{ "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": [ "\"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": "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", "from yolov5 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

\n", "Close the active learning loop by sampling images from your inference conditions with the `roboflow` pip package\n", "

\n", "\n", "Train a YOLOv5s model on the [COCO128](https://www.kaggle.com/ultralytics/coco128) dataset with `--data coco128.yaml`, starting from pretrained `--weights yolov5s.pt`, or from randomly initialized `--weights '' --cfg yolov5s.yaml`.\n", "\n", "- **Pretrained [Models](https://github.com/ultralytics/yolov5/tree/master/models)** are downloaded\n", "automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases)\n", "- **[Datasets](https://github.com/ultralytics/yolov5/tree/master/data)** available for autodownload include: [COCO](https://github.com/ultralytics/yolov5/blob/master/data/coco.yaml), [COCO128](https://github.com/ultralytics/yolov5/blob/master/data/coco128.yaml), [VOC](https://github.com/ultralytics/yolov5/blob/master/data/VOC.yaml), [Argoverse](https://github.com/ultralytics/yolov5/blob/master/data/Argoverse.yaml), [VisDrone](https://github.com/ultralytics/yolov5/blob/master/data/VisDrone.yaml), [GlobalWheat](https://github.com/ultralytics/yolov5/blob/master/data/GlobalWheat2020.yaml), [xView](https://github.com/ultralytics/yolov5/blob/master/data/xView.yaml), [Objects365](https://github.com/ultralytics/yolov5/blob/master/data/Objects365.yaml), [SKU-110K](https://github.com/ultralytics/yolov5/blob/master/data/SKU-110K.yaml).\n", "- **Training Results** are saved to `runs/train/` with incrementing run directories, i.e. `runs/train/exp2`, `runs/train/exp3` etc.\n", "

\n", "\n", "## Train on Custom Data with Roboflow 🌟 NEW\n", "\n", "[Roboflow](https://roboflow.com/?ref=ultralytics) enables you to easily **organize, label, and prepare** a high quality dataset with your own custom data. Roboflow also makes it easy to establish an active learning pipeline, collaborate with your team on dataset improvement, and integrate directly into your model building workflow with the `roboflow` pip package.\n", "\n", "- Custom Training Example: [https://blog.roboflow.com/how-to-train-yolov5-on-a-custom-dataset/](https://blog.roboflow.com/how-to-train-yolov5-on-a-custom-dataset/?ref=ultralytics)\n", "- Custom Training Notebook: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/roboflow-ai/yolov5-custom-training-tutorial/blob/main/yolov5-custom-training.ipynb)\n", "
\n", "\n", "

Label images lightning fast (including with model-assisted labeling)" ] }, { "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": "8724d13d-6711-4a12-d96a-1c655e5c3549" }, "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", "name": "stdout", "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, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, adam=False, sync_bn=False, workers=8, project=runs/train, name=exp, exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, patience=100, freeze=0, save_period=-1, 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 🚀 v6.0-48-g84a8099 torch 1.10.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n", "\n", "\u001b[34m\u001b[1mhyperparameters: \u001b[0mlr0=0.01, lrf=0.1, 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", "\n", " from n params module arguments \n", " 0 -1 1 3520 models.common.Conv [3, 32, 6, 2, 2] \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 2 115712 models.common.C3 [128, 128, 2] \n", " 5 -1 1 295424 models.common.Conv [128, 256, 3, 2] \n", " 6 -1 3 625152 models.common.C3 [256, 256, 3] \n", " 7 -1 1 1180672 models.common.Conv [256, 512, 3, 2] \n", " 8 -1 1 1182720 models.common.C3 [512, 512, 1] \n", " 9 -1 1 656896 models.common.SPPF [512, 512, 5] \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: 270 layers, 7235389 parameters, 7235389 gradients, 16.5 GFLOPs\n", "\n", "Transferred 349/349 items from yolov5s.pt\n", "Scaled weight_decay = 0.0005\n", "\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 57 weight, 60 weight (no decay), 60 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.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00\"Weights

" ] }, { "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 'yolov5n', 'yolov5s', 'yolov5m', 'yolov5l', 'yolov5x':\n", " !python val.py --weights {x}.pt --data coco.yaml --img 640 --task speed # 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": [ "# CI Checks\n", "%%shell\n", "export PYTHONPATH=\"$PWD\" # to run *.py. files in subdirectories\n", "rm -rf runs # remove runs/\n", "for m in yolov5n; do # models\n", " python train.py --img 64 --batch 32 --weights $m.pt --epochs 1 --device 0 # train pretrained\n", " python train.py --img 64 --batch 32 --weights '' --cfg $m.yaml --epochs 1 --device 0 # train scratch\n", " for d in 0 cpu; do # devices\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", " 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", " done\n", " python hubconf.py # hub\n", " python models/yolo.py --cfg $m.yaml # build PyTorch model\n", " python models/tf.py --weights $m.pt # build TensorFlow model\n", " python export.py --img 64 --batch 1 --weights $m.pt --include torchscript onnx # 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, 64, 64, 32, 16], ['yolov5n', 'yolov5s', 'yolov5m', 'yolov5l', 'yolov5x']): # batch, model\n", " !python train.py --batch {b} --weights {m}.pt --data VOC.yaml --epochs 50 --img 512 --hyp hyp.VOC.yaml --project VOC --name {m} --cache" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "VTRwsvA9u7ln" }, "source": [ "# TensorRT \n", "# https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html#installing-pip\n", "!pip install -U nvidia-tensorrt --index-url https://pypi.ngc.nvidia.com # install\n", "!python export.py --weights yolov5s.pt --include engine --imgsz 640 640 --device 0 # export\n", "!python detect.py --weights yolov5s.engine --imgsz 640 640 --device 0 # inference" ], "execution_count": null, "outputs": [] } ] }