{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "YOLOv5 Tutorial",
"provenance": [],
"collapsed_sections": [],
"toc_visible": true,
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "GPU",
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"2e915d9016c846e095e382b6a02ee773": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "HBoxView",
"_dom_classes": [],
"_model_name": "HBoxModel",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.5.0",
"box_style": "",
"layout": "IPY_MODEL_cb7fc3a5c6cc4fde8d2c83e594a7c86e",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_ac3edef4e3434f4587e6cbf8aa048770",
"IPY_MODEL_853ac234cc2a4236946fc516871e10eb"
]
}
},
"cb7fc3a5c6cc4fde8d2c83e594a7c86e": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"ac3edef4e3434f4587e6cbf8aa048770": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_13842ca90c0047e584b8d68d99dad2b1",
"_dom_classes": [],
"description": "100%",
"_model_name": "FloatProgressModel",
"bar_style": "success",
"max": 818322941,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 818322941,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_f454999c3a924c7bad0746fb453dec36"
}
},
"853ac234cc2a4236946fc516871e10eb": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_f94a7ca8c1f04761bf38fdc5f99664b8",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 780M/780M [03:59<00:00, 3.42MB/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_9da1a23b042c41618dd14b0e30aa7cbe"
}
},
"13842ca90c0047e584b8d68d99dad2b1": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "initial",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"f454999c3a924c7bad0746fb453dec36": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"f94a7ca8c1f04761bf38fdc5f99664b8": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "StyleView",
"_model_name": "DescriptionStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"_model_module": "@jupyter-widgets/controls"
}
},
"9da1a23b042c41618dd14b0e30aa7cbe": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"6ff8a710ded44391a624dec5c460b771": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "HBoxView",
"_dom_classes": [],
"_model_name": "HBoxModel",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.5.0",
"box_style": "",
"layout": "IPY_MODEL_3c19729b51cd45d4848035da06e96ff8",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_23b2f0ae3d46438c8de375987c77f580",
"IPY_MODEL_dd9498c321a9422da6faf17a0be026d4"
]
}
},
"3c19729b51cd45d4848035da06e96ff8": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"23b2f0ae3d46438c8de375987c77f580": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_d8dda4b2ce864fd682e558b9a48f602e",
"_dom_classes": [],
"description": "100%",
"_model_name": "FloatProgressModel",
"bar_style": "success",
"max": 6984509,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 6984509,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_ff8151449e444a14869684212b9ab14e"
}
},
"dd9498c321a9422da6faf17a0be026d4": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_0f84fe609bcf4aa9afdc32a8cf076909",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 6.66M/6.66M [00:01<00:00, 6.08MB/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_8fda673769984e2b928ef820d34c85c3"
}
},
"d8dda4b2ce864fd682e558b9a48f602e": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "initial",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"ff8151449e444a14869684212b9ab14e": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"0f84fe609bcf4aa9afdc32a8cf076909": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "StyleView",
"_model_name": "DescriptionStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"_model_module": "@jupyter-widgets/controls"
}
},
"8fda673769984e2b928ef820d34c85c3": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
}
}
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "t6MPjfT5NrKQ"
},
"source": [
"\n",
"\n",
"\n",
"This is the **official YOLOv5 🚀 notebook** authored by **Ultralytics**, and is freely available for redistribution under the [GPL-3.0 license](https://choosealicense.com/licenses/gpl-3.0/). \n",
"For more information please visit https://github.com/ultralytics/yolov5 and https://ultralytics.com. Thank you!"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "7mGmQbAO5pQb"
},
"source": [
"# Setup\n",
"\n",
"Clone repo, install dependencies and check PyTorch and GPU."
]
},
{
"cell_type": "code",
"metadata": {
"id": "wbvMlHd_QwMG",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "ada1dd8d-e0aa-4858-e893-dc320319ca30"
},
"source": [
"!git clone https://github.com/ultralytics/yolov5 # clone repo\n",
"%cd yolov5\n",
"%pip install -qr requirements.txt # install dependencies\n",
"\n",
"import torch\n",
"from IPython.display import Image, clear_output # to display images\n",
"\n",
"clear_output()\n",
"print(f\"Setup complete. Using torch {torch.__version__} ({torch.cuda.get_device_properties(0).name if torch.cuda.is_available() else 'CPU'})\")"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"Setup complete. Using torch 1.9.0+cu102 (Tesla V100-SXM2-16GB)\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "4JnkELT0cIJg"
},
"source": [
"# 1. Inference\n",
"\n",
"`detect.py` runs YOLOv5 inference on a variety of sources, downloading models automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases), and saving results to `runs/detect`. Example inference sources are:\n",
"\n",
"```shell\n",
"python detect.py --source 0 # webcam\n",
" file.jpg # image \n",
" file.mp4 # video\n",
" path/ # directory\n",
" path/*.jpg # glob\n",
" 'https://youtu.be/NUsoVlDFqZg' # YouTube\n",
" 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream\n",
"```"
]
},
{
"cell_type": "code",
"metadata": {
"id": "zR9ZbuQCH7FX",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "a7a37616-a82b-4bdb-a463-6ead850b5615"
},
"source": [
"!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images/\n",
"Image(filename='runs/detect/exp/zidane.jpg', width=600)"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov5s.pt'], source=data/images/, imgsz=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\n",
"YOLOv5 🚀 v5.0-330-g18f6ba7 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",
"\n",
"Fusing layers... \n",
"Model Summary: 224 layers, 7266973 parameters, 0 gradients\n",
"image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, 1 fire hydrant, Done. (0.008s)\n",
"image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.008s)\n",
"Results saved to runs/detect/exp\n",
"Done. (0.091s)\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "hkAzDWJ7cWTr"
},
"source": [
" \n",
""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "0eq1SMWl6Sfn"
},
"source": [
"# 2. Validate\n",
"Validate a model's accuracy on [COCO](https://cocodataset.org/#home) val or test-dev datasets. Models are downloaded automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases). To show results by class use the `--verbose` flag. Note that `pycocotools` metrics may be ~1% better than the equivalent repo metrics, as is visible below, due to slight differences in mAP computation."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "eyTZYGgRjnMc"
},
"source": [
"## COCO val2017\n",
"Download [COCO val 2017](https://github.com/ultralytics/yolov5/blob/74b34872fdf41941cddcf243951cdb090fbac17b/data/coco.yaml#L14) dataset (1GB - 5000 images), and test model accuracy."
]
},
{
"cell_type": "code",
"metadata": {
"id": "WQPtK1QYVaD_",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 66,
"referenced_widgets": [
"2e915d9016c846e095e382b6a02ee773",
"cb7fc3a5c6cc4fde8d2c83e594a7c86e",
"ac3edef4e3434f4587e6cbf8aa048770",
"853ac234cc2a4236946fc516871e10eb",
"13842ca90c0047e584b8d68d99dad2b1",
"f454999c3a924c7bad0746fb453dec36",
"f94a7ca8c1f04761bf38fdc5f99664b8",
"9da1a23b042c41618dd14b0e30aa7cbe"
]
},
"outputId": "3606f305-aa67-43fd-d5d6-93d1f311768c"
},
"source": [
"# Download COCO val2017\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 ../datasets && rm tmp.zip"
],
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "2e915d9016c846e095e382b6a02ee773",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=0.0, max=818322941.0), HTML(value='')))"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "X58w8JLpMnjH",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "20fbc423-f536-43ff-e70b-3acf6aeade99"
},
"source": [
"# Run YOLOv5x on COCO val2017\n",
"!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"\u001b[34m\u001b[1mval: \u001b[0mdata=./data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.65, task=val, device=, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True\n",
"YOLOv5 🚀 v5.0-330-g18f6ba7 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",
"\n",
"Downloading https://github.com/ultralytics/yolov5/releases/download/v5.0/yolov5x.pt to yolov5x.pt...\n",
"100% 168M/168M [00:05<00:00, 31.9MB/s]\n",
"\n",
"Fusing layers... \n",
"Model Summary: 476 layers, 87730285 parameters, 0 gradients\n",
"\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:01<00:00, 2653.03it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mNew cache created: ../datasets/coco/val2017.cache\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [01:18<00:00, 2.00it/s]\n",
" all 5000 36335 0.746 0.626 0.68 0.49\n",
"Speed: 0.1ms pre-process, 5.1ms 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",
"loading annotations into memory...\n",
"Done (t=0.44s)\n",
"creating index...\n",
"index created!\n",
"Loading and preparing results...\n",
"DONE (t=4.82s)\n",
"creating index...\n",
"index created!\n",
"Running per image evaluation...\n",
"Evaluate annotation type *bbox*\n",
"DONE (t=84.52s).\n",
"Accumulating evaluation results...\n",
"DONE (t=13.82s).\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.504\n",
" Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.688\n",
" Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.546\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.351\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.551\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.644\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 ] = 0.629\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.681\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.524\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.735\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.827\n",
"Results saved to runs/val/exp\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "rc_KbFk0juX2"
},
"source": [
"## COCO test-dev2017\n",
"Download [COCO test2017](https://github.com/ultralytics/yolov5/blob/74b34872fdf41941cddcf243951cdb090fbac17b/data/coco.yaml#L15) dataset (7GB - 40,000 images), to test model accuracy on test-dev set (**20,000 images, no labels**). Results are saved to a `*.json` file which should be **zipped** and submitted to the evaluation server at https://competitions.codalab.org/competitions/20794."
]
},
{
"cell_type": "code",
"metadata": {
"id": "V0AJnSeCIHyJ"
},
"source": [
"# Download COCO test-dev2017\n",
"torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco2017labels.zip', 'tmp.zip')\n",
"!unzip -q tmp.zip -d ../ && rm tmp.zip # unzip labels\n",
"!f=\"test2017.zip\" && curl http://images.cocodataset.org/zips/$f -o $f && unzip -q $f && rm $f # 7GB, 41k images\n",
"%mv ./test2017 ../coco/images # move to /coco"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "29GJXAP_lPrt"
},
"source": [
"# Run YOLOv5s on COCO test-dev2017 using --task test\n",
"!python val.py --weights yolov5s.pt --data coco.yaml --task test"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "VUOiNLtMP5aG"
},
"source": [
"# 3. Train\n",
"\n",
"Download [COCO128](https://www.kaggle.com/ultralytics/coco128), a small 128-image tutorial dataset, start tensorboard and train YOLOv5s from a pretrained checkpoint for 3 epochs (note actual training is typically much longer, around **300-1000 epochs**, depending on your dataset)."
]
},
{
"cell_type": "code",
"metadata": {
"id": "Knxi2ncxWffW",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 66,
"referenced_widgets": [
"6ff8a710ded44391a624dec5c460b771",
"3c19729b51cd45d4848035da06e96ff8",
"23b2f0ae3d46438c8de375987c77f580",
"dd9498c321a9422da6faf17a0be026d4",
"d8dda4b2ce864fd682e558b9a48f602e",
"ff8151449e444a14869684212b9ab14e",
"0f84fe609bcf4aa9afdc32a8cf076909",
"8fda673769984e2b928ef820d34c85c3"
]
},
"outputId": "4510c6b0-8d2a-436c-d3f4-c8f8470d913a"
},
"source": [
"# Download COCO128\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"
],
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "6ff8a710ded44391a624dec5c460b771",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=0.0, max=6984509.0), HTML(value='')))"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "_pOkGLv1dMqh"
},
"source": [
"Train a YOLOv5s model on [COCO128](https://www.kaggle.com/ultralytics/coco128) with `--data coco128.yaml`, starting from pretrained `--weights yolov5s.pt`, or from randomly initialized `--weights '' --cfg yolov5s.yaml`. Models are downloaded automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases), and **COCO, COCO128, and VOC datasets are downloaded automatically** on first use.\n",
"\n",
"All training results are saved to `runs/train/` with incrementing run directories, i.e. `runs/train/exp2`, `runs/train/exp3` etc.\n"
]
},
{
"cell_type": "code",
"metadata": {
"id": "bOy5KI2ncnWd"
},
"source": [
"# Tensorboard (optional)\n",
"%load_ext tensorboard\n",
"%tensorboard --logdir runs/train"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "2fLAV42oNb7M"
},
"source": [
"# Weights & Biases (optional)\n",
"%pip install -q wandb\n",
"import wandb\n",
"wandb.login()"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "1NcFxRcFdJ_O",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "cd8ac17d-19a8-4e87-ab6a-31af1edac1ef"
},
"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,
"outputs": [
{
"output_type": "stream",
"text": [
"\u001b[34m\u001b[1mtrain: \u001b[0mweights=yolov5s.pt, cfg=, data=coco128.yaml, hyp=data/hyps/hyp.scratch.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, evolve=None, bucket=, cache_images=True, image_weights=False, device=, multi_scale=False, single_cls=False, adam=False, sync_bn=False, workers=8, project=runs/train, entity=None, name=exp, exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, upload_dataset=False, bbox_interval=-1, save_period=-1, artifact_alias=latest, local_rank=-1\n",
"\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov5 ✅\n",
"YOLOv5 🚀 v5.0-330-g18f6ba7 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",
"\n",
"\u001b[34m\u001b[1mhyperparameters: \u001b[0mlr0=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, copy_paste=0.0\n",
"\u001b[34m\u001b[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)\n",
"\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/\n",
"2021-07-29 22:56:52.096481: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudart.so.11.0\n",
"\n",
"WARNING: Dataset not found, nonexistent paths: ['/content/datasets/coco128/images/train2017']\n",
"Downloading https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip ...\n",
"100% 6.66M/6.66M [00:00<00:00, 44.0MB/s]\n",
"Dataset autodownload success\n",
"\n",
"\n",
" from n params module arguments \n",
" 0 -1 1 3520 models.common.Focus [3, 32, 3] \n",
" 1 -1 1 18560 models.common.Conv [32, 64, 3, 2] \n",
" 2 -1 1 18816 models.common.C3 [64, 64, 1] \n",
" 3 -1 1 73984 models.common.Conv [64, 128, 3, 2] \n",
" 4 -1 1 156928 models.common.C3 [128, 128, 3] \n",
" 5 -1 1 295424 models.common.Conv [128, 256, 3, 2] \n",
" 6 -1 1 625152 models.common.C3 [256, 256, 3] \n",
" 7 -1 1 1180672 models.common.Conv [256, 512, 3, 2] \n",
" 8 -1 1 656896 models.common.SPP [512, 512, [5, 9, 13]] \n",
" 9 -1 1 1182720 models.common.C3 [512, 512, 1, False] \n",
" 10 -1 1 131584 models.common.Conv [512, 256, 1, 1] \n",
" 11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n",
" 12 [-1, 6] 1 0 models.common.Concat [1] \n",
" 13 -1 1 361984 models.common.C3 [512, 256, 1, False] \n",
" 14 -1 1 33024 models.common.Conv [256, 128, 1, 1] \n",
" 15 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n",
" 16 [-1, 4] 1 0 models.common.Concat [1] \n",
" 17 -1 1 90880 models.common.C3 [256, 128, 1, False] \n",
" 18 -1 1 147712 models.common.Conv [128, 128, 3, 2] \n",
" 19 [-1, 14] 1 0 models.common.Concat [1] \n",
" 20 -1 1 296448 models.common.C3 [256, 256, 1, False] \n",
" 21 -1 1 590336 models.common.Conv [256, 256, 3, 2] \n",
" 22 [-1, 10] 1 0 models.common.Concat [1] \n",
" 23 -1 1 1182720 models.common.C3 [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",
"Model Summary: 283 layers, 7276605 parameters, 7276605 gradients, 17.1 GFLOPs\n",
"\n",
"Transferred 362/362 items from yolov5s.pt\n",
"Scaled weight_decay = 0.0005\n",
"\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 59 weight, 62 weight (no decay), 62 bias\n",
"\u001b[34m\u001b[1malbumentations: \u001b[0mversion 1.0.3 required by YOLOv5, but version 0.1.12 is currently installed\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mScanning '../datasets/coco128/labels/train2017' images and labels...128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<00:00, 2021.98it/s]\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: ../datasets/coco128/labels/train2017.cache\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB): 100% 128/128 [00:00<00:00, 273.58it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<00:00, 506004.63it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB): 100% 128/128 [00:01<00:00, 121.71it/s]\n",
"[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)\n",
"[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)\n",
"Plotting labels... \n",
"\n",
"\u001b[34m\u001b[1mautoanchor: \u001b[0mAnalyzing anchors... anchors/target = 4.27, Best Possible Recall (BPR) = 0.9935\n",
"Image sizes 640 train, 640 val\n",
"Using 2 dataloader workers\n",
"Logging results to runs/train/exp\n",
"Starting training for 3 epochs...\n",
"\n",
" Epoch gpu_mem box obj cls labels img_size\n",
" 0/2 3.64G 0.0441 0.06646 0.02229 290 640: 100% 8/8 [00:04<00:00, 1.93it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 3.45it/s]\n",
" all 128 929 0.696 0.562 0.644 0.419\n",
"\n",
" Epoch gpu_mem box obj cls labels img_size\n",
" 1/2 5.04G 0.04573 0.06289 0.021 226 640: 100% 8/8 [00:01<00:00, 5.46it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 3.16it/s]\n",
" all 128 929 0.71 0.567 0.654 0.424\n",
"\n",
" Epoch gpu_mem box obj cls labels img_size\n",
" 2/2 5.04G 0.04542 0.0715 0.02028 242 640: 100% 8/8 [00:01<00:00, 5.12it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.46it/s]\n",
" all 128 929 0.731 0.563 0.658 0.427\n",
"3 epochs completed in 0.006 hours.\n",
"\n",
"Optimizer stripped from runs/train/exp/weights/last.pt, 14.8MB\n",
"Optimizer stripped from runs/train/exp/weights/best.pt, 14.8MB\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "15glLzbQx5u0"
},
"source": [
"# 4. Visualize"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "DLI1JmHU7B0l"
},
"source": [
"## Weights & Biases Logging 🌟 NEW\n",
"\n",
"[Weights & Biases](https://wandb.ai/site?utm_campaign=repo_yolo_notebook) (W&B) is now integrated with YOLOv5 for real-time visualization and cloud logging of training runs. This allows for better run comparison and introspection, as well improved visibility and collaboration for teams. To enable W&B `pip install wandb`, and then train normally (you will be guided through setup on first use). \n",
"\n",
"During training you will see live updates at [https://wandb.ai/home](https://wandb.ai/home?utm_campaign=repo_yolo_notebook), and you can create and share detailed [Reports](https://wandb.ai/glenn-jocher/yolov5_tutorial/reports/YOLOv5-COCO128-Tutorial-Results--VmlldzozMDI5OTY) of your results. For more information see the [YOLOv5 Weights & Biases Tutorial](https://github.com/ultralytics/yolov5/issues/1289). \n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "-WPvRbS5Swl6"
},
"source": [
"## Local Logging\n",
"\n",
"All results are logged by default to `runs/train`, with a new experiment directory created for each new training as `runs/train/exp2`, `runs/train/exp3`, etc. View train and val jpgs to see mosaics, labels, predictions and augmentation effects. Note an Ultralytics **Mosaic Dataloader** is used for training (shown below), which combines 4 images into 1 mosaic during training.\n",
"\n",
"> \n",
"`train_batch0.jpg` shows train batch 0 mosaics and labels\n",
"\n",
"> \n",
"`test_batch0_labels.jpg` shows val batch 0 labels\n",
"\n",
"> \n",
"`test_batch0_pred.jpg` shows val batch 0 _predictions_\n",
"\n",
"Training results are automatically logged to [Tensorboard](https://www.tensorflow.org/tensorboard) and [CSV](https://github.com/ultralytics/yolov5/pull/4148) as `results.csv`, which is plotted as `results.png` (below) after training completes. You can also plot any `results.csv` file manually:\n",
"\n",
"```python\n",
"from utils.plots import plot_results \n",
"plot_results('path/to/results.csv') # plot 'results.csv' as 'results.png'\n",
"```\n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Zelyeqbyt3GD"
},
"source": [
"# Environments\n",
"\n",
"YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled):\n",
"\n",
"- **Google Colab and Kaggle** notebooks with free GPU: \n",
"- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart)\n",
"- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart)\n",
"- **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) \n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "6Qu7Iesl0p54"
},
"source": [
"# Status\n",
"\n",
"![CI CPU testing](https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg)\n",
"\n",
"If this badge is green, all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training ([train.py](https://github.com/ultralytics/yolov5/blob/master/train.py)), testing ([val.py](https://github.com/ultralytics/yolov5/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov5/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov5/blob/master/export.py)) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "IEijrePND_2I"
},
"source": [
"# Appendix\n",
"\n",
"Optional extras below. Unit tests validate repo functionality and should be run on any PRs submitted.\n"
]
},
{
"cell_type": "code",
"metadata": {
"id": "mcKoSIK2WSzj"
},
"source": [
"# Reproduce\n",
"for x in 'yolov5s', 'yolov5m', 'yolov5l', 'yolov5x':\n",
" !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.25 --iou 0.45 # speed\n",
" !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.001 --iou 0.65 # mAP"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "GMusP4OAxFu6"
},
"source": [
"# PyTorch Hub\n",
"import torch\n",
"\n",
"# Model\n",
"model = torch.hub.load('ultralytics/yolov5', 'yolov5s')\n",
"\n",
"# Images\n",
"dir = 'https://ultralytics.com/images/'\n",
"imgs = [dir + f for f in ('zidane.jpg', 'bus.jpg')] # batch of images\n",
"\n",
"# Inference\n",
"results = model(imgs)\n",
"results.print() # or .show(), .save()"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "FGH0ZjkGjejy"
},
"source": [
"# Unit tests\n",
"%%shell\n",
"export PYTHONPATH=\"$PWD\" # to run *.py. files in subdirectories\n",
"\n",
"rm -rf runs # remove runs/\n",
"for m in yolov5s; do # models\n",
" python train.py --weights $m.pt --epochs 3 --img 320 --device 0 # train pretrained\n",
" python train.py --weights '' --cfg $m.yaml --epochs 3 --img 320 --device 0 # train scratch\n",
" for d in 0 cpu; do # devices\n",
" python detect.py --weights $m.pt --device $d # detect official\n",
" python detect.py --weights runs/train/exp/weights/best.pt --device $d # detect custom\n",
" python val.py --weights $m.pt --device $d # val official\n",
" python val.py --weights runs/train/exp/weights/best.pt --device $d # val custom\n",
" done\n",
" python hubconf.py # hub\n",
" python models/yolo.py --cfg $m.yaml # inspect\n",
" python export.py --weights $m.pt --img 640 --batch 1 # export\n",
"done"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "gogI-kwi3Tye"
},
"source": [
"# Profile\n",
"from utils.torch_utils import profile\n",
"\n",
"m1 = lambda x: x * torch.sigmoid(x)\n",
"m2 = torch.nn.SiLU()\n",
"results = profile(input=torch.randn(16, 3, 640, 640), ops=[m1, m2], n=100)"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "RVRSOhEvUdb5"
},
"source": [
"# Evolve\n",
"!python train.py --img 640 --batch 64 --epochs 100 --data coco128.yaml --weights yolov5s.pt --cache --noautoanchor --evolve\n",
"!d=runs/train/evolve && cp evolve.* $d && zip -r evolve.zip $d && gsutil mv evolve.zip gs://bucket # upload results (optional)"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "BSgFCAcMbk1R"
},
"source": [
"# VOC\n",
"for b, m in zip([64, 48, 32, 16], ['yolov5s', 'yolov5m', 'yolov5l', 'yolov5x']): # zip(batch_size, model)\n",
" !python train.py --batch {b} --weights {m}.pt --data VOC.yaml --epochs 50 --cache --img 512 --nosave --hyp hyp.finetune.yaml --project VOC --name {m}"
],
"execution_count": null,
"outputs": []
}
]
}