yolov5/tutorial.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "YOLOv5 Tutorial",
      "provenance": [],
      "collapsed_sections": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU",
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "484511f272e64eab8b42e68dac5f7a66": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_78cceec059784f2bb36988d3336e4d56",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_ab93d8b65c134605934ff9ec5efb1bb6",
              "IPY_MODEL_30df865ded4c434191bce772c9a82f3a",
              "IPY_MODEL_20cdc61eb3404f42a12b37901b0d85fb"
            ]
          }
        },
        "78cceec059784f2bb36988d3336e4d56": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "ab93d8b65c134605934ff9ec5efb1bb6": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_2d7239993a9645b09b221405ac682743",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": "100%",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_17b5a87f92104ec7ab96bf507637d0d2"
          }
        },
        "30df865ded4c434191bce772c9a82f3a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_2358bfb2270247359e94b066b3cc3d1f",
            "_dom_classes": [],
            "description": "",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 818322941,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 818322941,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_3e984405db654b0b83b88b2db08baffd"
          }
        },
        "20cdc61eb3404f42a12b37901b0d85fb": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_654d8a19b9f949c6bbdaf8b0875c931e",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 780M/780M [00:33<00:00, 24.4MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_896030c5d13b415aaa05032818d81a6e"
          }
        },
        "2d7239993a9645b09b221405ac682743": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "17b5a87f92104ec7ab96bf507637d0d2": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "2358bfb2270247359e94b066b3cc3d1f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "3e984405db654b0b83b88b2db08baffd": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "654d8a19b9f949c6bbdaf8b0875c931e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "896030c5d13b415aaa05032818d81a6e": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        }
      }
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<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 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": "4d67116a-43e9-4d84-d19e-1edd83f23a04"
      },
      "source": [
        "!git clone https://github.com/ultralytics/yolov5  # clone repo\n",
        "%cd yolov5\n",
        "%pip install -qr requirements.txt  # install dependencies\n",
        "\n",
        "import torch\n",
        "from IPython.display import Image, clear_output  # to display images\n",
        "\n",
        "clear_output()\n",
        "print(f\"Setup complete. Using torch {torch.__version__} ({torch.cuda.get_device_properties(0).name if torch.cuda.is_available() else 'CPU'})\")"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Setup complete. Using torch 1.9.0+cu102 (Tesla V100-SXM2-16GB)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "4JnkELT0cIJg"
      },
      "source": [
        "# 1. Inference\n",
        "\n",
        "`detect.py` runs YOLOv5 inference on a variety of sources, downloading models automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases), and saving results to `runs/detect`. Example inference sources are:\n",
        "\n",
        "```shell\n",
        "python detect.py --source 0  # webcam\n",
        "                          file.jpg  # image \n",
        "                          file.mp4  # video\n",
        "                          path/  # directory\n",
        "                          path/*.jpg  # glob\n",
        "                          'https://youtu.be/NUsoVlDFqZg'  # YouTube\n",
        "                          'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream\n",
        "```"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "zR9ZbuQCH7FX",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "8b728908-81ab-4861-edb0-4d0c46c439fb"
      },
      "source": [
        "%rm -rf runs\n",
        "!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images/\n",
        "#Image(filename='runs/detect/exp/zidane.jpg', width=600)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov5s.pt'], source=data/images/, imgsz=640, conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False\n",
            "YOLOv5 🚀 v5.0-367-g01cdb76 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",
            "\n",
            "Fusing layers... \n",
            "Model Summary: 224 layers, 7266973 parameters, 0 gradients\n",
            "image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, 1 fire hydrant, Done. (0.007s)\n",
            "image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.007s)\n",
            "Results saved to \u001b[1mruns/detect/exp\u001b[0m\n",
            "Done. (0.091s)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "hkAzDWJ7cWTr"
      },
      "source": [
        "&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 [COCO](https://cocodataset.org/#home) val or test-dev datasets. Models are downloaded automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases). To show results by class use the `--verbose` flag. Note that `pycocotools` metrics may be ~1% better than the equivalent repo metrics, as is visible below, due to slight differences in mAP computation."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eyTZYGgRjnMc"
      },
      "source": [
        "## COCO val2017\n",
        "Download [COCO val 2017](https://github.com/ultralytics/yolov5/blob/74b34872fdf41941cddcf243951cdb090fbac17b/data/coco.yaml#L14) dataset (1GB - 5000 images), and test model accuracy."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "WQPtK1QYVaD_",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 48,
          "referenced_widgets": [
            "484511f272e64eab8b42e68dac5f7a66",
            "78cceec059784f2bb36988d3336e4d56",
            "ab93d8b65c134605934ff9ec5efb1bb6",
            "30df865ded4c434191bce772c9a82f3a",
            "20cdc61eb3404f42a12b37901b0d85fb",
            "2d7239993a9645b09b221405ac682743",
            "17b5a87f92104ec7ab96bf507637d0d2",
            "2358bfb2270247359e94b066b3cc3d1f",
            "3e984405db654b0b83b88b2db08baffd",
            "654d8a19b9f949c6bbdaf8b0875c931e",
            "896030c5d13b415aaa05032818d81a6e"
          ]
        },
        "outputId": "7e6f5c96-c819-43e1-cd03-d3b9878cf8de"
      },
      "source": [
        "# Download COCO val2017\n",
        "torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco2017val.zip', 'tmp.zip')\n",
        "!unzip -q tmp.zip -d ../datasets && rm tmp.zip"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "484511f272e64eab8b42e68dac5f7a66",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "  0%|          | 0.00/780M [00:00<?, ?B/s]"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "X58w8JLpMnjH",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "3dd0e2fc-aecf-4108-91b1-6392da1863cb"
      },
      "source": [
        "# Run YOLOv5x on COCO val2017\n",
        "!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\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",
            "YOLOv5 🚀 v5.0-367-g01cdb76 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",
            "\n",
            "Downloading https://github.com/ultralytics/yolov5/releases/download/v5.0/yolov5x.pt to yolov5x.pt...\n",
            "100% 168M/168M [00:08<00:00, 20.6MB/s]\n",
            "\n",
            "Fusing layers... \n",
            "Model Summary: 476 layers, 87730285 parameters, 0 gradients\n",
            "\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:01<00:00, 2749.96it/s]\n",
            "\u001b[34m\u001b[1mval: \u001b[0mNew cache created: ../datasets/coco/val2017.cache\n",
            "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 157/157 [01:08<00:00,  2.28it/s]\n",
            "                 all       5000      36335      0.746      0.626       0.68       0.49\n",
            "Speed: 0.1ms pre-process, 5.1ms inference, 1.6ms 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=0.46s)\n",
            "creating index...\n",
            "index created!\n",
            "Loading and preparing results...\n",
            "DONE (t=4.94s)\n",
            "creating index...\n",
            "index created!\n",
            "Running per image evaluation...\n",
            "Evaluate annotation type *bbox*\n",
            "DONE (t=83.60s).\n",
            "Accumulating evaluation results...\n",
            "DONE (t=13.22s).\n",
            " Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.504\n",
            " Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.688\n",
            " Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.546\n",
            " Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.351\n",
            " Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.551\n",
            " Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.644\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 ] = 0.629\n",
            " Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.681\n",
            " Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.524\n",
            " Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.735\n",
            " Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.827\n",
            "Results saved to \u001b[1mruns/val/exp\u001b[0m\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "rc_KbFk0juX2"
      },
      "source": [
        "## COCO test-dev2017\n",
        "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."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "V0AJnSeCIHyJ"
      },
      "source": [
        "# Download COCO test-dev2017\n",
        "torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco2017labels.zip', 'tmp.zip')\n",
        "!unzip -q tmp.zip -d ../ && rm tmp.zip # unzip labels\n",
        "!f=\"test2017.zip\" && curl http://images.cocodataset.org/zips/$f -o $f && unzip -q $f && rm $f  # 7GB,  41k images\n",
        "%mv ./test2017 ../coco/images  # move to /coco"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "29GJXAP_lPrt"
      },
      "source": [
        "# Run YOLOv5s on COCO test-dev2017 using --task test\n",
        "!python val.py --weights yolov5s.pt --data coco.yaml --task test"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "VUOiNLtMP5aG"
      },
      "source": [
        "# 3. Train\n",
        "\n",
        "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)."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Knxi2ncxWffW"
      },
      "source": [
        "# Download COCO128\n",
        "torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip', 'tmp.zip')\n",
        "!unzip -q tmp.zip -d ../datasets && rm tmp.zip"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "_pOkGLv1dMqh"
      },
      "source": [
        "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",
        "\n",
        "All training results are saved to `runs/train/` with incrementing run directories, i.e. `runs/train/exp2`, `runs/train/exp3` etc.\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bOy5KI2ncnWd"
      },
      "source": [
        "# Tensorboard  (optional)\n",
        "%load_ext tensorboard\n",
        "%tensorboard --logdir runs/train"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "2fLAV42oNb7M"
      },
      "source": [
        "# Weights & Biases  (optional)\n",
        "%pip install -q wandb\n",
        "import wandb\n",
        "wandb.login()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "1NcFxRcFdJ_O",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "00ea4b14-a75c-44a2-a913-03b431b69de5"
      },
      "source": [
        "# Train YOLOv5s on COCO128 for 3 epochs\n",
        "!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\u001b[34m\u001b[1mtrain: \u001b[0mweights=yolov5s.pt, cfg=, data=coco128.yaml, hyp=data/hyps/hyp.scratch.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, adam=False, sync_bn=False, workers=8, project=runs/train, entity=None, name=exp, exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, upload_dataset=False, bbox_interval=-1, save_period=-1, artifact_alias=latest, local_rank=-1, freeze=0\n",
            "\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov5 ✅\n",
            "YOLOv5 🚀 v5.0-367-g01cdb76 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",
            "\n",
            "\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",
            "\u001b[34m\u001b[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)\n",
            "\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/\n",
            "2021-08-15 14:40:43.449642: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudart.so.11.0\n",
            "\n",
            "                 from  n    params  module                                  arguments                     \n",
            "  0                -1  1      3520  models.common.Focus                     [3, 32, 3]                    \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  3    156928  models.common.C3                        [128, 128, 3]                 \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    656896  models.common.SPP                       [512, 512, [5, 9, 13]]        \n",
            "  9                -1  1   1182720  models.common.C3                        [512, 512, 1, False]          \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: 283 layers, 7276605 parameters, 7276605 gradients, 17.1 GFLOPs\n",
            "\n",
            "Transferred 362/362 items from yolov5s.pt\n",
            "Scaled weight_decay = 0.0005\n",
            "\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 59 weight, 62 weight (no decay), 62 bias\n",
            "\u001b[34m\u001b[1malbumentations: \u001b[0mversion 1.0.3 required by YOLOv5, but version 0.1.12 is currently installed\n",
            "\u001b[34m\u001b[1mtrain: \u001b[0mScanning '../datasets/coco128/labels/train2017' images and labels...128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<00:00, 2440.28it/s]\n",
            "\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: ../datasets/coco128/labels/train2017.cache\n",
            "\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 302.61it/s]\n",
            "\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<?, ?it/s]\n",
            "\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 142.55it/s]\n",
            "[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)\n",
            "[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)\n",
            "Plotting labels... \n",
            "\n",
            "\u001b[34m\u001b[1mautoanchor: \u001b[0mAnalyzing anchors... anchors/target = 4.27, Best Possible Recall (BPR) = 0.9935\n",
            "Image sizes 640 train, 640 val\n",
            "Using 2 dataloader workers\n",
            "Logging results to runs/train/exp\n",
            "Starting training for 3 epochs...\n",
            "\n",
            "     Epoch   gpu_mem       box       obj       cls    labels  img_size\n",
            "       0/2     3.64G   0.04492    0.0674   0.02213       298       640: 100% 8/8 [00:03<00:00,  2.05it/s]\n",
            "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00,  4.70it/s]\n",
            "                 all        128        929      0.686      0.565      0.642      0.421\n",
            "\n",
            "     Epoch   gpu_mem       box       obj       cls    labels  img_size\n",
            "       1/2     5.04G   0.04403    0.0611   0.01986       232       640: 100% 8/8 [00:01<00:00,  5.59it/s]\n",
            "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00,  4.46it/s]\n",
            "                 all        128        929      0.694      0.563      0.654      0.425\n",
            "\n",
            "     Epoch   gpu_mem       box       obj       cls    labels  img_size\n",
            "       2/2     5.04G   0.04616   0.07056   0.02071       214       640: 100% 8/8 [00:01<00:00,  5.94it/s]\n",
            "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00,  1.52it/s]\n",
            "                 all        128        929      0.711      0.562       0.66      0.431\n",
            "\n",
            "3 epochs completed in 0.005 hours.\n",
            "Optimizer stripped from runs/train/exp/weights/last.pt, 14.8MB\n",
            "Optimizer stripped from runs/train/exp/weights/best.pt, 14.8MB\n",
            "Results saved to \u001b[1mruns/train/exp\u001b[0m\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "15glLzbQx5u0"
      },
      "source": [
        "# 4. Visualize"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "DLI1JmHU7B0l"
      },
      "source": [
        "## Weights & Biases Logging 🌟 NEW\n",
        "\n",
        "[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",
        "\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",
        "<img align=\"left\" src=\"https://user-images.githubusercontent.com/26833433/125274843-a27bc600-e30e-11eb-9a44-62af0b7a50a2.png\" width=\"800\">"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-WPvRbS5Swl6"
      },
      "source": [
        "## Local Logging\n",
        "\n",
        "All results are logged by default to `runs/train`, with a new experiment directory created for each new training as `runs/train/exp2`, `runs/train/exp3`, etc. View train and val jpgs to see mosaics, labels, predictions and augmentation effects. Note an Ultralytics **Mosaic Dataloader** is used for training (shown below), which combines 4 images into 1 mosaic during training.\n",
        "\n",
        "> <img src=\"https://user-images.githubusercontent.com/26833433/131255960-b536647f-7c61-4f60-bbc5-cb2544d71b2a.jpg\" width=\"700\">  \n",
        "`train_batch0.jpg` shows train batch 0 mosaics and labels\n",
        "\n",
        "> <img src=\"https://user-images.githubusercontent.com/26833433/131256748-603cafc7-55d1-4e58-ab26-83657761aed9.jpg\" width=\"700\">  \n",
        "`test_batch0_labels.jpg` shows val batch 0 labels\n",
        "\n",
        "> <img src=\"https://user-images.githubusercontent.com/26833433/131256752-3f25d7a5-7b0f-4bb3-ab78-46343c3800fe.jpg\" width=\"700\">  \n",
        "`test_batch0_pred.jpg` shows val batch 0 _predictions_\n",
        "\n",
        "Training results are automatically logged to [Tensorboard](https://www.tensorflow.org/tensorboard) and [CSV](https://github.com/ultralytics/yolov5/pull/4148) as `results.csv`, which is plotted as `results.png` (below) after training completes. You can also plot any `results.csv` file manually:\n",
        "\n",
        "```python\n",
        "from utils.plots import plot_results \n",
        "plot_results('path/to/results.csv')  # plot 'results.csv' as 'results.png'\n",
        "```\n",
        "\n",
        "<img align=\"left\" width=\"800\" alt=\"COCO128 Training Results\" src=\"https://user-images.githubusercontent.com/26833433/126906780-8c5e2990-6116-4de6-b78a-367244a33ccf.png\">"
      ]
    },
    {
      "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",
        "Optional extras below. Unit tests validate repo functionality and should be run on any PRs submitted.\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "mcKoSIK2WSzj"
      },
      "source": [
        "# Reproduce\n",
        "for x in 'yolov5s', 'yolov5m', 'yolov5l', 'yolov5x':\n",
        "  !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.25 --iou 0.45  # speed\n",
        "  !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.001 --iou 0.65  # mAP"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "GMusP4OAxFu6"
      },
      "source": [
        "# PyTorch Hub\n",
        "import torch\n",
        "\n",
        "# Model\n",
        "model = torch.hub.load('ultralytics/yolov5', 'yolov5s')\n",
        "\n",
        "# Images\n",
        "dir = 'https://ultralytics.com/images/'\n",
        "imgs = [dir + f for f in ('zidane.jpg', 'bus.jpg')]  # batch of images\n",
        "\n",
        "# Inference\n",
        "results = model(imgs)\n",
        "results.print()  # or .show(), .save()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "FGH0ZjkGjejy"
      },
      "source": [
        "# Unit tests\n",
        "%%shell\n",
        "export PYTHONPATH=\"$PWD\"  # to run *.py. files in subdirectories\n",
        "\n",
        "rm -rf runs  # remove runs/\n",
        "for m in yolov5s; do  # models\n",
        "  python train.py --weights $m.pt --epochs 3 --img 320 --device 0  # train pretrained\n",
        "  python train.py --weights '' --cfg $m.yaml --epochs 3 --img 320 --device 0  # train scratch\n",
        "  for d in 0 cpu; do  # devices\n",
        "    python detect.py --weights $m.pt --device $d  # detect official\n",
        "    python detect.py --weights runs/train/exp/weights/best.pt --device $d  # detect custom\n",
        "    python val.py --weights $m.pt --device $d # val official\n",
        "    python val.py --weights runs/train/exp/weights/best.pt --device $d # val custom\n",
        "  done\n",
        "  python hubconf.py  # hub\n",
        "  python models/yolo.py --cfg $m.yaml  # inspect\n",
        "  python export.py --weights $m.pt --img 640 --batch 1  # export\n",
        "done"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gogI-kwi3Tye"
      },
      "source": [
        "# Profile\n",
        "from utils.torch_utils import profile\n",
        "\n",
        "m1 = lambda x: x * torch.sigmoid(x)\n",
        "m2 = torch.nn.SiLU()\n",
        "results = profile(input=torch.randn(16, 3, 640, 640), ops=[m1, m2], n=100)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RVRSOhEvUdb5"
      },
      "source": [
        "# Evolve\n",
        "!python train.py --img 640 --batch 64 --epochs 100 --data coco128.yaml --weights yolov5s.pt --cache --noautoanchor --evolve\n",
        "!d=runs/train/evolve && cp evolve.* $d && zip -r evolve.zip $d && gsutil mv evolve.zip gs://bucket  # upload results (optional)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "BSgFCAcMbk1R"
      },
      "source": [
        "# VOC\n",
        "for b, m in zip([64, 48, 32, 16], ['yolov5s', 'yolov5m', 'yolov5l', 'yolov5x']):  # zip(batch_size, model)\n",
        "  !python train.py --batch {b} --weights {m}.pt --data VOC.yaml --epochs 50 --cache --img 512 --nosave --hyp hyp.finetune.yaml --project VOC --name {m}"
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}