53-4a760a534656"
"outputId": "32e3bc15-6d02-4352-f0a3-912059d134a5"
},
"source": [
"!git clone https://github.com/ultralytics/yolov5 # clone\n",
......@@ -418,7 +418,7 @@
"output_type": "stream",
"name": "stderr",
"text": [
"YOLOv5 🚀 v6.2-250-g467a57f Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n"
"YOLOv5 🚀 v6.2-256-g0051615 Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n"
]
},
{
......@@ -459,7 +459,7 @@
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "de684b46-7623-4836-ee44-49cdb320cbf3"
"outputId": "8e81d6e9-0360-4212-cd61-9a5a58d3f703"
},
"source": [
"!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images\n",
......@@ -472,16 +472,16 @@
"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, vid_stride=1\n",
"YOLOv5 🚀 v6.2-250-g467a57f Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n",
"YOLOv5 🚀 v6.2-256-g0051615 Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\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, 162MB/s]\n",
"100% 14.1M/14.1M [00:00<00:00, 19.5MB/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, 17.2ms\n",
"image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, 13.3ms\n",
"Speed: 0.5ms pre-process, 15.2ms inference, 19.5ms NMS per image at shape (1, 3, 640, 640)\n",
"image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, 17.5ms\n",
"image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, 18.0ms\n",
"Speed: 0.5ms pre-process, 17.8ms inference, 17.6ms NMS per image at shape (1, 3, 640, 640)\n",
"Results saved to \u001b[1mruns/detect/exp\u001b[0m\n"
]
}
......@@ -515,20 +515,20 @@
"base_uri": "https://localhost:8080/",
"height": 49,
"referenced_widgets": [
"13e0e8b77bf54b25b8893f0b4164315f",
"48037f2f7fea4012b9b341f6aee75297",
"3f3b925287274893baf5ed7bb0cf6635",
"c44bdca7c9784b20ba2146250ee744d6",
"5b0ed23cd32c4c7d8d9467b7425684ad",
"1e10b4db5d644cb78bd6e005bb34038a",
"a58728093ecb4eafb826bee11a84c549",
"9ce169fe4b8543c0b26d745daa230f18",
"d5da01aca8fb400c96e76f44c9403581",
"98cbaa572fdd4c42975f52015672b3a5",
"a636aa81f5cc453099c9e552f0986e63"
"300b4d5355ef4967bd5246afeef6eef5",
"84e6829bb88845a8a4f42700b8496925",
"c038e52d41bf4d5b9602930c3d074087",
"2667604641764341b0bc8c6afea438fd",
"98b3a4806ed14102b0d75e6c571d6134",
"c66a77395e42424d904699edcbb67291",
"c4bbc15bf853439399dbcf1d40a5a407",
"0aaabfac395b43afbdd6d752c502bbf6",
"3786d970492b4aa38f886f2572fd958c",
"b86d0f2d7be74cebbcaa884b53123eeb",
"fa7b1497925a457f89286a71f073f416"
]
},
"outputId": "b1e02a1f-981f-4739-e75d-10d0204cc32d"
"outputId": "61ffec5e-90ea-44f6-c0ea-b006e6e7072f"
},
"source": [
"# Download COCO val\n",
......@@ -546,7 +546,7 @@
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "13e0e8b77bf54b25b8893f0b4164315f"
"model_id": "300b4d5355ef4967bd5246afeef6eef5"
}
},
"metadata": {}
......@@ -560,7 +560,7 @@
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "9c2f755f-f383-4a9e-cd19-f73a0c763a9c"
"outputId": "aa5d5cea-14c1-4a19-bfdf-95b7164962cf"
},
"source": [
"# Validate YOLOv5s on COCO val\n",
......@@ -573,30 +573,30 @@
"name": "stdout",
"text": [
"\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, max_det=300, 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 🚀 v6.2-250-g467a57f Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n",
"YOLOv5 🚀 v6.2-256-g0051615 Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n",
"\n",
"Fusing layers... \n",
"YOLOv5s summary: 213 layers, 7225885 parameters, 0 gradients\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 [00:02<00:00, 2019.92it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mScanning /content/datasets/coco/val2017... 4952 images, 48 backgrounds, 0 corrupt: 100% 5000/5000 [00:02<00:00, 2066.57it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /content/datasets/coco/val2017.cache\n",
" Class Images Instances P R mAP50 mAP50-95: 100% 157/157 [01:09<00:00, 2.25it/s]\n",
" Class Images Instances P R mAP50 mAP50-95: 100% 157/157 [01:09<00:00, 2.26it/s]\n",
" all 5000 36335 0.67 0.521 0.566 0.371\n",
"Speed: 0.2ms pre-process, 2.7ms inference, 2.1ms NMS per image at shape (32, 3, 640, 640)\n",
"Speed: 0.1ms pre-process, 2.7ms inference, 1.9ms NMS per image at shape (32, 3, 640, 640)\n",
"\n",
"Evaluating pycocotools mAP... saving runs/val/exp/yolov5s_predictions.json...\n",
"loading annotations into memory...\n",
"Done (t=0.41s)\n",
"Done (t=0.82s)\n",
"creating index...\n",
"index created!\n",
"Loading and preparing results...\n",
"DONE (t=6.19s)\n",
"DONE (t=5.49s)\n",
"creating index...\n",
"index created!\n",
"Running per image evaluation...\n",
"Evaluate annotation type *bbox*\n",
"DONE (t=75.81s).\n",
"DONE (t=74.26s).\n",
"Accumulating evaluation results...\n",
"DONE (t=15.26s).\n",
"DONE (t=13.46s).\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",
......@@ -676,7 +676,7 @@
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "7d03d4d2-9a6e-47de-88f4-c673b55c73c5"
"outputId": "f0fcdc77-5326-41e1-bacc-be5432eefa2a"
},
"source": [
"# Train YOLOv5s on COCO128 for 3 epochs\n",
......@@ -690,7 +690,7 @@
"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 🚀 v6.2-250-g467a57f Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n",
"YOLOv5 🚀 v6.2-256-g0051615 Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\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[1mClearML: \u001b[0mrun 'pip install clearml' to automatically track, visualize and remotely train YOLOv5 🚀 in ClearML\n",
......@@ -699,8 +699,8 @@
"\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, 26.1MB/s]\n",
"Dataset download success ✅ (0.9s), saved to \u001b[1m/content/datasets\u001b[0m\n",
"100% 6.66M/6.66M [00:00<00:00, 39.8MB/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",
......@@ -734,11 +734,11 @@
"\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...126 found, 2 missing, 0 empty, 0 corrupt: 100% 128/128 [00:00<00:00, 1989.66it/s]\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mScanning /content/datasets/coco128/labels/train2017... 126 images, 2 backgrounds, 0 corrupt: 100% 128/128 [00:00<00:00, 2084.63it/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, 246.25it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mScanning '/content/datasets/coco128/labels/train2017.cache' images and labels... 126 found, 2 missing, 0 empty, 0 corrupt: 100% 128/128 [00:00<?, ?it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:01<00:00, 101.45it/s]\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 255.09it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mScanning /content/datasets/coco128/labels/train2017.cache... 126 images, 2 backgrounds, 0 corrupt: 100% 128/128 [00:00<?, ?it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:01<00:00, 106.58it/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",
......@@ -749,17 +749,17 @@
"\n",
" Epoch GPU_mem box_loss obj_loss cls_loss Instances Size\n",
" 0/2 3.74G 0.04618 0.07207 0.017 232 640: 100% 8/8 [00:06<00:00, 1.33it/s]\n",
" Class Images Instances P R mAP50 mAP50-95: 100% 4/4 [00:01<00:00, 2.84it/s]\n",
" Class Images Instances P R mAP50 mAP50-95: 100% 4/4 [00:01<00:00, 2.99it/s]\n",
" all 128 929 0.672 0.594 0.682 0.451\n",
"\n",
" Epoch GPU_mem box_loss obj_loss cls_loss Instances Size\n",
" 1/2 5.36G 0.04623 0.06888 0.01821 201 640: 100% 8/8 [00:02<00:00, 3.29it/s]\n",
" Class Images Instances P R mAP50 mAP50-95: 100% 4/4 [00:01<00:00, 3.12it/s]\n",
" 1/2 5.36G 0.04623 0.06888 0.01821 201 640: 100% 8/8 [00:02<00:00, 3.28it/s]\n",
" Class Images Instances P R mAP50 mAP50-95: 100% 4/4 [00:01<00:00, 3.02it/s]\n",
" all 128 929 0.721 0.639 0.724 0.48\n",
"\n",
" Epoch GPU_mem box_loss obj_loss cls_loss Instances Size\n",
" 2/2 5.36G 0.04361 0.06479 0.01698 227 640: 100% 8/8 [00:02<00:00, 3.39it/s]\n",
" Class Images Instances P R mAP50 mAP50-95: 100% 4/4 [00:01<00:00, 3.13it/s]\n",
" 2/2 5.36G 0.04361 0.06479 0.01698 227 640: 100% 8/8 [00:02<00:00, 3.50it/s]\n",
" Class Images Instances P R mAP50 mAP50-95: 100% 4/4 [00:01<00:00, 3.05it/s]\n",
" all 128 929 0.758 0.641 0.731 0.487\n",
"\n",
"3 epochs completed in 0.005 hours.\n",
......@@ -769,7 +769,7 @@
"Validating runs/train/exp/weights/best.pt...\n",
"Fusing layers... \n",
"Model summary: 157 layers, 7225885 parameters, 0 gradients, 16.4 GFLOPs\n",
" Class Images Instances P R mAP50 mAP50-95: 100% 4/4 [00:03<00:00, 1.04it/s]\n",
" Class Images Instances P R mAP50 mAP50-95: 100% 4/4 [00:03<00:00, 1.09it/s]\n",
" all 128 929 0.757 0.641 0.732 0.487\n",
" person 128 254 0.86 0.705 0.804 0.528\n",
" bicycle 128 6 0.773 0.578 0.725 0.426\n",
......@@ -972,4 +972,4 @@
"outputs": []
}
]
}
}
\ No newline at end of file
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