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.
1358 Коміти
5 Гілки
Дерево: 9468657502
Гілки Теги
${ item.name }
Створити гілку ${ searchTerm }
з '9468657502'
${ noResults }
yolov5/tutorial.ipynb

1211 lines
52KB
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.       "toc_visible": true,

  10.       "include_colab_link": true

  11.     },

  12.     "kernelspec": {

  13.       "name": "python3",

  14.       "display_name": "Python 3"

  15.     },

  16.     "accelerator": "GPU",

  17.     "widgets": {

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

  19.         "2e915d9016c846e095e382b6a02ee773": {

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

  21.           "model_name": "HBoxModel",

  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_cb7fc3a5c6cc4fde8d2c83e594a7c86e",

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

  33.             "children": [

  34.               "IPY_MODEL_ac3edef4e3434f4587e6cbf8aa048770",

  35.               "IPY_MODEL_853ac234cc2a4236946fc516871e10eb"

  36.             ]

  37.           }

  38.         },

  39.         "cb7fc3a5c6cc4fde8d2c83e594a7c86e": {

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

  41.           "model_name": "LayoutModel",

  42.           "state": {

  43.             "_view_name": "LayoutView",

  44.             "grid_template_rows": null,

  45.             "right": null,

  46.             "justify_content": null,

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

  48.             "overflow": null,

  49.             "_model_module_version": "1.2.0",

  50.             "_view_count": null,

  51.             "flex_flow": null,

  52.             "width": null,

  53.             "min_width": null,

  54.             "border": null,

  55.             "align_items": null,

  56.             "bottom": null,

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

  58.             "top": null,

  59.             "grid_column": null,

  60.             "overflow_y": null,

  61.             "overflow_x": null,

  62.             "grid_auto_flow": null,

  63.             "grid_area": null,

  64.             "grid_template_columns": null,

  65.             "flex": null,

  66.             "_model_name": "LayoutModel",

  67.             "justify_items": null,

  68.             "grid_row": null,

  69.             "max_height": null,

  70.             "align_content": null,

  71.             "visibility": null,

  72.             "align_self": null,

  73.             "height": null,

  74.             "min_height": null,

  75.             "padding": null,

  76.             "grid_auto_rows": null,

  77.             "grid_gap": null,

  78.             "max_width": null,

  79.             "order": null,

  80.             "_view_module_version": "1.2.0",

  81.             "grid_template_areas": null,

  82.             "object_position": null,

  83.             "object_fit": null,

  84.             "grid_auto_columns": null,

  85.             "margin": null,

  86.             "display": null,

  87.             "left": null

  88.           }

  89.         },

  90.         "ac3edef4e3434f4587e6cbf8aa048770": {

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

  92.           "model_name": "FloatProgressModel",

  93.           "state": {

  94.             "_view_name": "ProgressView",

  95.             "style": "IPY_MODEL_13842ca90c0047e584b8d68d99dad2b1",

  96.             "_dom_classes": [],

  97.             "description": "100%",

  98.             "_model_name": "FloatProgressModel",

  99.             "bar_style": "success",

  100.             "max": 818322941,

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

  102.             "_model_module_version": "1.5.0",

  103.             "value": 818322941,

  104.             "_view_count": null,

  105.             "_view_module_version": "1.5.0",

  106.             "orientation": "horizontal",

  107.             "min": 0,

  108.             "description_tooltip": null,

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

  110.             "layout": "IPY_MODEL_f454999c3a924c7bad0746fb453dec36"

  111.           }

  112.         },

  113.         "853ac234cc2a4236946fc516871e10eb": {

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

  115.           "model_name": "HTMLModel",

  116.           "state": {

  117.             "_view_name": "HTMLView",

  118.             "style": "IPY_MODEL_f94a7ca8c1f04761bf38fdc5f99664b8",

  119.             "_dom_classes": [],

  120.             "description": "",

  121.             "_model_name": "HTMLModel",

  122.             "placeholder": "​",

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

  124.             "_model_module_version": "1.5.0",

  125.             "value": " 780M/780M [03:59<00:00, 3.42MB/s]",

  126.             "_view_count": null,

  127.             "_view_module_version": "1.5.0",

  128.             "description_tooltip": null,

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

  130.             "layout": "IPY_MODEL_9da1a23b042c41618dd14b0e30aa7cbe"

  131.           }

  132.         },

  133.         "13842ca90c0047e584b8d68d99dad2b1": {

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

  135.           "model_name": "ProgressStyleModel",

  136.           "state": {

  137.             "_view_name": "StyleView",

  138.             "_model_name": "ProgressStyleModel",

  139.             "description_width": "initial",

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

  141.             "_model_module_version": "1.5.0",

  142.             "_view_count": null,

  143.             "_view_module_version": "1.2.0",

  144.             "bar_color": null,

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

  146.           }

  147.         },

  148.         "f454999c3a924c7bad0746fb453dec36": {

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

  150.           "model_name": "LayoutModel",

  151.           "state": {

  152.             "_view_name": "LayoutView",

  153.             "grid_template_rows": null,

  154.             "right": null,

  155.             "justify_content": null,

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

  157.             "overflow": null,

  158.             "_model_module_version": "1.2.0",

  159.             "_view_count": null,

  160.             "flex_flow": null,

  161.             "width": null,

  162.             "min_width": null,

  163.             "border": null,

  164.             "align_items": null,

  165.             "bottom": null,

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

  167.             "top": null,

  168.             "grid_column": null,

  169.             "overflow_y": null,

  170.             "overflow_x": null,

  171.             "grid_auto_flow": null,

  172.             "grid_area": null,

  173.             "grid_template_columns": null,

  174.             "flex": null,

  175.             "_model_name": "LayoutModel",

  176.             "justify_items": null,

  177.             "grid_row": null,

  178.             "max_height": null,

  179.             "align_content": null,

  180.             "visibility": null,

  181.             "align_self": null,

  182.             "height": null,

  183.             "min_height": null,

  184.             "padding": null,

  185.             "grid_auto_rows": null,

  186.             "grid_gap": null,

  187.             "max_width": null,

  188.             "order": null,

  189.             "_view_module_version": "1.2.0",

  190.             "grid_template_areas": null,

  191.             "object_position": null,

  192.             "object_fit": null,

  193.             "grid_auto_columns": null,

  194.             "margin": null,

  195.             "display": null,

  196.             "left": null

  197.           }

  198.         },

  199.         "f94a7ca8c1f04761bf38fdc5f99664b8": {

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

  201.           "model_name": "DescriptionStyleModel",

  202.           "state": {

  203.             "_view_name": "StyleView",

  204.             "_model_name": "DescriptionStyleModel",

  205.             "description_width": "",

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

  207.             "_model_module_version": "1.5.0",

  208.             "_view_count": null,

  209.             "_view_module_version": "1.2.0",

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

  211.           }

  212.         },

  213.         "9da1a23b042c41618dd14b0e30aa7cbe": {

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

  215.           "model_name": "LayoutModel",

  216.           "state": {

  217.             "_view_name": "LayoutView",

  218.             "grid_template_rows": null,

  219.             "right": null,

  220.             "justify_content": null,

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

  222.             "overflow": null,

  223.             "_model_module_version": "1.2.0",

  224.             "_view_count": null,

  225.             "flex_flow": null,

  226.             "width": null,

  227.             "min_width": null,

  228.             "border": null,

  229.             "align_items": null,

  230.             "bottom": null,

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

  232.             "top": null,

  233.             "grid_column": null,

  234.             "overflow_y": null,

  235.             "overflow_x": null,

  236.             "grid_auto_flow": null,

  237.             "grid_area": null,

  238.             "grid_template_columns": null,

  239.             "flex": null,

  240.             "_model_name": "LayoutModel",

  241.             "justify_items": null,

  242.             "grid_row": null,

  243.             "max_height": null,

  244.             "align_content": null,

  245.             "visibility": null,

  246.             "align_self": null,

  247.             "height": null,

  248.             "min_height": null,

  249.             "padding": null,

  250.             "grid_auto_rows": null,

  251.             "grid_gap": null,

  252.             "max_width": null,

  253.             "order": null,

  254.             "_view_module_version": "1.2.0",

  255.             "grid_template_areas": null,

  256.             "object_position": null,

  257.             "object_fit": null,

  258.             "grid_auto_columns": null,

  259.             "margin": null,

  260.             "display": null,

  261.             "left": null

  262.           }

  263.         },

  264.         "6ff8a710ded44391a624dec5c460b771": {

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

  266.           "model_name": "HBoxModel",

  267.           "state": {

  268.             "_view_name": "HBoxView",

  269.             "_dom_classes": [],

  270.             "_model_name": "HBoxModel",

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

  272.             "_model_module_version": "1.5.0",

  273.             "_view_count": null,

  274.             "_view_module_version": "1.5.0",

  275.             "box_style": "",

  276.             "layout": "IPY_MODEL_3c19729b51cd45d4848035da06e96ff8",

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

  278.             "children": [

  279.               "IPY_MODEL_23b2f0ae3d46438c8de375987c77f580",

  280.               "IPY_MODEL_dd9498c321a9422da6faf17a0be026d4"

  281.             ]

  282.           }

  283.         },

  284.         "3c19729b51cd45d4848035da06e96ff8": {

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

  286.           "model_name": "LayoutModel",

  287.           "state": {

  288.             "_view_name": "LayoutView",

  289.             "grid_template_rows": null,

  290.             "right": null,

  291.             "justify_content": null,

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

  293.             "overflow": null,

  294.             "_model_module_version": "1.2.0",

  295.             "_view_count": null,

  296.             "flex_flow": null,

  297.             "width": null,

  298.             "min_width": null,

  299.             "border": null,

  300.             "align_items": null,

  301.             "bottom": null,

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

  303.             "top": null,

  304.             "grid_column": null,

  305.             "overflow_y": null,

  306.             "overflow_x": null,

  307.             "grid_auto_flow": null,

  308.             "grid_area": null,

  309.             "grid_template_columns": null,

  310.             "flex": null,

  311.             "_model_name": "LayoutModel",

  312.             "justify_items": null,

  313.             "grid_row": null,

  314.             "max_height": null,

  315.             "align_content": null,

  316.             "visibility": null,

  317.             "align_self": null,

  318.             "height": null,

  319.             "min_height": null,

  320.             "padding": null,

  321.             "grid_auto_rows": null,

  322.             "grid_gap": null,

  323.             "max_width": null,

  324.             "order": null,

  325.             "_view_module_version": "1.2.0",

  326.             "grid_template_areas": null,

  327.             "object_position": null,

  328.             "object_fit": null,

  329.             "grid_auto_columns": null,

  330.             "margin": null,

  331.             "display": null,

  332.             "left": null

  333.           }

  334.         },

  335.         "23b2f0ae3d46438c8de375987c77f580": {

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

  337.           "model_name": "FloatProgressModel",

  338.           "state": {

  339.             "_view_name": "ProgressView",

  340.             "style": "IPY_MODEL_d8dda4b2ce864fd682e558b9a48f602e",

  341.             "_dom_classes": [],

  342.             "description": "100%",

  343.             "_model_name": "FloatProgressModel",

  344.             "bar_style": "success",

  345.             "max": 6984509,

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

  347.             "_model_module_version": "1.5.0",

  348.             "value": 6984509,

  349.             "_view_count": null,

  350.             "_view_module_version": "1.5.0",

  351.             "orientation": "horizontal",

  352.             "min": 0,

  353.             "description_tooltip": null,

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

  355.             "layout": "IPY_MODEL_ff8151449e444a14869684212b9ab14e"

  356.           }

  357.         },

  358.         "dd9498c321a9422da6faf17a0be026d4": {

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

  360.           "model_name": "HTMLModel",

  361.           "state": {

  362.             "_view_name": "HTMLView",

  363.             "style": "IPY_MODEL_0f84fe609bcf4aa9afdc32a8cf076909",

  364.             "_dom_classes": [],

  365.             "description": "",

  366.             "_model_name": "HTMLModel",

  367.             "placeholder": "​",

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

  369.             "_model_module_version": "1.5.0",

  370.             "value": " 6.66M/6.66M [00:01<00:00, 6.08MB/s]",

  371.             "_view_count": null,

  372.             "_view_module_version": "1.5.0",

  373.             "description_tooltip": null,

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

  375.             "layout": "IPY_MODEL_8fda673769984e2b928ef820d34c85c3"

  376.           }

  377.         },

  378.         "d8dda4b2ce864fd682e558b9a48f602e": {

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

  380.           "model_name": "ProgressStyleModel",

  381.           "state": {

  382.             "_view_name": "StyleView",

  383.             "_model_name": "ProgressStyleModel",

  384.             "description_width": "initial",

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

  386.             "_model_module_version": "1.5.0",

  387.             "_view_count": null,

  388.             "_view_module_version": "1.2.0",

  389.             "bar_color": null,

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

  391.           }

  392.         },

  393.         "ff8151449e444a14869684212b9ab14e": {

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

  395.           "model_name": "LayoutModel",

  396.           "state": {

  397.             "_view_name": "LayoutView",

  398.             "grid_template_rows": null,

  399.             "right": null,

  400.             "justify_content": null,

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

  402.             "overflow": null,

  403.             "_model_module_version": "1.2.0",

  404.             "_view_count": null,

  405.             "flex_flow": null,

  406.             "width": null,

  407.             "min_width": null,

  408.             "border": null,

  409.             "align_items": null,

  410.             "bottom": null,

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

  412.             "top": null,

  413.             "grid_column": null,

  414.             "overflow_y": null,

  415.             "overflow_x": null,

  416.             "grid_auto_flow": null,

  417.             "grid_area": null,

  418.             "grid_template_columns": null,

  419.             "flex": null,

  420.             "_model_name": "LayoutModel",

  421.             "justify_items": null,

  422.             "grid_row": null,

  423.             "max_height": null,

  424.             "align_content": null,

  425.             "visibility": null,

  426.             "align_self": null,

  427.             "height": null,

  428.             "min_height": null,

  429.             "padding": null,

  430.             "grid_auto_rows": null,

  431.             "grid_gap": null,

  432.             "max_width": null,

  433.             "order": null,

  434.             "_view_module_version": "1.2.0",

  435.             "grid_template_areas": null,

  436.             "object_position": null,

  437.             "object_fit": null,

  438.             "grid_auto_columns": null,

  439.             "margin": null,

  440.             "display": null,

  441.             "left": null

  442.           }

  443.         },

  444.         "0f84fe609bcf4aa9afdc32a8cf076909": {

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

  446.           "model_name": "DescriptionStyleModel",

  447.           "state": {

  448.             "_view_name": "StyleView",

  449.             "_model_name": "DescriptionStyleModel",

  450.             "description_width": "",

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

  452.             "_model_module_version": "1.5.0",

  453.             "_view_count": null,

  454.             "_view_module_version": "1.2.0",

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

  456.           }

  457.         },

  458.         "8fda673769984e2b928ef820d34c85c3": {

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

  460.           "model_name": "LayoutModel",

  461.           "state": {

  462.             "_view_name": "LayoutView",

  463.             "grid_template_rows": null,

  464.             "right": null,

  465.             "justify_content": null,

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

  467.             "overflow": null,

  468.             "_model_module_version": "1.2.0",

  469.             "_view_count": null,

  470.             "flex_flow": null,

  471.             "width": null,

  472.             "min_width": null,

  473.             "border": null,

  474.             "align_items": null,

  475.             "bottom": null,

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

  477.             "top": null,

  478.             "grid_column": null,

  479.             "overflow_y": null,

  480.             "overflow_x": null,

  481.             "grid_auto_flow": null,

  482.             "grid_area": null,

  483.             "grid_template_columns": null,

  484.             "flex": null,

  485.             "_model_name": "LayoutModel",

  486.             "justify_items": null,

  487.             "grid_row": null,

  488.             "max_height": null,

  489.             "align_content": null,

  490.             "visibility": null,

  491.             "align_self": null,

  492.             "height": null,

  493.             "min_height": null,

  494.             "padding": null,

  495.             "grid_auto_rows": null,

  496.             "grid_gap": null,

  497.             "max_width": null,

  498.             "order": null,

  499.             "_view_module_version": "1.2.0",

  500.             "grid_template_areas": null,

  501.             "object_position": null,

  502.             "object_fit": null,

  503.             "grid_auto_columns": null,

  504.             "margin": null,

  505.             "display": null,

  506.             "left": null

  507.           }

  508.         }

  509.       }

  510.     }

  511.   },

  512.   "cells": [

  513.     {

  514.       "cell_type": "markdown",

  515.       "metadata": {

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

  517.         "colab_type": "text"

  518.       },

  519.       "source": [

  520.         "<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>"

  521.       ]

  522.     },

  523.     {

  524.       "cell_type": "markdown",

  525.       "metadata": {

  526.         "id": "t6MPjfT5NrKQ"

  527.       },

  528.       "source": [

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

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

  531.         "\n",

  532.         "This is the **official YOLOv5 🚀 notebook** authored by **Ultralytics**, and is freely available for redistribution under the [GPL-3.0 license](https://choosealicense.com/licenses/gpl-3.0/). \n",

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

  534.       ]

  535.     },

  536.     {

  537.       "cell_type": "markdown",

  538.       "metadata": {

  539.         "id": "7mGmQbAO5pQb"

  540.       },

  541.       "source": [

  542.         "# Setup\n",

  543.         "\n",

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

  545.       ]

  546.     },

  547.     {

  548.       "cell_type": "code",

  549.       "metadata": {

  550.         "id": "wbvMlHd_QwMG",

  551.         "colab": {

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

  553.         },

  554.         "outputId": "ada1dd8d-e0aa-4858-e893-dc320319ca30"

  555.       },

  556.       "source": [

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

  558.         "%cd yolov5\n",

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

  560.         "\n",

  561.         "import torch\n",

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

  563.         "\n",

  564.         "clear_output()\n",

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

  566.       ],

  567.       "execution_count": 1,

  568.       "outputs": [

  569.         {

  570.           "output_type": "stream",

  571.           "text": [

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

  573.           ],

  574.           "name": "stdout"

  575.         }

  576.       ]

  577.     },

  578.     {

  579.       "cell_type": "markdown",

  580.       "metadata": {

  581.         "id": "4JnkELT0cIJg"

  582.       },

  583.       "source": [

  584.         "# 1. Inference\n",

  585.         "\n",

  586.         "`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",

  587.         "\n",

  588.         "<img align=\"left\" src=\"https://user-images.githubusercontent.com/26833433/114307955-5c7e4e80-9ae2-11eb-9f50-a90e39bee53f.png\" width=\"900\"> "

  589.       ]

  590.     },

  591.     {

  592.       "cell_type": "code",

  593.       "metadata": {

  594.         "id": "zR9ZbuQCH7FX",

  595.         "colab": {

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

  597.         },

  598.         "outputId": "a7a37616-a82b-4bdb-a463-6ead850b5615"

  599.       },

  600.       "source": [

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

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

  603.       ],

  604.       "execution_count": 9,

  605.       "outputs": [

  606.         {

  607.           "output_type": "stream",

  608.           "text": [

  609.             "\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",

  610.             "YOLOv5 🚀 v5.0-330-g18f6ba7 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",

  611.             "\n",

  612.             "Fusing layers... \n",

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

  614.             "image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, 1 fire hydrant, Done. (0.008s)\n",

  615.             "image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.008s)\n",

  616.             "Results saved to runs/detect/exp\n",

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

  618.           ],

  619.           "name": "stdout"

  620.         }

  621.       ]

  622.     },

  623.     {

  624.       "cell_type": "markdown",

  625.       "metadata": {

  626.         "id": "hkAzDWJ7cWTr"

  627.       },

  628.       "source": [

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

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

  631.       ]

  632.     },

  633.     {

  634.       "cell_type": "markdown",

  635.       "metadata": {

  636.         "id": "0eq1SMWl6Sfn"

  637.       },

  638.       "source": [

  639.         "# 2. Validate\n",

  640.         "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."

  641.       ]

  642.     },

  643.     {

  644.       "cell_type": "markdown",

  645.       "metadata": {

  646.         "id": "eyTZYGgRjnMc"

  647.       },

  648.       "source": [

  649.         "## COCO val2017\n",

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

  651.       ]

  652.     },

  653.     {

  654.       "cell_type": "code",

  655.       "metadata": {

  656.         "id": "WQPtK1QYVaD_",

  657.         "colab": {

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

  659.           "height": 66,

  660.           "referenced_widgets": [

  661.             "2e915d9016c846e095e382b6a02ee773",

  662.             "cb7fc3a5c6cc4fde8d2c83e594a7c86e",

  663.             "ac3edef4e3434f4587e6cbf8aa048770",

  664.             "853ac234cc2a4236946fc516871e10eb",

  665.             "13842ca90c0047e584b8d68d99dad2b1",

  666.             "f454999c3a924c7bad0746fb453dec36",

  667.             "f94a7ca8c1f04761bf38fdc5f99664b8",

  668.             "9da1a23b042c41618dd14b0e30aa7cbe"

  669.           ]

  670.         },

  671.         "outputId": "3606f305-aa67-43fd-d5d6-93d1f311768c"

  672.       },

  673.       "source": [

  674.         "# Download COCO val2017\n",

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

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

  677.       ],

  678.       "execution_count": 10,

  679.       "outputs": [

  680.         {

  681.           "output_type": "display_data",

  682.           "data": {

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

  684.               "model_id": "2e915d9016c846e095e382b6a02ee773",

  685.               "version_minor": 0,

  686.               "version_major": 2

  687.             },

  688.             "text/plain": [

  689.               "HBox(children=(FloatProgress(value=0.0, max=818322941.0), HTML(value='')))"

  690.             ]

  691.           },

  692.           "metadata": {

  693.             "tags": []

  694.           }

  695.         },

  696.         {

  697.           "output_type": "stream",

  698.           "text": [

  699.             "\n"

  700.           ],

  701.           "name": "stdout"

  702.         }

  703.       ]

  704.     },

  705.     {

  706.       "cell_type": "code",

  707.       "metadata": {

  708.         "id": "X58w8JLpMnjH",

  709.         "colab": {

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

  711.         },

  712.         "outputId": "20fbc423-f536-43ff-e70b-3acf6aeade99"

  713.       },

  714.       "source": [

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

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

  717.       ],

  718.       "execution_count": 11,

  719.       "outputs": [

  720.         {

  721.           "output_type": "stream",

  722.           "text": [

  723.             "\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",

  724.             "YOLOv5 🚀 v5.0-330-g18f6ba7 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",

  725.             "\n",

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

  727.             "100% 168M/168M [00:05<00:00, 31.9MB/s]\n",

  728.             "\n",

  729.             "Fusing layers... \n",

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

  731.             "\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:01<00:00, 2653.03it/s]\n",

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

  733.             "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 157/157 [01:18<00:00,  2.00it/s]\n",

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

  735.             "Speed: 0.1ms pre-process, 5.1ms inference, 1.5ms NMS per image at shape (32, 3, 640, 640)\n",

  736.             "\n",

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

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

  739.             "Done (t=0.44s)\n",

  740.             "creating index...\n",

  741.             "index created!\n",

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

  743.             "DONE (t=4.82s)\n",

  744.             "creating index...\n",

  745.             "index created!\n",

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

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

  748.             "DONE (t=84.52s).\n",

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

  750.             "DONE (t=13.82s).\n",

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

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

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

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

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

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

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

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

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

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

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

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

  763.             "Results saved to runs/val/exp\n"

  764.           ],

  765.           "name": "stdout"

  766.         }

  767.       ]

  768.     },

  769.     {

  770.       "cell_type": "markdown",

  771.       "metadata": {

  772.         "id": "rc_KbFk0juX2"

  773.       },

  774.       "source": [

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

  776.         "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."

  777.       ]

  778.     },

  779.     {

  780.       "cell_type": "code",

  781.       "metadata": {

  782.         "id": "V0AJnSeCIHyJ"

  783.       },

  784.       "source": [

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

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

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

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

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

  790.       ],

  791.       "execution_count": null,

  792.       "outputs": []

  793.     },

  794.     {

  795.       "cell_type": "code",

  796.       "metadata": {

  797.         "id": "29GJXAP_lPrt"

  798.       },

  799.       "source": [

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

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

  802.       ],

  803.       "execution_count": null,

  804.       "outputs": []

  805.     },

  806.     {

  807.       "cell_type": "markdown",

  808.       "metadata": {

  809.         "id": "VUOiNLtMP5aG"

  810.       },

  811.       "source": [

  812.         "# 3. Train\n",

  813.         "\n",

  814.         "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)."

  815.       ]

  816.     },

  817.     {

  818.       "cell_type": "code",

  819.       "metadata": {

  820.         "id": "Knxi2ncxWffW",

  821.         "colab": {

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

  823.           "height": 66,

  824.           "referenced_widgets": [

  825.             "6ff8a710ded44391a624dec5c460b771",

  826.             "3c19729b51cd45d4848035da06e96ff8",

  827.             "23b2f0ae3d46438c8de375987c77f580",

  828.             "dd9498c321a9422da6faf17a0be026d4",

  829.             "d8dda4b2ce864fd682e558b9a48f602e",

  830.             "ff8151449e444a14869684212b9ab14e",

  831.             "0f84fe609bcf4aa9afdc32a8cf076909",

  832.             "8fda673769984e2b928ef820d34c85c3"

  833.           ]

  834.         },

  835.         "outputId": "4510c6b0-8d2a-436c-d3f4-c8f8470d913a"

  836.       },

  837.       "source": [

  838.         "# Download COCO128\n",

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

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

  841.       ],

  842.       "execution_count": 12,

  843.       "outputs": [

  844.         {

  845.           "output_type": "display_data",

  846.           "data": {

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

  848.               "model_id": "6ff8a710ded44391a624dec5c460b771",

  849.               "version_minor": 0,

  850.               "version_major": 2

  851.             },

  852.             "text/plain": [

  853.               "HBox(children=(FloatProgress(value=0.0, max=6984509.0), HTML(value='')))"

  854.             ]

  855.           },

  856.           "metadata": {

  857.             "tags": []

  858.           }

  859.         },

  860.         {

  861.           "output_type": "stream",

  862.           "text": [

  863.             "\n"

  864.           ],

  865.           "name": "stdout"

  866.         }

  867.       ]

  868.     },

  869.     {

  870.       "cell_type": "markdown",

  871.       "metadata": {

  872.         "id": "_pOkGLv1dMqh"

  873.       },

  874.       "source": [

  875.         "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",

  876.         "\n",

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

  878.       ]

  879.     },

  880.     {

  881.       "cell_type": "code",

  882.       "metadata": {

  883.         "id": "bOy5KI2ncnWd"

  884.       },

  885.       "source": [

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

  887.         "%load_ext tensorboard\n",

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

  889.       ],

  890.       "execution_count": null,

  891.       "outputs": []

  892.     },

  893.     {

  894.       "cell_type": "code",

  895.       "metadata": {

  896.         "id": "2fLAV42oNb7M"

  897.       },

  898.       "source": [

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

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

  901.         "import wandb\n",

  902.         "wandb.login()"

  903.       ],

  904.       "execution_count": null,

  905.       "outputs": []

  906.     },

  907.     {

  908.       "cell_type": "code",

  909.       "metadata": {

  910.         "id": "1NcFxRcFdJ_O",

  911.         "colab": {

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

  913.         },

  914.         "outputId": "cd8ac17d-19a8-4e87-ab6a-31af1edac1ef"

  915.       },

  916.       "source": [

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

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

  919.       ],

  920.       "execution_count": 13,

  921.       "outputs": [

  922.         {

  923.           "output_type": "stream",

  924.           "text": [

  925.             "\u001b[34m\u001b[1mtrain: \u001b[0mweights=yolov5s.pt, cfg=, data=coco128.yaml, hyp=data/hyps/hyp.scratch.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, evolve=None, bucket=, cache_images=True, image_weights=False, device=, multi_scale=False, single_cls=False, adam=False, sync_bn=False, workers=8, project=runs/train, entity=None, name=exp, exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, upload_dataset=False, bbox_interval=-1, save_period=-1, artifact_alias=latest, local_rank=-1\n",

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

  927.             "YOLOv5 🚀 v5.0-330-g18f6ba7 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",

  928.             "\n",

  929.             "\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",

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

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

  932.             "2021-07-29 22:56:52.096481: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudart.so.11.0\n",

  933.             "\n",

  934.             "WARNING: Dataset not found, nonexistent paths: ['/content/datasets/coco128/images/train2017']\n",

  935.             "Downloading https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip ...\n",

  936.             "100% 6.66M/6.66M [00:00<00:00, 44.0MB/s]\n",

  937.             "Dataset autodownload success\n",

  938.             "\n",

  939.             "\n",

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

  941.             "  0                -1  1      3520  models.common.Focus                     [3, 32, 3]                    \n",

  942.             "  1                -1  1     18560  models.common.Conv                      [32, 64, 3, 2]                \n",

  943.             "  2                -1  1     18816  models.common.C3                        [64, 64, 1]                   \n",

  944.             "  3                -1  1     73984  models.common.Conv                      [64, 128, 3, 2]               \n",

  945.             "  4                -1  1    156928  models.common.C3                        [128, 128, 3]                 \n",

  946.             "  5                -1  1    295424  models.common.Conv                      [128, 256, 3, 2]              \n",

  947.             "  6                -1  1    625152  models.common.C3                        [256, 256, 3]                 \n",

  948.             "  7                -1  1   1180672  models.common.Conv                      [256, 512, 3, 2]              \n",

  949.             "  8                -1  1    656896  models.common.SPP                       [512, 512, [5, 9, 13]]        \n",

  950.             "  9                -1  1   1182720  models.common.C3                        [512, 512, 1, False]          \n",

  951.             " 10                -1  1    131584  models.common.Conv                      [512, 256, 1, 1]              \n",

  952.             " 11                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          \n",

  953.             " 12           [-1, 6]  1         0  models.common.Concat                    [1]                           \n",

  954.             " 13                -1  1    361984  models.common.C3                        [512, 256, 1, False]          \n",

  955.             " 14                -1  1     33024  models.common.Conv                      [256, 128, 1, 1]              \n",

  956.             " 15                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          \n",

  957.             " 16           [-1, 4]  1         0  models.common.Concat                    [1]                           \n",

  958.             " 17                -1  1     90880  models.common.C3                        [256, 128, 1, False]          \n",

  959.             " 18                -1  1    147712  models.common.Conv                      [128, 128, 3, 2]              \n",

  960.             " 19          [-1, 14]  1         0  models.common.Concat                    [1]                           \n",

  961.             " 20                -1  1    296448  models.common.C3                        [256, 256, 1, False]          \n",

  962.             " 21                -1  1    590336  models.common.Conv                      [256, 256, 3, 2]              \n",

  963.             " 22          [-1, 10]  1         0  models.common.Concat                    [1]                           \n",

  964.             " 23                -1  1   1182720  models.common.C3                        [512, 512, 1, False]          \n",

  965.             " 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",

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

  967.             "\n",

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

  969.             "Scaled weight_decay = 0.0005\n",

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

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

  972.             "\u001b[34m\u001b[1mtrain: \u001b[0mScanning '../datasets/coco128/labels/train2017' images and labels...128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<00:00, 2021.98it/s]\n",

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

  974.             "\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB): 100% 128/128 [00:00<00:00, 273.58it/s]\n",

  975.             "\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<00:00, 506004.63it/s]\n",

  976.             "\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB): 100% 128/128 [00:01<00:00, 121.71it/s]\n",

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

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

  979.             "Plotting labels... \n",

  980.             "\n",

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

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

  983.             "Using 2 dataloader workers\n",

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

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

  986.             "\n",

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

  988.             "       0/2     3.64G    0.0441   0.06646   0.02229       290       640: 100% 8/8 [00:04<00:00,  1.93it/s]\n",

  989.             "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00,  3.45it/s]\n",

  990.             "                 all        128        929      0.696      0.562      0.644      0.419\n",

  991.             "\n",

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

  993.             "       1/2     5.04G   0.04573   0.06289     0.021       226       640: 100% 8/8 [00:01<00:00,  5.46it/s]\n",

  994.             "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00,  3.16it/s]\n",

  995.             "                 all        128        929       0.71      0.567      0.654      0.424\n",

  996.             "\n",

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

  998.             "       2/2     5.04G   0.04542    0.0715   0.02028       242       640: 100% 8/8 [00:01<00:00,  5.12it/s]\n",

  999.             "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00,  1.46it/s]\n",

  1000.             "                 all        128        929      0.731      0.563      0.658      0.427\n",

  1001.             "3 epochs completed in 0.006 hours.\n",

  1002.             "\n",

  1003.             "Optimizer stripped from runs/train/exp/weights/last.pt, 14.8MB\n",

  1004.             "Optimizer stripped from runs/train/exp/weights/best.pt, 14.8MB\n"

  1005.           ],

  1006.           "name": "stdout"

  1007.         }

  1008.       ]

  1009.     },

  1010.     {

  1011.       "cell_type": "markdown",

  1012.       "metadata": {

  1013.         "id": "15glLzbQx5u0"

  1014.       },

  1015.       "source": [

  1016.         "# 4. Visualize"

  1017.       ]

  1018.     },

  1019.     {

  1020.       "cell_type": "markdown",

  1021.       "metadata": {

  1022.         "id": "DLI1JmHU7B0l"

  1023.       },

  1024.       "source": [

  1025.         "## Weights & Biases Logging 🌟 NEW\n",

  1026.         "\n",

  1027.         "[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",

  1028.         "\n",

  1029.         "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",

  1030.         "\n",

  1031.         "<img align=\"left\" src=\"https://user-images.githubusercontent.com/26833433/125274843-a27bc600-e30e-11eb-9a44-62af0b7a50a2.png\" width=\"800\">"

  1032.       ]

  1033.     },

  1034.     {

  1035.       "cell_type": "markdown",

  1036.       "metadata": {

  1037.         "id": "-WPvRbS5Swl6"

  1038.       },

  1039.       "source": [

  1040.         "## Local Logging\n",

  1041.         "\n",

  1042.         "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",

  1043.         "\n",

  1044.         "> <img src=\"https://user-images.githubusercontent.com/26833433/124931219-48bf8700-e002-11eb-84f0-e05d95b118dd.jpg\" width=\"700\">  \n",

  1045.         "`train_batch0.jpg` shows train batch 0 mosaics and labels\n",

  1046.         "\n",

  1047.         "> <img src=\"https://user-images.githubusercontent.com/26833433/124931217-4826f080-e002-11eb-87b9-ae0925a8c94b.jpg\" width=\"700\">  \n",

  1048.         "`test_batch0_labels.jpg` shows val batch 0 labels\n",

  1049.         "\n",

  1050.         "> <img src=\"https://user-images.githubusercontent.com/26833433/124931209-46f5c380-e002-11eb-9bd5-7a3de2be9851.jpg\" width=\"700\">  \n",

  1051.         "`test_batch0_pred.jpg` shows val batch 0 _predictions_\n",

  1052.         "\n",

  1053.         "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",

  1054.         "\n",

  1055.         "```python\n",

  1056.         "from utils.plots import plot_results \n",

  1057.         "plot_results('path/to/results.csv')  # plot 'results.csv' as 'results.png'\n",

  1058.         "```\n",

  1059.         "\n",

  1060.         "<img align=\"left\" width=\"800\" alt=\"COCO128 Training Results\" src=\"https://user-images.githubusercontent.com/26833433/126906780-8c5e2990-6116-4de6-b78a-367244a33ccf.png\">"

  1061.       ]

  1062.     },

  1063.     {

  1064.       "cell_type": "markdown",

  1065.       "metadata": {

  1066.         "id": "Zelyeqbyt3GD"

  1067.       },

  1068.       "source": [

  1069.         "# Environments\n",

  1070.         "\n",

  1071.         "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",

  1072.         "\n",

  1073.         "- **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",

  1074.         "- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart)\n",

  1075.         "- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart)\n",

  1076.         "- **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"

  1077.       ]

  1078.     },

  1079.     {

  1080.       "cell_type": "markdown",

  1081.       "metadata": {

  1082.         "id": "6Qu7Iesl0p54"

  1083.       },

  1084.       "source": [

  1085.         "# Status\n",

  1086.         "\n",

  1087.         "![CI CPU testing](https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg)\n",

  1088.         "\n",

  1089.         "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"

  1090.       ]

  1091.     },

  1092.     {

  1093.       "cell_type": "markdown",

  1094.       "metadata": {

  1095.         "id": "IEijrePND_2I"

  1096.       },

  1097.       "source": [

  1098.         "# Appendix\n",

  1099.         "\n",

  1100.         "Optional extras below. Unit tests validate repo functionality and should be run on any PRs submitted.\n"

  1101.       ]

  1102.     },

  1103.     {

  1104.       "cell_type": "code",

  1105.       "metadata": {

  1106.         "id": "mcKoSIK2WSzj"

  1107.       },

  1108.       "source": [

  1109.         "# Reproduce\n",

  1110.         "for x in 'yolov5s', 'yolov5m', 'yolov5l', 'yolov5x':\n",

  1111.         "  !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.25 --iou 0.45  # speed\n",

  1112.         "  !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.001 --iou 0.65  # mAP"

  1113.       ],

  1114.       "execution_count": null,

  1115.       "outputs": []

  1116.     },

  1117.     {

  1118.       "cell_type": "code",

  1119.       "metadata": {

  1120.         "id": "GMusP4OAxFu6"

  1121.       },

  1122.       "source": [

  1123.         "# PyTorch Hub\n",

  1124.         "import torch\n",

  1125.         "\n",

  1126.         "# Model\n",

  1127.         "model = torch.hub.load('ultralytics/yolov5', 'yolov5s')\n",

  1128.         "\n",

  1129.         "# Images\n",

  1130.         "dir = 'https://ultralytics.com/images/'\n",

  1131.         "imgs = [dir + f for f in ('zidane.jpg', 'bus.jpg')]  # batch of images\n",

  1132.         "\n",

  1133.         "# Inference\n",

  1134.         "results = model(imgs)\n",

  1135.         "results.print()  # or .show(), .save()"

  1136.       ],

  1137.       "execution_count": null,

  1138.       "outputs": []

  1139.     },

  1140.     {

  1141.       "cell_type": "code",

  1142.       "metadata": {

  1143.         "id": "FGH0ZjkGjejy"

  1144.       },

  1145.       "source": [

  1146.         "# Unit tests\n",

  1147.         "%%shell\n",

  1148.         "export PYTHONPATH=\"$PWD\"  # to run *.py. files in subdirectories\n",

  1149.         "\n",

  1150.         "rm -rf runs  # remove runs/\n",

  1151.         "for m in yolov5s; do  # models\n",

  1152.         "  python train.py --weights $m.pt --epochs 3 --img 320 --device 0  # train pretrained\n",

  1153.         "  python train.py --weights '' --cfg $m.yaml --epochs 3 --img 320 --device 0  # train scratch\n",

  1154.         "  for d in 0 cpu; do  # devices\n",

  1155.         "    python detect.py --weights $m.pt --device $d  # detect official\n",

  1156.         "    python detect.py --weights runs/train/exp/weights/best.pt --device $d  # detect custom\n",

  1157.         "    python val.py --weights $m.pt --device $d # val official\n",

  1158.         "    python val.py --weights runs/train/exp/weights/best.pt --device $d # val custom\n",

  1159.         "  done\n",

  1160.         "  python hubconf.py  # hub\n",

  1161.         "  python models/yolo.py --cfg $m.yaml  # inspect\n",

  1162.         "  python export.py --weights $m.pt --img 640 --batch 1  # export\n",

  1163.         "done"

  1164.       ],

  1165.       "execution_count": null,

  1166.       "outputs": []

  1167.     },

  1168.     {

  1169.       "cell_type": "code",

  1170.       "metadata": {

  1171.         "id": "gogI-kwi3Tye"

  1172.       },

  1173.       "source": [

  1174.         "# Profile\n",

  1175.         "from utils.torch_utils import profile \n",

  1176.         "\n",

  1177.         "m1 = lambda x: x * torch.sigmoid(x)\n",

  1178.         "m2 = torch.nn.SiLU()\n",

  1179.         "profile(x=torch.randn(16, 3, 640, 640), ops=[m1, m2], n=100)"

  1180.       ],

  1181.       "execution_count": null,

  1182.       "outputs": []

  1183.     },

  1184.     {

  1185.       "cell_type": "code",

  1186.       "metadata": {

  1187.         "id": "RVRSOhEvUdb5"

  1188.       },

  1189.       "source": [

  1190.         "# Evolve\n",

  1191.         "!python train.py --img 640 --batch 64 --epochs 100 --data coco128.yaml --weights yolov5s.pt --cache --noautoanchor --evolve\n",

  1192.         "!d=runs/train/evolve && cp evolve.* $d && zip -r evolve.zip $d && gsutil mv evolve.zip gs://bucket  # upload results (optional)"

  1193.       ],

  1194.       "execution_count": null,

  1195.       "outputs": []

  1196.     },

  1197.     {

  1198.       "cell_type": "code",

  1199.       "metadata": {

  1200.         "id": "BSgFCAcMbk1R"

  1201.       },

  1202.       "source": [

  1203.         "# VOC\n",

  1204.         "for b, m in zip([64, 48, 32, 16], ['yolov5s', 'yolov5m', 'yolov5l', 'yolov5x']):  # zip(batch_size, model)\n",

  1205.         "  !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}"

  1206.       ],

  1207.       "execution_count": null,

  1208.       "outputs": []

  1209.     }

  1210.   ]

  1211. }