zjc
/
yolov5
Слідкувати 1
В обрані 0
Форк 0
Код Проблеми 0 Запити на злиття 0 Релізи 0 Вікі Активність
Ви не можете вибрати більше 25 тем Теми мають розпочинатися з літери або цифри, можуть містити дефіси (-) і не повинні перевищувати 35 символів.
1393 Коміти
5 Гілки
Дерево: 19d03a955c
Гілки Теги
${ item.name }
Створити гілку ${ searchTerm }
з '19d03a955c'
${ noResults }
yolov5/tutorial.ipynb

1023 lines
46KB
Неформатований Blame Історія 

  1. {

  2.   "nbformat": 4,

  3.   "nbformat_minor": 0,

  4.   "metadata": {

  5.     "colab": {

  6.       "name": "YOLOv5 Tutorial",

  7.       "provenance": [],

  8.       "collapsed_sections": [],

  9.       "include_colab_link": true

  10.     },

  11.     "kernelspec": {

  12.       "name": "python3",

  13.       "display_name": "Python 3"

  14.     },

  15.     "accelerator": "GPU",

  16.     "widgets": {

  17.       "application/vnd.jupyter.widget-state+json": {

  18.         "484511f272e64eab8b42e68dac5f7a66": {

  19.           "model_module": "@jupyter-widgets/controls",

  20.           "model_name": "HBoxModel",

  21.           "model_module_version": "1.5.0",

  22.           "state": {

  23.             "_view_name": "HBoxView",

  24.             "_dom_classes": [],

  25.             "_model_name": "HBoxModel",

  26.             "_view_module": "@jupyter-widgets/controls",

  27.             "_model_module_version": "1.5.0",

  28.             "_view_count": null,

  29.             "_view_module_version": "1.5.0",

  30.             "box_style": "",

  31.             "layout": "IPY_MODEL_78cceec059784f2bb36988d3336e4d56",

  32.             "_model_module": "@jupyter-widgets/controls",

  33.             "children": [

  34.               "IPY_MODEL_ab93d8b65c134605934ff9ec5efb1bb6",

  35.               "IPY_MODEL_30df865ded4c434191bce772c9a82f3a",

  36.               "IPY_MODEL_20cdc61eb3404f42a12b37901b0d85fb"

  37.             ]

  38.           }

  39.         },

  40.         "78cceec059784f2bb36988d3336e4d56": {

  41.           "model_module": "@jupyter-widgets/base",

  42.           "model_name": "LayoutModel",

  43.           "model_module_version": "1.2.0",

  44.           "state": {

  45.             "_view_name": "LayoutView",

  46.             "grid_template_rows": null,

  47.             "right": null,

  48.             "justify_content": null,

  49.             "_view_module": "@jupyter-widgets/base",

  50.             "overflow": null,

  51.             "_model_module_version": "1.2.0",

  52.             "_view_count": null,

  53.             "flex_flow": null,

  54.             "width": null,

  55.             "min_width": null,

  56.             "border": null,

  57.             "align_items": null,

  58.             "bottom": null,

  59.             "_model_module": "@jupyter-widgets/base",

  60.             "top": null,

  61.             "grid_column": null,

  62.             "overflow_y": null,

  63.             "overflow_x": null,

  64.             "grid_auto_flow": null,

  65.             "grid_area": null,

  66.             "grid_template_columns": null,

  67.             "flex": null,

  68.             "_model_name": "LayoutModel",

  69.             "justify_items": null,

  70.             "grid_row": null,

  71.             "max_height": null,

  72.             "align_content": null,

  73.             "visibility": null,

  74.             "align_self": null,

  75.             "height": null,

  76.             "min_height": null,

  77.             "padding": null,

  78.             "grid_auto_rows": null,

  79.             "grid_gap": null,

  80.             "max_width": null,

  81.             "order": null,

  82.             "_view_module_version": "1.2.0",

  83.             "grid_template_areas": null,

  84.             "object_position": null,

  85.             "object_fit": null,

  86.             "grid_auto_columns": null,

  87.             "margin": null,

  88.             "display": null,

  89.             "left": null

  90.           }

  91.         },

  92.         "ab93d8b65c134605934ff9ec5efb1bb6": {

  93.           "model_module": "@jupyter-widgets/controls",

  94.           "model_name": "HTMLModel",

  95.           "model_module_version": "1.5.0",

  96.           "state": {

  97.             "_view_name": "HTMLView",

  98.             "style": "IPY_MODEL_2d7239993a9645b09b221405ac682743",

  99.             "_dom_classes": [],

  100.             "description": "",

  101.             "_model_name": "HTMLModel",

  102.             "placeholder": "​",

  103.             "_view_module": "@jupyter-widgets/controls",

  104.             "_model_module_version": "1.5.0",

  105.             "value": "100%",

  106.             "_view_count": null,

  107.             "_view_module_version": "1.5.0",

  108.             "description_tooltip": null,

  109.             "_model_module": "@jupyter-widgets/controls",

  110.             "layout": "IPY_MODEL_17b5a87f92104ec7ab96bf507637d0d2"

  111.           }

  112.         },

  113.         "30df865ded4c434191bce772c9a82f3a": {

  114.           "model_module": "@jupyter-widgets/controls",

  115.           "model_name": "FloatProgressModel",

  116.           "model_module_version": "1.5.0",

  117.           "state": {

  118.             "_view_name": "ProgressView",

  119.             "style": "IPY_MODEL_2358bfb2270247359e94b066b3cc3d1f",

  120.             "_dom_classes": [],

  121.             "description": "",

  122.             "_model_name": "FloatProgressModel",

  123.             "bar_style": "success",

  124.             "max": 818322941,

  125.             "_view_module": "@jupyter-widgets/controls",

  126.             "_model_module_version": "1.5.0",

  127.             "value": 818322941,

  128.             "_view_count": null,

  129.             "_view_module_version": "1.5.0",

  130.             "orientation": "horizontal",

  131.             "min": 0,

  132.             "description_tooltip": null,

  133.             "_model_module": "@jupyter-widgets/controls",

  134.             "layout": "IPY_MODEL_3e984405db654b0b83b88b2db08baffd"

  135.           }

  136.         },

  137.         "20cdc61eb3404f42a12b37901b0d85fb": {

  138.           "model_module": "@jupyter-widgets/controls",

  139.           "model_name": "HTMLModel",

  140.           "model_module_version": "1.5.0",

  141.           "state": {

  142.             "_view_name": "HTMLView",

  143.             "style": "IPY_MODEL_654d8a19b9f949c6bbdaf8b0875c931e",

  144.             "_dom_classes": [],

  145.             "description": "",

  146.             "_model_name": "HTMLModel",

  147.             "placeholder": "​",

  148.             "_view_module": "@jupyter-widgets/controls",

  149.             "_model_module_version": "1.5.0",

  150.             "value": " 780M/780M [00:33<00:00, 24.4MB/s]",

  151.             "_view_count": null,

  152.             "_view_module_version": "1.5.0",

  153.             "description_tooltip": null,

  154.             "_model_module": "@jupyter-widgets/controls",

  155.             "layout": "IPY_MODEL_896030c5d13b415aaa05032818d81a6e"

  156.           }

  157.         },

  158.         "2d7239993a9645b09b221405ac682743": {

  159.           "model_module": "@jupyter-widgets/controls",

  160.           "model_name": "DescriptionStyleModel",

  161.           "model_module_version": "1.5.0",

  162.           "state": {

  163.             "_view_name": "StyleView",

  164.             "_model_name": "DescriptionStyleModel",

  165.             "description_width": "",

  166.             "_view_module": "@jupyter-widgets/base",

  167.             "_model_module_version": "1.5.0",

  168.             "_view_count": null,

  169.             "_view_module_version": "1.2.0",

  170.             "_model_module": "@jupyter-widgets/controls"

  171.           }

  172.         },

  173.         "17b5a87f92104ec7ab96bf507637d0d2": {

  174.           "model_module": "@jupyter-widgets/base",

  175.           "model_name": "LayoutModel",

  176.           "model_module_version": "1.2.0",

  177.           "state": {

  178.             "_view_name": "LayoutView",

  179.             "grid_template_rows": null,

  180.             "right": null,

  181.             "justify_content": null,

  182.             "_view_module": "@jupyter-widgets/base",

  183.             "overflow": null,

  184.             "_model_module_version": "1.2.0",

  185.             "_view_count": null,

  186.             "flex_flow": null,

  187.             "width": null,

  188.             "min_width": null,

  189.             "border": null,

  190.             "align_items": null,

  191.             "bottom": null,

  192.             "_model_module": "@jupyter-widgets/base",

  193.             "top": null,

  194.             "grid_column": null,

  195.             "overflow_y": null,

  196.             "overflow_x": null,

  197.             "grid_auto_flow": null,

  198.             "grid_area": null,

  199.             "grid_template_columns": null,

  200.             "flex": null,

  201.             "_model_name": "LayoutModel",

  202.             "justify_items": null,

  203.             "grid_row": null,

  204.             "max_height": null,

  205.             "align_content": null,

  206.             "visibility": null,

  207.             "align_self": null,

  208.             "height": null,

  209.             "min_height": null,

  210.             "padding": null,

  211.             "grid_auto_rows": null,

  212.             "grid_gap": null,

  213.             "max_width": null,

  214.             "order": null,

  215.             "_view_module_version": "1.2.0",

  216.             "grid_template_areas": null,

  217.             "object_position": null,

  218.             "object_fit": null,

  219.             "grid_auto_columns": null,

  220.             "margin": null,

  221.             "display": null,

  222.             "left": null

  223.           }

  224.         },

  225.         "2358bfb2270247359e94b066b3cc3d1f": {

  226.           "model_module": "@jupyter-widgets/controls",

  227.           "model_name": "ProgressStyleModel",

  228.           "model_module_version": "1.5.0",

  229.           "state": {

  230.             "_view_name": "StyleView",

  231.             "_model_name": "ProgressStyleModel",

  232.             "description_width": "",

  233.             "_view_module": "@jupyter-widgets/base",

  234.             "_model_module_version": "1.5.0",

  235.             "_view_count": null,

  236.             "_view_module_version": "1.2.0",

  237.             "bar_color": null,

  238.             "_model_module": "@jupyter-widgets/controls"

  239.           }

  240.         },

  241.         "3e984405db654b0b83b88b2db08baffd": {

  242.           "model_module": "@jupyter-widgets/base",

  243.           "model_name": "LayoutModel",

  244.           "model_module_version": "1.2.0",

  245.           "state": {

  246.             "_view_name": "LayoutView",

  247.             "grid_template_rows": null,

  248.             "right": null,

  249.             "justify_content": null,

  250.             "_view_module": "@jupyter-widgets/base",

  251.             "overflow": null,

  252.             "_model_module_version": "1.2.0",

  253.             "_view_count": null,

  254.             "flex_flow": null,

  255.             "width": null,

  256.             "min_width": null,

  257.             "border": null,

  258.             "align_items": null,

  259.             "bottom": null,

  260.             "_model_module": "@jupyter-widgets/base",

  261.             "top": null,

  262.             "grid_column": null,

  263.             "overflow_y": null,

  264.             "overflow_x": null,

  265.             "grid_auto_flow": null,

  266.             "grid_area": null,

  267.             "grid_template_columns": null,

  268.             "flex": null,

  269.             "_model_name": "LayoutModel",

  270.             "justify_items": null,

  271.             "grid_row": null,

  272.             "max_height": null,

  273.             "align_content": null,

  274.             "visibility": null,

  275.             "align_self": null,

  276.             "height": null,

  277.             "min_height": null,

  278.             "padding": null,

  279.             "grid_auto_rows": null,

  280.             "grid_gap": null,

  281.             "max_width": null,

  282.             "order": null,

  283.             "_view_module_version": "1.2.0",

  284.             "grid_template_areas": null,

  285.             "object_position": null,

  286.             "object_fit": null,

  287.             "grid_auto_columns": null,

  288.             "margin": null,

  289.             "display": null,

  290.             "left": null

  291.           }

  292.         },

  293.         "654d8a19b9f949c6bbdaf8b0875c931e": {

  294.           "model_module": "@jupyter-widgets/controls",

  295.           "model_name": "DescriptionStyleModel",

  296.           "model_module_version": "1.5.0",

  297.           "state": {

  298.             "_view_name": "StyleView",

  299.             "_model_name": "DescriptionStyleModel",

  300.             "description_width": "",

  301.             "_view_module": "@jupyter-widgets/base",

  302.             "_model_module_version": "1.5.0",

  303.             "_view_count": null,

  304.             "_view_module_version": "1.2.0",

  305.             "_model_module": "@jupyter-widgets/controls"

  306.           }

  307.         },

  308.         "896030c5d13b415aaa05032818d81a6e": {

  309.           "model_module": "@jupyter-widgets/base",

  310.           "model_name": "LayoutModel",

  311.           "model_module_version": "1.2.0",

  312.           "state": {

  313.             "_view_name": "LayoutView",

  314.             "grid_template_rows": null,

  315.             "right": null,

  316.             "justify_content": null,

  317.             "_view_module": "@jupyter-widgets/base",

  318.             "overflow": null,

  319.             "_model_module_version": "1.2.0",

  320.             "_view_count": null,

  321.             "flex_flow": null,

  322.             "width": null,

  323.             "min_width": null,

  324.             "border": null,

  325.             "align_items": null,

  326.             "bottom": null,

  327.             "_model_module": "@jupyter-widgets/base",

  328.             "top": null,

  329.             "grid_column": null,

  330.             "overflow_y": null,

  331.             "overflow_x": null,

  332.             "grid_auto_flow": null,

  333.             "grid_area": null,

  334.             "grid_template_columns": null,

  335.             "flex": null,

  336.             "_model_name": "LayoutModel",

  337.             "justify_items": null,

  338.             "grid_row": null,

  339.             "max_height": null,

  340.             "align_content": null,

  341.             "visibility": null,

  342.             "align_self": null,

  343.             "height": null,

  344.             "min_height": null,

  345.             "padding": null,

  346.             "grid_auto_rows": null,

  347.             "grid_gap": null,

  348.             "max_width": null,

  349.             "order": null,

  350.             "_view_module_version": "1.2.0",

  351.             "grid_template_areas": null,

  352.             "object_position": null,

  353.             "object_fit": null,

  354.             "grid_auto_columns": null,

  355.             "margin": null,

  356.             "display": null,

  357.             "left": null

  358.           }

  359.         }

  360.       }

  361.     }

  362.   },

  363.   "cells": [

  364.     {

  365.       "cell_type": "markdown",

  366.       "metadata": {

  367.         "id": "view-in-github",

  368.         "colab_type": "text"

  369.       },

  370.       "source": [

  371.         "<a href=\"https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"

  372.       ]

  373.     },

  374.     {

  375.       "cell_type": "markdown",

  376.       "metadata": {

  377.         "id": "t6MPjfT5NrKQ"

  378.       },

  379.       "source": [

  380.         "<a align=\"left\" href=\"https://ultralytics.com/yolov5\" target=\"_blank\">\n",

  381.         "<img src=\"https://user-images.githubusercontent.com/26833433/125273437-35b3fc00-e30d-11eb-9079-46f313325424.png\"></a>\n",

  382.         "\n",

  383.         "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",

  384.         "For more information please visit https://github.com/ultralytics/yolov5 and https://ultralytics.com. Thank you!"

  385.       ]

  386.     },

  387.     {

  388.       "cell_type": "markdown",

  389.       "metadata": {

  390.         "id": "7mGmQbAO5pQb"

  391.       },

  392.       "source": [

  393.         "# Setup\n",

  394.         "\n",

  395.         "Clone repo, install dependencies and check PyTorch and GPU."

  396.       ]

  397.     },

  398.     {

  399.       "cell_type": "code",

  400.       "metadata": {

  401.         "id": "wbvMlHd_QwMG",

  402.         "colab": {

  403.           "base_uri": "https://localhost:8080/"

  404.         },

  405.         "outputId": "4d67116a-43e9-4d84-d19e-1edd83f23a04"

  406.       },

  407.       "source": [

  408.         "!git clone https://github.com/ultralytics/yolov5  # clone repo\n",

  409.         "%cd yolov5\n",

  410.         "%pip install -qr requirements.txt  # install dependencies\n",

  411.         "\n",

  412.         "import torch\n",

  413.         "from IPython.display import Image, clear_output  # to display images\n",

  414.         "\n",

  415.         "clear_output()\n",

  416.         "print(f\"Setup complete. Using torch {torch.__version__} ({torch.cuda.get_device_properties(0).name if torch.cuda.is_available() else 'CPU'})\")"

  417.       ],

  418.       "execution_count": 1,

  419.       "outputs": [

  420.         {

  421.           "output_type": "stream",

  422.           "text": [

  423.             "Setup complete. Using torch 1.9.0+cu102 (Tesla V100-SXM2-16GB)\n"

  424.           ],

  425.           "name": "stdout"

  426.         }

  427.       ]

  428.     },

  429.     {

  430.       "cell_type": "markdown",

  431.       "metadata": {

  432.         "id": "4JnkELT0cIJg"

  433.       },

  434.       "source": [

  435.         "# 1. Inference\n",

  436.         "\n",

  437.         "`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",

  438.         "\n",

  439.         "```shell\n",

  440.         "python detect.py --source 0  # webcam\n",

  441.         "                          file.jpg  # image \n",

  442.         "                          file.mp4  # video\n",

  443.         "                          path/  # directory\n",

  444.         "                          path/*.jpg  # glob\n",

  445.         "                          'https://youtu.be/NUsoVlDFqZg'  # YouTube\n",

  446.         "                          'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream\n",

  447.         "```"

  448.       ]

  449.     },

  450.     {

  451.       "cell_type": "code",

  452.       "metadata": {

  453.         "id": "zR9ZbuQCH7FX",

  454.         "colab": {

  455.           "base_uri": "https://localhost:8080/"

  456.         },

  457.         "outputId": "8b728908-81ab-4861-edb0-4d0c46c439fb"

  458.       },

  459.       "source": [

  460.         "%rm -rf runs\n",

  461.         "!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images/\n",

  462.         "#Image(filename='runs/detect/exp/zidane.jpg', width=600)"

  463.       ],

  464.       "execution_count": 4,

  465.       "outputs": [

  466.         {

  467.           "output_type": "stream",

  468.           "text": [

  469.             "\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",

  470.             "YOLOv5 🚀 v5.0-367-g01cdb76 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",

  471.             "\n",

  472.             "Fusing layers... \n",

  473.             "Model Summary: 224 layers, 7266973 parameters, 0 gradients\n",

  474.             "image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, 1 fire hydrant, Done. (0.007s)\n",

  475.             "image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.007s)\n",

  476.             "Results saved to \u001b[1mruns/detect/exp\u001b[0m\n",

  477.             "Done. (0.091s)\n"

  478.           ],

  479.           "name": "stdout"

  480.         }

  481.       ]

  482.     },

  483.     {

  484.       "cell_type": "markdown",

  485.       "metadata": {

  486.         "id": "hkAzDWJ7cWTr"

  487.       },

  488.       "source": [

  489.         "&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\n",

  490.         "<img align=\"left\" src=\"https://user-images.githubusercontent.com/26833433/127574988-6a558aa1-d268-44b9-bf6b-62d4c605cc72.jpg\" width=\"600\">"

  491.       ]

  492.     },

  493.     {

  494.       "cell_type": "markdown",

  495.       "metadata": {

  496.         "id": "0eq1SMWl6Sfn"

  497.       },

  498.       "source": [

  499.         "# 2. Validate\n",

  500.         "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."

  501.       ]

  502.     },

  503.     {

  504.       "cell_type": "markdown",

  505.       "metadata": {

  506.         "id": "eyTZYGgRjnMc"

  507.       },

  508.       "source": [

  509.         "## COCO val2017\n",

  510.         "Download [COCO val 2017](https://github.com/ultralytics/yolov5/blob/74b34872fdf41941cddcf243951cdb090fbac17b/data/coco.yaml#L14) dataset (1GB - 5000 images), and test model accuracy."

  511.       ]

  512.     },

  513.     {

  514.       "cell_type": "code",

  515.       "metadata": {

  516.         "id": "WQPtK1QYVaD_",

  517.         "colab": {

  518.           "base_uri": "https://localhost:8080/",

  519.           "height": 48,

  520.           "referenced_widgets": [

  521.             "484511f272e64eab8b42e68dac5f7a66",

  522.             "78cceec059784f2bb36988d3336e4d56",

  523.             "ab93d8b65c134605934ff9ec5efb1bb6",

  524.             "30df865ded4c434191bce772c9a82f3a",

  525.             "20cdc61eb3404f42a12b37901b0d85fb",

  526.             "2d7239993a9645b09b221405ac682743",

  527.             "17b5a87f92104ec7ab96bf507637d0d2",

  528.             "2358bfb2270247359e94b066b3cc3d1f",

  529.             "3e984405db654b0b83b88b2db08baffd",

  530.             "654d8a19b9f949c6bbdaf8b0875c931e",

  531.             "896030c5d13b415aaa05032818d81a6e"

  532.           ]

  533.         },

  534.         "outputId": "7e6f5c96-c819-43e1-cd03-d3b9878cf8de"

  535.       },

  536.       "source": [

  537.         "# Download COCO val2017\n",

  538.         "torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco2017val.zip', 'tmp.zip')\n",

  539.         "!unzip -q tmp.zip -d ../datasets && rm tmp.zip"

  540.       ],

  541.       "execution_count": 5,

  542.       "outputs": [

  543.         {

  544.           "output_type": "display_data",

  545.           "data": {

  546.             "application/vnd.jupyter.widget-view+json": {

  547.               "model_id": "484511f272e64eab8b42e68dac5f7a66",

  548.               "version_minor": 0,

  549.               "version_major": 2

  550.             },

  551.             "text/plain": [

  552.               "  0%|          | 0.00/780M [00:00<?, ?B/s]"

  553.             ]

  554.           },

  555.           "metadata": {

  556.             "tags": []

  557.           }

  558.         }

  559.       ]

  560.     },

  561.     {

  562.       "cell_type": "code",

  563.       "metadata": {

  564.         "id": "X58w8JLpMnjH",

  565.         "colab": {

  566.           "base_uri": "https://localhost:8080/"

  567.         },

  568.         "outputId": "3dd0e2fc-aecf-4108-91b1-6392da1863cb"

  569.       },

  570.       "source": [

  571.         "# Run YOLOv5x on COCO val2017\n",

  572.         "!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half"

  573.       ],

  574.       "execution_count": 6,

  575.       "outputs": [

  576.         {

  577.           "output_type": "stream",

  578.           "text": [

  579.             "\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",

  580.             "YOLOv5 🚀 v5.0-367-g01cdb76 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",

  581.             "\n",

  582.             "Downloading https://github.com/ultralytics/yolov5/releases/download/v5.0/yolov5x.pt to yolov5x.pt...\n",

  583.             "100% 168M/168M [00:08<00:00, 20.6MB/s]\n",

  584.             "\n",

  585.             "Fusing layers... \n",

  586.             "Model Summary: 476 layers, 87730285 parameters, 0 gradients\n",

  587.             "\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, 2749.96it/s]\n",

  588.             "\u001b[34m\u001b[1mval: \u001b[0mNew cache created: ../datasets/coco/val2017.cache\n",

  589.             "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 157/157 [01:08<00:00,  2.28it/s]\n",

  590.             "                 all       5000      36335      0.746      0.626       0.68       0.49\n",

  591.             "Speed: 0.1ms pre-process, 5.1ms inference, 1.6ms NMS per image at shape (32, 3, 640, 640)\n",

  592.             "\n",

  593.             "Evaluating pycocotools mAP... saving runs/val/exp/yolov5x_predictions.json...\n",

  594.             "loading annotations into memory...\n",

  595.             "Done (t=0.46s)\n",

  596.             "creating index...\n",

  597.             "index created!\n",

  598.             "Loading and preparing results...\n",

  599.             "DONE (t=4.94s)\n",

  600.             "creating index...\n",

  601.             "index created!\n",

  602.             "Running per image evaluation...\n",

  603.             "Evaluate annotation type *bbox*\n",

  604.             "DONE (t=83.60s).\n",

  605.             "Accumulating evaluation results...\n",

  606.             "DONE (t=13.22s).\n",

  607.             " Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.504\n",

  608.             " Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.688\n",

  609.             " Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.546\n",

  610.             " Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.351\n",

  611.             " Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.551\n",

  612.             " Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.644\n",

  613.             " Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.382\n",

  614.             " Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.629\n",

  615.             " Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.681\n",

  616.             " Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.524\n",

  617.             " Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.735\n",

  618.             " Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.827\n",

  619.             "Results saved to \u001b[1mruns/val/exp\u001b[0m\n"

  620.           ],

  621.           "name": "stdout"

  622.         }

  623.       ]

  624.     },

  625.     {

  626.       "cell_type": "markdown",

  627.       "metadata": {

  628.         "id": "rc_KbFk0juX2"

  629.       },

  630.       "source": [

  631.         "## COCO test-dev2017\n",

  632.         "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."

  633.       ]

  634.     },

  635.     {

  636.       "cell_type": "code",

  637.       "metadata": {

  638.         "id": "V0AJnSeCIHyJ"

  639.       },

  640.       "source": [

  641.         "# Download COCO test-dev2017\n",

  642.         "torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco2017labels.zip', 'tmp.zip')\n",

  643.         "!unzip -q tmp.zip -d ../ && rm tmp.zip # unzip labels\n",

  644.         "!f=\"test2017.zip\" && curl http://images.cocodataset.org/zips/$f -o $f && unzip -q $f && rm $f  # 7GB,  41k images\n",

  645.         "%mv ./test2017 ../coco/images  # move to /coco"

  646.       ],

  647.       "execution_count": null,

  648.       "outputs": []

  649.     },

  650.     {

  651.       "cell_type": "code",

  652.       "metadata": {

  653.         "id": "29GJXAP_lPrt"

  654.       },

  655.       "source": [

  656.         "# Run YOLOv5s on COCO test-dev2017 using --task test\n",

  657.         "!python val.py --weights yolov5s.pt --data coco.yaml --task test"

  658.       ],

  659.       "execution_count": null,

  660.       "outputs": []

  661.     },

  662.     {

  663.       "cell_type": "markdown",

  664.       "metadata": {

  665.         "id": "VUOiNLtMP5aG"

  666.       },

  667.       "source": [

  668.         "# 3. Train\n",

  669.         "\n",

  670.         "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)."

  671.       ]

  672.     },

  673.     {

  674.       "cell_type": "code",

  675.       "metadata": {

  676.         "id": "Knxi2ncxWffW"

  677.       },

  678.       "source": [

  679.         "# Download COCO128\n",

  680.         "torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip', 'tmp.zip')\n",

  681.         "!unzip -q tmp.zip -d ../datasets && rm tmp.zip"

  682.       ],

  683.       "execution_count": null,

  684.       "outputs": []

  685.     },

  686.     {

  687.       "cell_type": "markdown",

  688.       "metadata": {

  689.         "id": "_pOkGLv1dMqh"

  690.       },

  691.       "source": [

  692.         "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",

  693.         "\n",

  694.         "All training results are saved to `runs/train/` with incrementing run directories, i.e. `runs/train/exp2`, `runs/train/exp3` etc.\n"

  695.       ]

  696.     },

  697.     {

  698.       "cell_type": "code",

  699.       "metadata": {

  700.         "id": "bOy5KI2ncnWd"

  701.       },

  702.       "source": [

  703.         "# Tensorboard  (optional)\n",

  704.         "%load_ext tensorboard\n",

  705.         "%tensorboard --logdir runs/train"

  706.       ],

  707.       "execution_count": null,

  708.       "outputs": []

  709.     },

  710.     {

  711.       "cell_type": "code",

  712.       "metadata": {

  713.         "id": "2fLAV42oNb7M"

  714.       },

  715.       "source": [

  716.         "# Weights & Biases  (optional)\n",

  717.         "%pip install -q wandb\n",

  718.         "import wandb\n",

  719.         "wandb.login()"

  720.       ],

  721.       "execution_count": null,

  722.       "outputs": []

  723.     },

  724.     {

  725.       "cell_type": "code",

  726.       "metadata": {

  727.         "id": "1NcFxRcFdJ_O",

  728.         "colab": {

  729.           "base_uri": "https://localhost:8080/"

  730.         },

  731.         "outputId": "00ea4b14-a75c-44a2-a913-03b431b69de5"

  732.       },

  733.       "source": [

  734.         "# Train YOLOv5s on COCO128 for 3 epochs\n",

  735.         "!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache"

  736.       ],

  737.       "execution_count": 8,

  738.       "outputs": [

  739.         {

  740.           "output_type": "stream",

  741.           "text": [

  742.             "\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=ram, 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, freeze=0\n",

  743.             "\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov5 ✅\n",

  744.             "YOLOv5 🚀 v5.0-367-g01cdb76 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",

  745.             "\n",

  746.             "\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",

  747.             "\u001b[34m\u001b[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)\n",

  748.             "\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/\n",

  749.             "2021-08-15 14:40:43.449642: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudart.so.11.0\n",

  750.             "\n",

  751.             "                 from  n    params  module                                  arguments                     \n",

  752.             "  0                -1  1      3520  models.common.Focus                     [3, 32, 3]                    \n",

  753.             "  1                -1  1     18560  models.common.Conv                      [32, 64, 3, 2]                \n",

  754.             "  2                -1  1     18816  models.common.C3                        [64, 64, 1]                   \n",

  755.             "  3                -1  1     73984  models.common.Conv                      [64, 128, 3, 2]               \n",

  756.             "  4                -1  3    156928  models.common.C3                        [128, 128, 3]                 \n",

  757.             "  5                -1  1    295424  models.common.Conv                      [128, 256, 3, 2]              \n",

  758.             "  6                -1  3    625152  models.common.C3                        [256, 256, 3]                 \n",

  759.             "  7                -1  1   1180672  models.common.Conv                      [256, 512, 3, 2]              \n",

  760.             "  8                -1  1    656896  models.common.SPP                       [512, 512, [5, 9, 13]]        \n",

  761.             "  9                -1  1   1182720  models.common.C3                        [512, 512, 1, False]          \n",

  762.             " 10                -1  1    131584  models.common.Conv                      [512, 256, 1, 1]              \n",

  763.             " 11                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          \n",

  764.             " 12           [-1, 6]  1         0  models.common.Concat                    [1]                           \n",

  765.             " 13                -1  1    361984  models.common.C3                        [512, 256, 1, False]          \n",

  766.             " 14                -1  1     33024  models.common.Conv                      [256, 128, 1, 1]              \n",

  767.             " 15                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          \n",

  768.             " 16           [-1, 4]  1         0  models.common.Concat                    [1]                           \n",

  769.             " 17                -1  1     90880  models.common.C3                        [256, 128, 1, False]          \n",

  770.             " 18                -1  1    147712  models.common.Conv                      [128, 128, 3, 2]              \n",

  771.             " 19          [-1, 14]  1         0  models.common.Concat                    [1]                           \n",

  772.             " 20                -1  1    296448  models.common.C3                        [256, 256, 1, False]          \n",

  773.             " 21                -1  1    590336  models.common.Conv                      [256, 256, 3, 2]              \n",

  774.             " 22          [-1, 10]  1         0  models.common.Concat                    [1]                           \n",

  775.             " 23                -1  1   1182720  models.common.C3                        [512, 512, 1, False]          \n",

  776.             " 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",

  777.             "Model Summary: 283 layers, 7276605 parameters, 7276605 gradients, 17.1 GFLOPs\n",

  778.             "\n",

  779.             "Transferred 362/362 items from yolov5s.pt\n",

  780.             "Scaled weight_decay = 0.0005\n",

  781.             "\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 59 weight, 62 weight (no decay), 62 bias\n",

  782.             "\u001b[34m\u001b[1malbumentations: \u001b[0mversion 1.0.3 required by YOLOv5, but version 0.1.12 is currently installed\n",

  783.             "\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, 2440.28it/s]\n",

  784.             "\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: ../datasets/coco128/labels/train2017.cache\n",

  785.             "\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 302.61it/s]\n",

  786.             "\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<?, ?it/s]\n",

  787.             "\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 142.55it/s]\n",

  788.             "[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)\n",

  789.             "[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)\n",

  790.             "Plotting labels... \n",

  791.             "\n",

  792.             "\u001b[34m\u001b[1mautoanchor: \u001b[0mAnalyzing anchors... anchors/target = 4.27, Best Possible Recall (BPR) = 0.9935\n",

  793.             "Image sizes 640 train, 640 val\n",

  794.             "Using 2 dataloader workers\n",

  795.             "Logging results to runs/train/exp\n",

  796.             "Starting training for 3 epochs...\n",

  797.             "\n",

  798.             "     Epoch   gpu_mem       box       obj       cls    labels  img_size\n",

  799.             "       0/2     3.64G   0.04492    0.0674   0.02213       298       640: 100% 8/8 [00:03<00:00,  2.05it/s]\n",

  800.             "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00,  4.70it/s]\n",

  801.             "                 all        128        929      0.686      0.565      0.642      0.421\n",

  802.             "\n",

  803.             "     Epoch   gpu_mem       box       obj       cls    labels  img_size\n",

  804.             "       1/2     5.04G   0.04403    0.0611   0.01986       232       640: 100% 8/8 [00:01<00:00,  5.59it/s]\n",

  805.             "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00,  4.46it/s]\n",

  806.             "                 all        128        929      0.694      0.563      0.654      0.425\n",

  807.             "\n",

  808.             "     Epoch   gpu_mem       box       obj       cls    labels  img_size\n",

  809.             "       2/2     5.04G   0.04616   0.07056   0.02071       214       640: 100% 8/8 [00:01<00:00,  5.94it/s]\n",

  810.             "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00,  1.52it/s]\n",

  811.             "                 all        128        929      0.711      0.562       0.66      0.431\n",

  812.             "\n",

  813.             "3 epochs completed in 0.005 hours.\n",

  814.             "Optimizer stripped from runs/train/exp/weights/last.pt, 14.8MB\n",

  815.             "Optimizer stripped from runs/train/exp/weights/best.pt, 14.8MB\n",

  816.             "Results saved to \u001b[1mruns/train/exp\u001b[0m\n"

  817.           ],

  818.           "name": "stdout"

  819.         }

  820.       ]

  821.     },

  822.     {

  823.       "cell_type": "markdown",

  824.       "metadata": {

  825.         "id": "15glLzbQx5u0"

  826.       },

  827.       "source": [

  828.         "# 4. Visualize"

  829.       ]

  830.     },

  831.     {

  832.       "cell_type": "markdown",

  833.       "metadata": {

  834.         "id": "DLI1JmHU7B0l"

  835.       },

  836.       "source": [

  837.         "## Weights & Biases Logging 🌟 NEW\n",

  838.         "\n",

  839.         "[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",

  840.         "\n",

  841.         "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",

  842.         "\n",

  843.         "<img align=\"left\" src=\"https://user-images.githubusercontent.com/26833433/125274843-a27bc600-e30e-11eb-9a44-62af0b7a50a2.png\" width=\"800\">"

  844.       ]

  845.     },

  846.     {

  847.       "cell_type": "markdown",

  848.       "metadata": {

  849.         "id": "-WPvRbS5Swl6"

  850.       },

  851.       "source": [

  852.         "## Local Logging\n",

  853.         "\n",

  854.         "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",

  855.         "\n",

  856.         "> <img src=\"https://user-images.githubusercontent.com/26833433/124931219-48bf8700-e002-11eb-84f0-e05d95b118dd.jpg\" width=\"700\">  \n",

  857.         "`train_batch0.jpg` shows train batch 0 mosaics and labels\n",

  858.         "\n",

  859.         "> <img src=\"https://user-images.githubusercontent.com/26833433/124931217-4826f080-e002-11eb-87b9-ae0925a8c94b.jpg\" width=\"700\">  \n",

  860.         "`test_batch0_labels.jpg` shows val batch 0 labels\n",

  861.         "\n",

  862.         "> <img src=\"https://user-images.githubusercontent.com/26833433/124931209-46f5c380-e002-11eb-9bd5-7a3de2be9851.jpg\" width=\"700\">  \n",

  863.         "`test_batch0_pred.jpg` shows val batch 0 _predictions_\n",

  864.         "\n",

  865.         "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",

  866.         "\n",

  867.         "```python\n",

  868.         "from utils.plots import plot_results \n",

  869.         "plot_results('path/to/results.csv')  # plot 'results.csv' as 'results.png'\n",

  870.         "```\n",

  871.         "\n",

  872.         "<img align=\"left\" width=\"800\" alt=\"COCO128 Training Results\" src=\"https://user-images.githubusercontent.com/26833433/126906780-8c5e2990-6116-4de6-b78a-367244a33ccf.png\">"

  873.       ]

  874.     },

  875.     {

  876.       "cell_type": "markdown",

  877.       "metadata": {

  878.         "id": "Zelyeqbyt3GD"

  879.       },

  880.       "source": [

  881.         "# Environments\n",

  882.         "\n",

  883.         "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",

  884.         "\n",

  885.         "- **Google Colab and Kaggle** notebooks with free GPU: <a href=\"https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"></a> <a href=\"https://www.kaggle.com/ultralytics/yolov5\"><img src=\"https://kaggle.com/static/images/open-in-kaggle.svg\" alt=\"Open In Kaggle\"></a>\n",

  886.         "- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart)\n",

  887.         "- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart)\n",

  888.         "- **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) <a href=\"https://hub.docker.com/r/ultralytics/yolov5\"><img src=\"https://img.shields.io/docker/pulls/ultralytics/yolov5?logo=docker\" alt=\"Docker Pulls\"></a>\n"

  889.       ]

  890.     },

  891.     {

  892.       "cell_type": "markdown",

  893.       "metadata": {

  894.         "id": "6Qu7Iesl0p54"

  895.       },

  896.       "source": [

  897.         "# Status\n",

  898.         "\n",

  899.         "![CI CPU testing](https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg)\n",

  900.         "\n",

  901.         "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"

  902.       ]

  903.     },

  904.     {

  905.       "cell_type": "markdown",

  906.       "metadata": {

  907.         "id": "IEijrePND_2I"

  908.       },

  909.       "source": [

  910.         "# Appendix\n",

  911.         "\n",

  912.         "Optional extras below. Unit tests validate repo functionality and should be run on any PRs submitted.\n"

  913.       ]

  914.     },

  915.     {

  916.       "cell_type": "code",

  917.       "metadata": {

  918.         "id": "mcKoSIK2WSzj"

  919.       },

  920.       "source": [

  921.         "# Reproduce\n",

  922.         "for x in 'yolov5s', 'yolov5m', 'yolov5l', 'yolov5x':\n",

  923.         "  !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.25 --iou 0.45  # speed\n",

  924.         "  !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.001 --iou 0.65  # mAP"

  925.       ],

  926.       "execution_count": null,

  927.       "outputs": []

  928.     },

  929.     {

  930.       "cell_type": "code",

  931.       "metadata": {

  932.         "id": "GMusP4OAxFu6"

  933.       },

  934.       "source": [

  935.         "# PyTorch Hub\n",

  936.         "import torch\n",

  937.         "\n",

  938.         "# Model\n",

  939.         "model = torch.hub.load('ultralytics/yolov5', 'yolov5s')\n",

  940.         "\n",

  941.         "# Images\n",

  942.         "dir = 'https://ultralytics.com/images/'\n",

  943.         "imgs = [dir + f for f in ('zidane.jpg', 'bus.jpg')]  # batch of images\n",

  944.         "\n",

  945.         "# Inference\n",

  946.         "results = model(imgs)\n",

  947.         "results.print()  # or .show(), .save()"

  948.       ],

  949.       "execution_count": null,

  950.       "outputs": []

  951.     },

  952.     {

  953.       "cell_type": "code",

  954.       "metadata": {

  955.         "id": "FGH0ZjkGjejy"

  956.       },

  957.       "source": [

  958.         "# Unit tests\n",

  959.         "%%shell\n",

  960.         "export PYTHONPATH=\"$PWD\"  # to run *.py. files in subdirectories\n",

  961.         "\n",

  962.         "rm -rf runs  # remove runs/\n",

  963.         "for m in yolov5s; do  # models\n",

  964.         "  python train.py --weights $m.pt --epochs 3 --img 320 --device 0  # train pretrained\n",

  965.         "  python train.py --weights '' --cfg $m.yaml --epochs 3 --img 320 --device 0  # train scratch\n",

  966.         "  for d in 0 cpu; do  # devices\n",

  967.         "    python detect.py --weights $m.pt --device $d  # detect official\n",

  968.         "    python detect.py --weights runs/train/exp/weights/best.pt --device $d  # detect custom\n",

  969.         "    python val.py --weights $m.pt --device $d # val official\n",

  970.         "    python val.py --weights runs/train/exp/weights/best.pt --device $d # val custom\n",

  971.         "  done\n",

  972.         "  python hubconf.py  # hub\n",

  973.         "  python models/yolo.py --cfg $m.yaml  # inspect\n",

  974.         "  python export.py --weights $m.pt --img 640 --batch 1  # export\n",

  975.         "done"

  976.       ],

  977.       "execution_count": null,

  978.       "outputs": []

  979.     },

  980.     {

  981.       "cell_type": "code",

  982.       "metadata": {

  983.         "id": "gogI-kwi3Tye"

  984.       },

  985.       "source": [

  986.         "# Profile\n",

  987.         "from utils.torch_utils import profile\n",

  988.         "\n",

  989.         "m1 = lambda x: x * torch.sigmoid(x)\n",

  990.         "m2 = torch.nn.SiLU()\n",

  991.         "results = profile(input=torch.randn(16, 3, 640, 640), ops=[m1, m2], n=100)"

  992.       ],

  993.       "execution_count": null,

  994.       "outputs": []

  995.     },

  996.     {

  997.       "cell_type": "code",

  998.       "metadata": {

  999.         "id": "RVRSOhEvUdb5"

  1000.       },

  1001.       "source": [

  1002.         "# Evolve\n",

  1003.         "!python train.py --img 640 --batch 64 --epochs 100 --data coco128.yaml --weights yolov5s.pt --cache --noautoanchor --evolve\n",

  1004.         "!d=runs/train/evolve && cp evolve.* $d && zip -r evolve.zip $d && gsutil mv evolve.zip gs://bucket  # upload results (optional)"

  1005.       ],

  1006.       "execution_count": null,

  1007.       "outputs": []

  1008.     },

  1009.     {

  1010.       "cell_type": "code",

  1011.       "metadata": {

  1012.         "id": "BSgFCAcMbk1R"

  1013.       },

  1014.       "source": [

  1015.         "# VOC\n",

  1016.         "for b, m in zip([64, 48, 32, 16], ['yolov5s', 'yolov5m', 'yolov5l', 'yolov5x']):  # zip(batch_size, model)\n",

  1017.         "  !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}"

  1018.       ],

  1019.       "execution_count": null,

  1020.       "outputs": []

  1021.     }

  1022.   ]

  1023. }