{ "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": { "484511f272e64eab8b42e68dac5f7a66": { "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_78cceec059784f2bb36988d3336e4d56", "_model_module": "@jupyter-widgets/controls", "children": [ "IPY_MODEL_ab93d8b65c134605934ff9ec5efb1bb6", "IPY_MODEL_30df865ded4c434191bce772c9a82f3a", "IPY_MODEL_20cdc61eb3404f42a12b37901b0d85fb" ] } }, "78cceec059784f2bb36988d3336e4d56": { "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 } }, "ab93d8b65c134605934ff9ec5efb1bb6": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_view_name": "HTMLView", "style": "IPY_MODEL_2d7239993a9645b09b221405ac682743", "_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_17b5a87f92104ec7ab96bf507637d0d2" } }, "30df865ded4c434191bce772c9a82f3a": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_view_name": "ProgressView", "style": "IPY_MODEL_2358bfb2270247359e94b066b3cc3d1f", "_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_3e984405db654b0b83b88b2db08baffd" } }, "20cdc61eb3404f42a12b37901b0d85fb": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_view_name": "HTMLView", "style": "IPY_MODEL_654d8a19b9f949c6bbdaf8b0875c931e", "_dom_classes": [], "description": "", "_model_name": "HTMLModel", "placeholder": "​", "_view_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "value": " 780M/780M [00:33<00:00, 24.4MB/s]", "_view_count": null, "_view_module_version": "1.5.0", "description_tooltip": null, "_model_module": "@jupyter-widgets/controls", "layout": "IPY_MODEL_896030c5d13b415aaa05032818d81a6e" } }, "2d7239993a9645b09b221405ac682743": { "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" } }, "17b5a87f92104ec7ab96bf507637d0d2": { "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 } }, "2358bfb2270247359e94b066b3cc3d1f": { "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" } }, "3e984405db654b0b83b88b2db08baffd": { "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 } }, "654d8a19b9f949c6bbdaf8b0875c931e": { "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" } }, "896030c5d13b415aaa05032818d81a6e": { "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": [ "\"Open" ] }, { "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": "4d67116a-43e9-4d84-d19e-1edd83f23a04" }, "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": 1, "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": "8b728908-81ab-4861-edb0-4d0c46c439fb" }, "source": [ "%rm -rf runs\n", "!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": 4, "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 🚀 v5.0-367-g01cdb76 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. (0.007s)\n", "image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.007s)\n", "Results saved to \u001b[1mruns/detect/exp\u001b[0m\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": 48, "referenced_widgets": [ "484511f272e64eab8b42e68dac5f7a66", "78cceec059784f2bb36988d3336e4d56", "ab93d8b65c134605934ff9ec5efb1bb6", "30df865ded4c434191bce772c9a82f3a", "20cdc61eb3404f42a12b37901b0d85fb", "2d7239993a9645b09b221405ac682743", "17b5a87f92104ec7ab96bf507637d0d2", "2358bfb2270247359e94b066b3cc3d1f", "3e984405db654b0b83b88b2db08baffd", "654d8a19b9f949c6bbdaf8b0875c931e", "896030c5d13b415aaa05032818d81a6e" ] }, "outputId": "7e6f5c96-c819-43e1-cd03-d3b9878cf8de" }, "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": 5, "outputs": [ { "output_type": "display_data", "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "484511f272e64eab8b42e68dac5f7a66", "version_minor": 0, "version_major": 2 }, "text/plain": [ " 0%| | 0.00/780M [00:00" ] }, { "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", "\"COCO128" ] }, { "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: \"Open \"Open\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) \"Docker\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": [] } ] }