{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "YOLOv5 Tutorial",
"provenance": [],
"collapsed_sections": [],
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "GPU",
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"eb95db7cae194218b3fcefb439b6352f": {
"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_769ecde6f2e64bacb596ce972f8d3d2d",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_384a001876054c93b0af45cd1e960bfe",
"IPY_MODEL_dded0aeae74440f7ba2ffa0beb8dd612",
"IPY_MODEL_5296d28be75740b2892ae421bbec3657"
]
}
},
"769ecde6f2e64bacb596ce972f8d3d2d": {
"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
}
},
"384a001876054c93b0af45cd1e960bfe": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_9f09facb2a6c4a7096810d327c8b551c",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": "100%",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_25621cff5d16448cb7260e839fd0f543"
}
},
"dded0aeae74440f7ba2ffa0beb8dd612": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_0ce7164fc0c74bb9a2b5c7037375a727",
"_dom_classes": [],
"description": "",
"_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_c4c4593c10904cb5b8a5724d60c7e181"
}
},
"5296d28be75740b2892ae421bbec3657": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_473371611126476c88d5d42ec7031ed6",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 780M/780M [00:11<00:00, 91.9MB/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_65efdfd0d26c46e79c8c5ff3b77126cc"
}
},
"9f09facb2a6c4a7096810d327c8b551c": {
"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"
}
},
"25621cff5d16448cb7260e839fd0f543": {
"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
}
},
"0ce7164fc0c74bb9a2b5c7037375a727": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "",
"_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"
}
},
"c4c4593c10904cb5b8a5724d60c7e181": {
"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
}
},
"473371611126476c88d5d42ec7031ed6": {
"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"
}
},
"65efdfd0d26c46e79c8c5ff3b77126cc": {
"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** 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": "3809e5a9-dd41-4577-fe62-5531abf7cca2"
},
"source": [
"!git clone https://github.com/ultralytics/yolov5 # clone\n",
"%cd yolov5\n",
"%pip install -qr requirements.txt # install\n",
"\n",
"import torch\n",
"import utils\n",
"display = utils.notebook_init() # checks"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"YOLOv5 🚀 v6.0-48-g84a8099 torch 1.10.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"Setup complete ✅ (2 CPUs, 12.7 GB RAM, 42.2/166.8 GB disk)\n"
]
}
]
},
{
"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",
" img.jpg # image \n",
" vid.mp4 # video\n",
" path/ # directory\n",
" path/*.jpg # glob\n",
" 'https://youtu.be/Zgi9g1ksQHc' # 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": "8f7e6588-215d-4ebd-93af-88b871e770a7"
},
"source": [
"!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images\n",
"display.Image(filename='runs/detect/exp/zidane.jpg', width=600)"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov5s.pt'], source=data/images, 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 🚀 v6.0-48-g84a8099 torch 1.10.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"\n",
"Fusing layers... \n",
"Model Summary: 213 layers, 7225885 parameters, 0 gradients\n",
"image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, Done. (0.007s)\n",
"image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 1 tie, Done. (0.007s)\n",
"Speed: 0.5ms pre-process, 6.9ms inference, 1.3ms NMS per image at shape (1, 3, 640, 640)\n",
"Results saved to \u001b[1mruns/detect/exp\u001b[0m\n"
]
}
]
},
{
"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 val\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": 48,
"referenced_widgets": [
"eb95db7cae194218b3fcefb439b6352f",
"769ecde6f2e64bacb596ce972f8d3d2d",
"384a001876054c93b0af45cd1e960bfe",
"dded0aeae74440f7ba2ffa0beb8dd612",
"5296d28be75740b2892ae421bbec3657",
"9f09facb2a6c4a7096810d327c8b551c",
"25621cff5d16448cb7260e839fd0f543",
"0ce7164fc0c74bb9a2b5c7037375a727",
"c4c4593c10904cb5b8a5724d60c7e181",
"473371611126476c88d5d42ec7031ed6",
"65efdfd0d26c46e79c8c5ff3b77126cc"
]
},
"outputId": "bcf9a448-1f9b-4a41-ad49-12f181faf05a"
},
"source": [
"# Download COCO val\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"
],
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "eb95db7cae194218b3fcefb439b6352f",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
" 0%| | 0.00/780M [00:00, ?B/s]"
]
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "X58w8JLpMnjH",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "74f1dfa9-6b6d-4b36-f67e-bbae243869f9"
},
"source": [
"# Run YOLOv5x on COCO val\n",
"!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[34m\u001b[1mval: \u001b[0mdata=/content/yolov5/data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.65, task=val, device=, 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 🚀 v6.0-48-g84a8099 torch 1.10.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"\n",
"Downloading https://github.com/ultralytics/yolov5/releases/download/v6.0/yolov5x.pt to yolov5x.pt...\n",
"100% 166M/166M [00:03<00:00, 54.1MB/s]\n",
"\n",
"Fusing layers... \n",
"Model Summary: 444 layers, 86705005 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, 2636.64it/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 [01:12<00:00, 2.17it/s]\n",
" all 5000 36335 0.729 0.63 0.683 0.496\n",
"Speed: 0.1ms pre-process, 4.9ms inference, 1.9ms 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=0.46s)\n",
"creating index...\n",
"index created!\n",
"Loading and preparing results...\n",
"DONE (t=5.15s)\n",
"creating index...\n",
"index created!\n",
"Running per image evaluation...\n",
"Evaluate annotation type *bbox*\n",
"DONE (t=90.39s).\n",
"Accumulating evaluation results...\n",
"DONE (t=14.54s).\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.507\n",
" Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.689\n",
" Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.552\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.345\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.559\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.652\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.381\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.630\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.682\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.526\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.732\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.829\n",
"Results saved to \u001b[1mruns/val/exp\u001b[0m\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "rc_KbFk0juX2"
},
"source": [
"## COCO test\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://ultralytics.com/assets/coco2017labels.zip', 'tmp.zip')\n",
"!unzip -q tmp.zip -d ../datasets && rm tmp.zip\n",
"!f=\"test2017.zip\" && curl http://images.cocodataset.org/zips/$f -o $f && unzip -q $f -d ../datasets/coco/images"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "29GJXAP_lPrt"
},
"source": [
"# Run YOLOv5x on COCO test\n",
"!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half --task test"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "ZY2VXXXu74w5"
},
"source": [
"# 3. Train\n",
"\n",
"