yolov5/tutorial.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "YOLOv5 Tutorial",
      "provenance": [],
      "collapsed_sections": [],
      "machine_shape": "hm",
      "toc_visible": true,
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU",
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "da0946bcefd9414fa282977f7f609e36": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "2.0.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "2.0.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "2.0.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_7838c0af44244ccc906c413cea0989d7",
              "IPY_MODEL_309ea78b3e814198b4080beb878d5329",
              "IPY_MODEL_b2d1d998e5db4ca1a36280902e1647c7"
            ],
            "layout": "IPY_MODEL_e7d7f56c77884717ba122f1d603c0852",
            "tabbable": null,
            "tooltip": null
          }
        },
        "7838c0af44244ccc906c413cea0989d7": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "2.0.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "2.0.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "2.0.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_allow_html": false,
            "layout": "IPY_MODEL_abf60d6b8ea847f9bb358ae2b045458b",
            "placeholder": "​",
            "style": "IPY_MODEL_379196a2761b4a29aca8ef088dc60c10",
            "tabbable": null,
            "tooltip": null,
            "value": "100%"
          }
        },
        "309ea78b3e814198b4080beb878d5329": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "2.0.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "2.0.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "2.0.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_allow_html": false,
            "layout": "IPY_MODEL_52b546a356e54174a95049b30cb52c81",
            "max": 818322941,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_0889e134327e4aa0a8719d03a0d6941b",
            "tabbable": null,
            "tooltip": null,
            "value": 818322941
          }
        },
        "b2d1d998e5db4ca1a36280902e1647c7": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "2.0.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "2.0.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "2.0.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_allow_html": false,
            "layout": "IPY_MODEL_30f22a3e42d24f10ad9851f40a6703f3",
            "placeholder": "​",
            "style": "IPY_MODEL_648b3512bb7d4ccca5d75af36c133e92",
            "tabbable": null,
            "tooltip": null,
            "value": " 780M/780M [01:31<00:00, 12.3MB/s]"
          }
        },
        "e7d7f56c77884717ba122f1d603c0852": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "2.0.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "2.0.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "2.0.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border_bottom": null,
            "border_left": null,
            "border_right": null,
            "border_top": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "abf60d6b8ea847f9bb358ae2b045458b": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "2.0.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "2.0.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "2.0.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border_bottom": null,
            "border_left": null,
            "border_right": null,
            "border_top": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "379196a2761b4a29aca8ef088dc60c10": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLStyleModel",
          "model_module_version": "2.0.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "2.0.0",
            "_model_name": "HTMLStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "2.0.0",
            "_view_name": "StyleView",
            "background": null,
            "description_width": "",
            "font_size": null,
            "text_color": null
          }
        },
        "52b546a356e54174a95049b30cb52c81": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "2.0.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "2.0.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "2.0.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border_bottom": null,
            "border_left": null,
            "border_right": null,
            "border_top": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "0889e134327e4aa0a8719d03a0d6941b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "2.0.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "2.0.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "2.0.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "30f22a3e42d24f10ad9851f40a6703f3": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "2.0.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "2.0.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "2.0.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border_bottom": null,
            "border_left": null,
            "border_right": null,
            "border_top": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "648b3512bb7d4ccca5d75af36c133e92": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLStyleModel",
          "model_module_version": "2.0.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "2.0.0",
            "_model_name": "HTMLStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "2.0.0",
            "_view_name": "StyleView",
            "background": null,
            "description_width": "",
            "font_size": null,
            "text_color": null
          }
        }
      }
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<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>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "t6MPjfT5NrKQ"
      },
      "source": [
        "<a align=\"left\" href=\"https://ultralytics.com/yolov5\" target=\"_blank\">\n",
        "<img width=\"1024\", src=\"https://user-images.githubusercontent.com/26833433/125273437-35b3fc00-e30d-11eb-9079-46f313325424.png\"></a>\n",
        "\n",
        "This is the **official YOLOv5 🚀 notebook** by **Ultralytics**, and is freely available for redistribution under the [GPL-3.0 license](https://choosealicense.com/licenses/gpl-3.0/). \n",
        "For more information please visit https://github.com/ultralytics/yolov5 and https://ultralytics.com. Thank you!"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "7mGmQbAO5pQb"
      },
      "source": [
        "# Setup\n",
        "\n",
        "Clone repo, install dependencies and check PyTorch and GPU."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "wbvMlHd_QwMG",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "4200fd6f-c6f5-4505-a4f9-a918f3ed1f86"
      },
      "source": [
        "!git clone https://github.com/ultralytics/yolov5  # clone\n",
        "%cd yolov5\n",
        "%pip install -qr requirements.txt  # install\n",
        "\n",
        "import torch\n",
        "import utils\n",
        "display = utils.notebook_init()  # checks"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "YOLOv5 🚀 v6.2-41-g8665d55 Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Setup complete ✅ (8 CPUs, 51.0 GB RAM, 37.4/166.8 GB disk)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "4JnkELT0cIJg"
      },
      "source": [
        "# 1. Detect\n",
        "\n",
        "`detect.py` runs YOLOv5 inference on a variety of sources, downloading models automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases), and saving results to `runs/detect`. Example inference sources are:\n",
        "\n",
        "```shell\n",
        "python detect.py --source 0  # webcam\n",
        "                          img.jpg  # image \n",
        "                          vid.mp4  # video\n",
        "                          path/  # directory\n",
        "                          'path/*.jpg'  # glob\n",
        "                          'https://youtu.be/Zgi9g1ksQHc'  # YouTube\n",
        "                          'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream\n",
        "```"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "zR9ZbuQCH7FX",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "1af15107-bcd1-4e8f-b5bd-0ee1a737e051"
      },
      "source": [
        "!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images\n",
        "# display.Image(filename='runs/detect/exp/zidane.jpg', width=600)"
      ],
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov5s.pt'], source=data/images, data=data/coco128.yaml, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False\n",
            "YOLOv5 🚀 v6.2-41-g8665d55 Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
            "\n",
            "Downloading https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5s.pt to yolov5s.pt...\n",
            "100% 14.1M/14.1M [00:00<00:00, 41.7MB/s]\n",
            "\n",
            "Fusing layers... \n",
            "YOLOv5s summary: 213 layers, 7225885 parameters, 0 gradients\n",
            "image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, 14.5ms\n",
            "image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, 18.9ms\n",
            "Speed: 0.5ms pre-process, 16.7ms inference, 21.4ms NMS per image at shape (1, 3, 640, 640)\n",
            "Results saved to \u001b[1mruns/detect/exp\u001b[0m\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "hkAzDWJ7cWTr"
      },
      "source": [
        "&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\n",
        "<img align=\"left\" src=\"https://user-images.githubusercontent.com/26833433/127574988-6a558aa1-d268-44b9-bf6b-62d4c605cc72.jpg\" width=\"600\">"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "0eq1SMWl6Sfn"
      },
      "source": [
        "# 2. Validate\n",
        "Validate a model's accuracy on the [COCO](https://cocodataset.org/#home) dataset's `val` or `test` splits. Models are downloaded automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases). To show results by class use the `--verbose` flag."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "WQPtK1QYVaD_",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 17,
          "referenced_widgets": [
            "da0946bcefd9414fa282977f7f609e36",
            "7838c0af44244ccc906c413cea0989d7",
            "309ea78b3e814198b4080beb878d5329",
            "b2d1d998e5db4ca1a36280902e1647c7",
            "e7d7f56c77884717ba122f1d603c0852",
            "abf60d6b8ea847f9bb358ae2b045458b",
            "379196a2761b4a29aca8ef088dc60c10",
            "52b546a356e54174a95049b30cb52c81",
            "0889e134327e4aa0a8719d03a0d6941b",
            "30f22a3e42d24f10ad9851f40a6703f3",
            "648b3512bb7d4ccca5d75af36c133e92"
          ]
        },
        "outputId": "5f129105-eca5-4f33-fb1d-981255f814ad"
      },
      "source": [
        "# Download COCO val\n",
        "torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017val.zip', 'tmp.zip')  # download (780M - 5000 images)\n",
        "!unzip -q tmp.zip -d ../datasets && rm tmp.zip  # unzip"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "  0%|          | 0.00/780M [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "da0946bcefd9414fa282977f7f609e36"
            },
            "application/json": {
              "n": 0,
              "total": 818322941,
              "elapsed": 0.020366430282592773,
              "ncols": null,
              "nrows": null,
              "prefix": "",
              "ascii": false,
              "unit": "B",
              "unit_scale": true,
              "rate": null,
              "bar_format": null,
              "postfix": null,
              "unit_divisor": 1024,
              "initial": 0,
              "colour": null
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "X58w8JLpMnjH",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "40d5d000-abee-46a0-c07d-1066e1662e01"
      },
      "source": [
        "# Validate YOLOv5x on COCO val\n",
        "!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[34m\u001b[1mval: \u001b[0mdata=/content/yolov5/data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.65, task=val, device=, workers=8, 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, dnn=False\n",
            "YOLOv5 🚀 v6.2-41-g8665d55 Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
            "\n",
            "Downloading https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5x.pt to yolov5x.pt...\n",
            "100% 166M/166M [00:10<00:00, 16.6MB/s]\n",
            "\n",
            "Fusing layers... \n",
            "YOLOv5x summary: 444 layers, 86705005 parameters, 0 gradients\n",
            "Downloading https://ultralytics.com/assets/Arial.ttf to /root/.config/Ultralytics/Arial.ttf...\n",
            "100% 755k/755k [00:00<00:00, 1.39MB/s]\n",
            "\u001b[34m\u001b[1mval: \u001b[0mScanning '/content/datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupt: 100% 5000/5000 [00:00<00:00, 10506.48it/s]\n",
            "\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /content/datasets/coco/val2017.cache\n",
            "                 Class     Images  Instances          P          R     mAP@.5 mAP@.5:.95: 100% 157/157 [01:06<00:00,  2.36it/s]\n",
            "                   all       5000      36335      0.743      0.625      0.683      0.504\n",
            "Speed: 0.1ms pre-process, 4.6ms inference, 1.1ms NMS per image at shape (32, 3, 640, 640)\n",
            "\n",
            "Evaluating pycocotools mAP... saving runs/val/exp/yolov5x_predictions.json...\n",
            "loading annotations into memory...\n",
            "Done (t=0.38s)\n",
            "creating index...\n",
            "index created!\n",
            "Loading and preparing results...\n",
            "DONE (t=5.49s)\n",
            "creating index...\n",
            "index created!\n",
            "Running per image evaluation...\n",
            "Evaluate annotation type *bbox*\n",
            "DONE (t=72.10s).\n",
            "Accumulating evaluation results...\n",
            "DONE (t=13.94s).\n",
            " Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.506\n",
            " Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.688\n",
            " Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.549\n",
            " Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.340\n",
            " Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.558\n",
            " Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.651\n",
            " Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.382\n",
            " Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.631\n",
            " Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.684\n",
            " Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.528\n",
            " Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.737\n",
            " Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.833\n",
            "Results saved to \u001b[1mruns/val/exp\u001b[0m\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ZY2VXXXu74w5"
      },
      "source": [
        "# 3. Train\n",
        "\n",
        "<p align=\"\"><a href=\"https://roboflow.com/?ref=ultralytics\"><img width=\"1000\" src=\"https://uploads-ssl.webflow.com/5f6bc60e665f54545a1e52a5/615627e5824c9c6195abfda9_computer-vision-cycle.png\"/></a></p>\n",
        "Close the active learning loop by sampling images from your inference conditions with the `roboflow` pip package\n",
        "<br><br>\n",
        "\n",
        "Train a YOLOv5s model on the [COCO128](https://www.kaggle.com/ultralytics/coco128) dataset with `--data coco128.yaml`, starting from pretrained `--weights yolov5s.pt`, or from randomly initialized `--weights '' --cfg yolov5s.yaml`.\n",
        "\n",
        "- **Pretrained [Models](https://github.com/ultralytics/yolov5/tree/master/models)** are downloaded\n",
        "automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases)\n",
        "- **[Datasets](https://github.com/ultralytics/yolov5/tree/master/data)** available for autodownload include: [COCO](https://github.com/ultralytics/yolov5/blob/master/data/coco.yaml), [COCO128](https://github.com/ultralytics/yolov5/blob/master/data/coco128.yaml), [VOC](https://github.com/ultralytics/yolov5/blob/master/data/VOC.yaml), [Argoverse](https://github.com/ultralytics/yolov5/blob/master/data/Argoverse.yaml), [VisDrone](https://github.com/ultralytics/yolov5/blob/master/data/VisDrone.yaml), [GlobalWheat](https://github.com/ultralytics/yolov5/blob/master/data/GlobalWheat2020.yaml), [xView](https://github.com/ultralytics/yolov5/blob/master/data/xView.yaml), [Objects365](https://github.com/ultralytics/yolov5/blob/master/data/Objects365.yaml), [SKU-110K](https://github.com/ultralytics/yolov5/blob/master/data/SKU-110K.yaml).\n",
        "- **Training Results** are saved to `runs/train/` with incrementing run directories, i.e. `runs/train/exp2`, `runs/train/exp3` etc.\n",
        "<br><br>\n",
        "\n",
        "A **Mosaic Dataloader** is used for training which combines 4 images into 1 mosaic.\n",
        "\n",
        "## Train on Custom Data with Roboflow 🌟 NEW\n",
        "\n",
        "[Roboflow](https://roboflow.com/?ref=ultralytics) enables you to easily **organize, label, and prepare** a high quality dataset with your own custom data. Roboflow also makes it easy to establish an active learning pipeline, collaborate with your team on dataset improvement, and integrate directly into your model building workflow with the `roboflow` pip package.\n",
        "\n",
        "- Custom Training Example: [https://blog.roboflow.com/how-to-train-yolov5-on-a-custom-dataset/](https://blog.roboflow.com/how-to-train-yolov5-on-a-custom-dataset/?ref=ultralytics)\n",
        "- Custom Training Notebook: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/roboflow-ai/yolov5-custom-training-tutorial/blob/main/yolov5-custom-training.ipynb)\n",
        "<br>\n",
        "\n",
        "<p align=\"\"><a href=\"https://roboflow.com/?ref=ultralytics\"><img width=\"480\" src=\"https://uploads-ssl.webflow.com/5f6bc60e665f54545a1e52a5/6152a275ad4b4ac20cd2e21a_roboflow-annotate.gif\"/></a></p>Label images lightning fast (including with model-assisted labeling)"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#@title Select YOLOv5 🚀 logger {run: 'auto'}\n",
        "logger = 'TensorBoard' #@param ['TensorBoard', 'ClearML', 'W&B']\n",
        "\n",
        "if logger == 'TensorBoard':\n",
        "  %load_ext tensorboard\n",
        "  %tensorboard --logdir runs/train\n",
        "elif logger == 'ClearML':\n",
        "  %pip install -q clearml && clearml-init\n",
        "elif logger == 'W&B':\n",
        "  %pip install -q wandb\n",
        "  import wandb; wandb.login()"
      ],
      "metadata": {
        "id": "i3oKtE4g-aNn"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "1NcFxRcFdJ_O",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "f0ce0354-7f50-4546-f3f9-672b4b522d59"
      },
      "source": [
        "# Train YOLOv5s on COCO128 for 3 epochs\n",
        "!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[34m\u001b[1mtrain: \u001b[0mweights=yolov5s.pt, cfg=, data=coco128.yaml, hyp=data/hyps/hyp.scratch-low.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, noplots=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, optimizer=SGD, sync_bn=False, workers=8, project=runs/train, name=exp, exist_ok=False, quad=False, cos_lr=False, label_smoothing=0.0, patience=100, freeze=[0], save_period=-1, seed=0, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest\n",
            "\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov5 ✅\n",
            "YOLOv5 🚀 v6.2-41-g8665d55 Python-3.7.13 torch-1.12.1+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
            "\n",
            "\u001b[34m\u001b[1mhyperparameters: \u001b[0mlr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0\n",
            "\u001b[34m\u001b[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs in Weights & Biases\n",
            "\u001b[34m\u001b[1mClearML: \u001b[0mrun 'pip install clearml' to automatically track, visualize and remotely train YOLOv5 🚀 in ClearML\n",
            "\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/\n",
            "\n",
            "Dataset not found ⚠️, missing paths ['/content/datasets/coco128/images/train2017']\n",
            "Downloading https://ultralytics.com/assets/coco128.zip to coco128.zip...\n",
            "100% 6.66M/6.66M [00:00<00:00, 76.7MB/s]\n",
            "Dataset download success ✅ (0.5s), saved to \u001b[1m/content/datasets\u001b[0m\n",
            "\n",
            "                 from  n    params  module                                  arguments                     \n",
            "  0                -1  1      3520  models.common.Conv                      [3, 32, 6, 2, 2]              \n",
            "  1                -1  1     18560  models.common.Conv                      [32, 64, 3, 2]                \n",
            "  2                -1  1     18816  models.common.C3                        [64, 64, 1]                   \n",
            "  3                -1  1     73984  models.common.Conv                      [64, 128, 3, 2]               \n",
            "  4                -1  2    115712  models.common.C3                        [128, 128, 2]                 \n",
            "  5                -1  1    295424  models.common.Conv                      [128, 256, 3, 2]              \n",
            "  6                -1  3    625152  models.common.C3                        [256, 256, 3]                 \n",
            "  7                -1  1   1180672  models.common.Conv                      [256, 512, 3, 2]              \n",
            "  8                -1  1   1182720  models.common.C3                        [512, 512, 1]                 \n",
            "  9                -1  1    656896  models.common.SPPF                      [512, 512, 5]                 \n",
            " 10                -1  1    131584  models.common.Conv                      [512, 256, 1, 1]              \n",
            " 11                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          \n",
            " 12           [-1, 6]  1         0  models.common.Concat                    [1]                           \n",
            " 13                -1  1    361984  models.common.C3                        [512, 256, 1, False]          \n",
            " 14                -1  1     33024  models.common.Conv                      [256, 128, 1, 1]              \n",
            " 15                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          \n",
            " 16           [-1, 4]  1         0  models.common.Concat                    [1]                           \n",
            " 17                -1  1     90880  models.common.C3                        [256, 128, 1, False]          \n",
            " 18                -1  1    147712  models.common.Conv                      [128, 128, 3, 2]              \n",
            " 19          [-1, 14]  1         0  models.common.Concat                    [1]                           \n",
            " 20                -1  1    296448  models.common.C3                        [256, 256, 1, False]          \n",
            " 21                -1  1    590336  models.common.Conv                      [256, 256, 3, 2]              \n",
            " 22          [-1, 10]  1         0  models.common.Concat                    [1]                           \n",
            " 23                -1  1   1182720  models.common.C3                        [512, 512, 1, False]          \n",
            " 24      [17, 20, 23]  1    229245  models.yolo.Detect                      [80, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]\n",
            "Model summary: 270 layers, 7235389 parameters, 7235389 gradients, 16.6 GFLOPs\n",
            "\n",
            "Transferred 349/349 items from yolov5s.pt\n",
            "\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n",
            "\u001b[34m\u001b[1moptimizer:\u001b[0m SGD(lr=0.01) with parameter groups 57 weight(decay=0.0), 60 weight(decay=0.0005), 60 bias\n",
            "\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01), CLAHE(p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8))\n",
            "\u001b[34m\u001b[1mtrain: \u001b[0mScanning '/content/datasets/coco128/labels/train2017' images and labels...128 found, 0 missing, 2 empty, 0 corrupt: 100% 128/128 [00:00<00:00, 7984.87it/s]\n",
            "\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /content/datasets/coco128/labels/train2017.cache\n",
            "\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 1018.19it/s]\n",
            "\u001b[34m\u001b[1mval: \u001b[0mScanning '/content/datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupt: 100% 128/128 [00:00<?, ?it/s]\n",
            "\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 246.87it/s]\n",
            "\n",
            "\u001b[34m\u001b[1mAutoAnchor: \u001b[0m4.27 anchors/target, 0.994 Best Possible Recall (BPR). Current anchors are a good fit to dataset ✅\n",
            "Plotting labels to runs/train/exp/labels.jpg... \n",
            "Image sizes 640 train, 640 val\n",
            "Using 8 dataloader workers\n",
            "Logging results to \u001b[1mruns/train/exp\u001b[0m\n",
            "Starting training for 3 epochs...\n",
            "\n",
            "      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size\n",
            "        0/2      3.77G    0.04529    0.06712    0.01835        323        640: 100% 8/8 [00:04<00:00,  1.96it/s]\n",
            "                 Class     Images  Instances          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00,  4.12it/s]\n",
            "                   all        128        929      0.647      0.611       0.68      0.449\n",
            "\n",
            "      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size\n",
            "        1/2      4.79G    0.04244    0.06423    0.01611        236        640: 100% 8/8 [00:00<00:00,  8.08it/s]\n",
            "                 Class     Images  Instances          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00,  4.43it/s]\n",
            "                   all        128        929      0.737      0.623       0.72      0.482\n",
            "\n",
            "      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size\n",
            "        2/2      4.79G    0.04695    0.06875     0.0173        189        640: 100% 8/8 [00:00<00:00,  8.87it/s]\n",
            "                 Class     Images  Instances          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00,  4.57it/s]\n",
            "                   all        128        929       0.76      0.631      0.733      0.497\n",
            "\n",
            "3 epochs completed in 0.003 hours.\n",
            "Optimizer stripped from runs/train/exp/weights/last.pt, 14.9MB\n",
            "Optimizer stripped from runs/train/exp/weights/best.pt, 14.9MB\n",
            "\n",
            "Validating runs/train/exp/weights/best.pt...\n",
            "Fusing layers... \n",
            "Model summary: 213 layers, 7225885 parameters, 0 gradients, 16.4 GFLOPs\n",
            "                 Class     Images  Instances          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00,  1.25it/s]\n",
            "                   all        128        929       0.76      0.631      0.733      0.497\n",
            "                person        128        254      0.872      0.699      0.807      0.533\n",
            "               bicycle        128          6      0.761      0.536      0.725      0.444\n",
            "                   car        128         46      0.771      0.413      0.553      0.242\n",
            "            motorcycle        128          5      0.795          1      0.928      0.592\n",
            "              airplane        128          6      0.983          1      0.995      0.689\n",
            "                   bus        128          7      0.648      0.714      0.755      0.691\n",
            "                 train        128          3          1      0.586      0.995      0.603\n",
            "                 truck        128         12      0.616      0.333      0.482      0.259\n",
            "                  boat        128          6      0.921      0.333      0.524      0.211\n",
            "         traffic light        128         14       0.76      0.229      0.374       0.21\n",
            "             stop sign        128          2      0.824          1      0.995      0.821\n",
            "                 bench        128          9      0.822      0.519      0.674      0.316\n",
            "                  bird        128         16      0.973          1      0.995        0.6\n",
            "                   cat        128          4      0.861          1      0.995      0.772\n",
            "                   dog        128          9          1      0.666       0.88      0.645\n",
            "                 horse        128          2      0.845          1      0.995      0.622\n",
            "              elephant        128         17      0.923      0.882       0.93      0.716\n",
            "                  bear        128          1       0.71          1      0.995      0.995\n",
            "                 zebra        128          4      0.866          1      0.995      0.922\n",
            "               giraffe        128          9      0.771      0.752      0.891      0.705\n",
            "              backpack        128          6      0.888        0.5      0.753      0.294\n",
            "              umbrella        128         18      0.876      0.784      0.899      0.539\n",
            "               handbag        128         19        0.8       0.21      0.335      0.181\n",
            "                   tie        128          7      0.798      0.714      0.787      0.478\n",
            "              suitcase        128          4      0.662          1      0.945      0.581\n",
            "               frisbee        128          5      0.727        0.8      0.759      0.701\n",
            "                  skis        128          1          0          0     0.0585     0.0139\n",
            "             snowboard        128          7      0.807      0.714      0.853      0.591\n",
            "           sports ball        128          6      0.649      0.667      0.602      0.307\n",
            "                  kite        128         10        0.7       0.47      0.543      0.212\n",
            "          baseball bat        128          4          1      0.496      0.544      0.208\n",
            "        baseball glove        128          7      0.619      0.429       0.47      0.313\n",
            "            skateboard        128          5      0.847        0.6      0.712      0.496\n",
            "         tennis racket        128          7      0.757      0.429      0.544       0.34\n",
            "                bottle        128         18      0.546      0.334       0.53      0.259\n",
            "            wine glass        128         16      0.716      0.875      0.907      0.528\n",
            "                   cup        128         36      0.826      0.639      0.802      0.538\n",
            "                  fork        128          6          1      0.329      0.496      0.364\n",
            "                 knife        128         16      0.706      0.625      0.604      0.382\n",
            "                 spoon        128         22      0.837      0.467      0.618       0.38\n",
            "                  bowl        128         28      0.757      0.607      0.714      0.519\n",
            "                banana        128          1      0.889          1      0.995      0.399\n",
            "              sandwich        128          2          1          0      0.638       0.56\n",
            "                orange        128          4          1      0.663      0.945      0.592\n",
            "              broccoli        128         11      0.545      0.437      0.471      0.351\n",
            "                carrot        128         24      0.701      0.585      0.697      0.454\n",
            "               hot dog        128          2      0.501          1      0.995      0.995\n",
            "                 pizza        128          5      0.809          1      0.962      0.747\n",
            "                 donut        128         14       0.66          1       0.96      0.837\n",
            "                  cake        128          4      0.871          1      0.995      0.822\n",
            "                 chair        128         35      0.536      0.561      0.595      0.325\n",
            "                 couch        128          6      0.931      0.667      0.828      0.539\n",
            "          potted plant        128         14      0.733      0.786      0.823      0.495\n",
            "                   bed        128          3      0.691      0.333       0.83      0.422\n",
            "          dining table        128         13      0.621      0.255      0.513       0.34\n",
            "                toilet        128          2      0.797          1      0.995      0.846\n",
            "                    tv        128          2       0.57          1      0.995      0.796\n",
            "                laptop        128          3          1          0      0.694      0.316\n",
            "                 mouse        128          2          1          0      0.172     0.0862\n",
            "                remote        128          8          1       0.62      0.634      0.551\n",
            "            cell phone        128          8      0.591      0.375      0.425      0.216\n",
            "             microwave        128          3      0.736          1      0.995      0.766\n",
            "                  oven        128          5      0.333        0.4      0.438      0.299\n",
            "                  sink        128          6      0.427      0.333      0.329       0.23\n",
            "          refrigerator        128          5      0.559        0.8      0.798      0.565\n",
            "                  book        128         29      0.558      0.241      0.307      0.155\n",
            "                 clock        128          9      0.761      0.889      0.888      0.711\n",
            "                  vase        128          2      0.287          1      0.995      0.895\n",
            "              scissors        128          1          1          0      0.497     0.0574\n",
            "            teddy bear        128         21      0.838      0.493      0.745      0.509\n",
            "            toothbrush        128          5      0.789          1      0.928       0.59\n",
            "Results saved to \u001b[1mruns/train/exp\u001b[0m\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "15glLzbQx5u0"
      },
      "source": [
        "# 4. Visualize"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ClearML Logging and Automation 🌟 NEW\n",
        "\n",
        "[ClearML](https://cutt.ly/yolov5-notebook-clearml) is completely integrated into YOLOv5 to track your experimentation, manage dataset versions and even remotely execute training runs. To enable ClearML (check cells above):\n",
        "\n",
        "- `pip install clearml`\n",
        "- run `clearml-init` to connect to a ClearML server (**deploy your own [open-source server](https://github.com/allegroai/clearml-server)**, or use our [free hosted server](https://cutt.ly/yolov5-notebook-clearml))\n",
        "\n",
        "You'll get all the great expected features from an experiment manager: live updates, model upload, experiment comparison etc. but ClearML also tracks uncommitted changes and installed packages for example. Thanks to that ClearML Tasks (which is what we call experiments) are also reproducible on different machines! With only 1 extra line, we can schedule a YOLOv5 training task on a queue to be executed by any number of ClearML Agents (workers).\n",
        "\n",
        "You can use ClearML Data to version your dataset and then pass it to YOLOv5 simply using its unique ID. This will help you keep track of your data without adding extra hassle. Explore the [ClearML Tutorial](https://github.com/ultralytics/yolov5/tree/master/utils/loggers/clearml) for details!\n",
        "\n",
        "<a href=\"https://cutt.ly/yolov5-notebook-clearml\">\n",
        "<img alt=\"ClearML Experiment Management UI\" src=\"https://github.com/thepycoder/clearml_screenshots/raw/main/scalars.jpg\" width=\"1280\"/></a>"
      ],
      "metadata": {
        "id": "Lay2WsTjNJzP"
      }
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "DLI1JmHU7B0l"
      },
      "source": [
        "## Weights & Biases Logging\n",
        "\n",
        "[Weights & Biases](https://wandb.ai/site?utm_campaign=repo_yolo_notebook) (W&B) is 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",
        "\n",
        "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",
        "\n",
        "<a href=\"https://wandb.ai/glenn-jocher/yolov5_tutorial\">\n",
        "<img alt=\"Weights & Biases dashboard\" src=\"https://user-images.githubusercontent.com/26833433/182482859-288a9622-4661-48db-99de-650d1dead5c6.jpg\" width=\"1280\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-WPvRbS5Swl6"
      },
      "source": [
        "## Local Logging\n",
        "\n",
        "Training results are automatically logged with [Tensorboard](https://www.tensorflow.org/tensorboard) and [CSV](https://github.com/ultralytics/yolov5/pull/4148) loggers to `runs/train`, with a new experiment directory created for each new training as `runs/train/exp2`, `runs/train/exp3`, etc.\n",
        "\n",
        "This directory contains train and val statistics, mosaics, labels, predictions and augmentated mosaics, as well as metrics and charts including precision-recall (PR) curves and confusion matrices. \n",
        "\n",
        "<img alt=\"Local logging results\" src=\"https://user-images.githubusercontent.com/26833433/183222430-e1abd1b7-782c-4cde-b04d-ad52926bf818.jpg\" width=\"1280\"/>\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Zelyeqbyt3GD"
      },
      "source": [
        "# Environments\n",
        "\n",
        "YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled):\n",
        "\n",
        "- **Google Colab and Kaggle** notebooks with free GPU: <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",
        "- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart)\n",
        "- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart)\n",
        "- **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) <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"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "6Qu7Iesl0p54"
      },
      "source": [
        "# Status\n",
        "\n",
        "![CI CPU testing](https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg)\n",
        "\n",
        "If this badge is green, all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training ([train.py](https://github.com/ultralytics/yolov5/blob/master/train.py)), testing ([val.py](https://github.com/ultralytics/yolov5/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov5/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov5/blob/master/export.py)) on macOS, Windows, and Ubuntu every 24 hours and on every commit.\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "IEijrePND_2I"
      },
      "source": [
        "# Appendix\n",
        "\n",
        "Additional content below for PyTorch Hub, CI, reproducing results, profiling speeds, VOC training, classification training and TensorRT example."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "GMusP4OAxFu6"
      },
      "source": [
        "import torch\n",
        "\n",
        "# PyTorch Hub Model\n",
        "model = torch.hub.load('ultralytics/yolov5', 'yolov5s')  # or yolov5n - yolov5x6, custom\n",
        "\n",
        "# Images\n",
        "img = 'https://ultralytics.com/images/zidane.jpg'  # or file, Path, PIL, OpenCV, numpy, list\n",
        "\n",
        "# Inference\n",
        "results = model(img)\n",
        "\n",
        "# Results\n",
        "results.print()  # or .show(), .save(), .crop(), .pandas(), etc."
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "FGH0ZjkGjejy"
      },
      "source": [
        "# YOLOv5 CI\n",
        "%%shell\n",
        "rm -rf runs  # remove runs/\n",
        "m=yolov5n  # official weights\n",
        "b=runs/train/exp/weights/best  # best.pt checkpoint\n",
        "python train.py --imgsz 64 --batch 32 --weights $m.pt --cfg $m.yaml --epochs 1 --device 0  # train\n",
        "for d in 0 cpu; do  # devices\n",
        "  for w in $m $b; do  # weights\n",
        "    python val.py --imgsz 64 --batch 32 --weights $w.pt --device $d  # val\n",
        "    python detect.py --imgsz 64 --weights $w.pt --device $d  # detect\n",
        "  done\n",
        "done\n",
        "python hubconf.py --model $m  # hub\n",
        "python models/tf.py --weights $m.pt  # build TF model\n",
        "python models/yolo.py --cfg $m.yaml  # build PyTorch model\n",
        "python export.py --weights $m.pt --img 64 --include torchscript  # export"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "mcKoSIK2WSzj"
      },
      "source": [
        "# Reproduce\n",
        "for x in (f'yolov5{x}' for x in 'nsmlx'):\n",
        "  !python val.py --weights {x}.pt --data coco.yaml --img 640 --task speed  # speed\n",
        "  !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.001 --iou 0.65  # mAP"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gogI-kwi3Tye"
      },
      "source": [
        "# Profile\n",
        "from utils.torch_utils import profile\n",
        "\n",
        "m1 = lambda x: x * torch.sigmoid(x)\n",
        "m2 = torch.nn.SiLU()\n",
        "results = profile(input=torch.randn(16, 3, 640, 640), ops=[m1, m2], n=100)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "BSgFCAcMbk1R"
      },
      "source": [
        "# VOC\n",
        "for b, m in zip([64, 64, 64, 32, 16], [f'yolov5{x}' for x in 'nsmlx']):  # batch, model\n",
        "  !python train.py --batch {b} --weights {m}.pt --data VOC.yaml --epochs 50 --img 512 --hyp hyp.VOC.yaml --project VOC --name {m} --cache"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Classification train\n",
        "for m in [*(f'yolov5{x}-cls.pt' for x in 'nsmlx'), 'resnet50.pt', 'resnet101.pt', 'efficientnet_b0.pt', 'efficientnet_b1.pt']:\n",
        "  for d in 'mnist', 'fashion-mnist', 'cifar10', 'cifar100', 'imagenette160', 'imagenette320', 'imagenette', 'imagewoof160', 'imagewoof320', 'imagewoof':\n",
        "    !python classify/train.py --model {m} --data {d} --epochs 10 --project YOLOv5-cls --name {m}-{d}"
      ],
      "metadata": {
        "id": "UWGH7H6yakVl"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Classification val\n",
        "!bash data/scripts/get_imagenet.sh --val  # download ImageNet val split (6.3G - 50000 images)\n",
        "!python classify/val.py --weights yolov5m-cls.pt --data ../datasets/imagenet --img 224  # validate"
      ],
      "metadata": {
        "id": "yYgOiFNHZx-1"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Validate on COCO test. Zip results.json and submit to eval server at https://competitions.codalab.org/competitions/20794\n",
        "!bash data/scripts/get_coco.sh --test  # download COCO test-dev2017 (7G - 40000 images, test 20000)\n",
        "!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half --task test"
      ],
      "metadata": {
        "id": "aq4DPWGu0Bl1"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "VTRwsvA9u7ln"
      },
      "source": [
        "# TensorRT \n",
        "!pip install -U nvidia-tensorrt --index-url https://pypi.ngc.nvidia.com  # install\n",
        "!python export.py --weights yolov5s.pt --include engine --imgsz 640 --device 0  # export\n",
        "!python detect.py --weights yolov5s.engine --imgsz 640 --device 0  # inference"
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}