1054 lines
52 KiB
Plaintext
Vendored
1054 lines
52 KiB
Plaintext
Vendored
{
|
||
"nbformat": 4,
|
||
"nbformat_minor": 0,
|
||
"metadata": {
|
||
"colab": {
|
||
"name": "YOLOv3 Tutorial",
|
||
"provenance": [],
|
||
"include_colab_link": true
|
||
},
|
||
"kernelspec": {
|
||
"name": "python3",
|
||
"display_name": "Python 3"
|
||
},
|
||
"accelerator": "GPU",
|
||
"widgets": {
|
||
"application/vnd.jupyter.widget-state+json": {
|
||
"eeda9d6850e8406f9bbc5b06051b3710": {
|
||
"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_1e823c45174a4216be7234a6cc5cfd99",
|
||
"_model_module": "@jupyter-widgets/controls",
|
||
"children": [
|
||
"IPY_MODEL_cd8efd6c5de94ea8848a7d5b8766a4d6",
|
||
"IPY_MODEL_a4ec69c4697c4b0e84e6193be227f63e",
|
||
"IPY_MODEL_9a5694c133be46df8d2fe809b77c1c35"
|
||
]
|
||
}
|
||
},
|
||
"1e823c45174a4216be7234a6cc5cfd99": {
|
||
"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
|
||
}
|
||
},
|
||
"cd8efd6c5de94ea8848a7d5b8766a4d6": {
|
||
"model_module": "@jupyter-widgets/controls",
|
||
"model_name": "HTMLModel",
|
||
"model_module_version": "1.5.0",
|
||
"state": {
|
||
"_view_name": "HTMLView",
|
||
"style": "IPY_MODEL_d584167143f84a0484006dded3fd2620",
|
||
"_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_b9a25c0d425c4fe4b8cd51ae6a301b0d"
|
||
}
|
||
},
|
||
"a4ec69c4697c4b0e84e6193be227f63e": {
|
||
"model_module": "@jupyter-widgets/controls",
|
||
"model_name": "FloatProgressModel",
|
||
"model_module_version": "1.5.0",
|
||
"state": {
|
||
"_view_name": "ProgressView",
|
||
"style": "IPY_MODEL_654525fe1ed34d5fbe1c36ed80ae1c1c",
|
||
"_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_09544845070e47baafc5e37d45ff23e9"
|
||
}
|
||
},
|
||
"9a5694c133be46df8d2fe809b77c1c35": {
|
||
"model_module": "@jupyter-widgets/controls",
|
||
"model_name": "HTMLModel",
|
||
"model_module_version": "1.5.0",
|
||
"state": {
|
||
"_view_name": "HTMLView",
|
||
"style": "IPY_MODEL_1066f1d5b6104a3dae19f26269745bd0",
|
||
"_dom_classes": [],
|
||
"description": "",
|
||
"_model_name": "HTMLModel",
|
||
"placeholder": "",
|
||
"_view_module": "@jupyter-widgets/controls",
|
||
"_model_module_version": "1.5.0",
|
||
"value": " 780M/780M [00:03<00:00, 200MB/s]",
|
||
"_view_count": null,
|
||
"_view_module_version": "1.5.0",
|
||
"description_tooltip": null,
|
||
"_model_module": "@jupyter-widgets/controls",
|
||
"layout": "IPY_MODEL_dd3a70e1ef4547ec8d3463749ce06285"
|
||
}
|
||
},
|
||
"d584167143f84a0484006dded3fd2620": {
|
||
"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"
|
||
}
|
||
},
|
||
"b9a25c0d425c4fe4b8cd51ae6a301b0d": {
|
||
"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
|
||
}
|
||
},
|
||
"654525fe1ed34d5fbe1c36ed80ae1c1c": {
|
||
"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"
|
||
}
|
||
},
|
||
"09544845070e47baafc5e37d45ff23e9": {
|
||
"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
|
||
}
|
||
},
|
||
"1066f1d5b6104a3dae19f26269745bd0": {
|
||
"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"
|
||
}
|
||
},
|
||
"dd3a70e1ef4547ec8d3463749ce06285": {
|
||
"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/yolov3/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/yolov3\" target=\"_blank\">\n",
|
||
"<img width=\"1024\", src=\"https://user-images.githubusercontent.com/26833433/99805971-90f66b80-2b3d-11eb-80eb-8b45a15cb68e.jpg\"></a>\n",
|
||
"\n",
|
||
"This is the **official YOLOv3 🚀 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/yolov3 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": "141002fc-fe49-48d2-a575-2555bf903413"
|
||
},
|
||
"source": [
|
||
"!git clone https://github.com/ultralytics/yolov3 # clone\n",
|
||
"%cd yolov3\n",
|
||
"%pip install -qr requirements.txt # install\n",
|
||
"\n",
|
||
"import torch\n",
|
||
"from yolov3 import utils\n",
|
||
"display = utils.notebook_init() # checks"
|
||
],
|
||
"execution_count": 1,
|
||
"outputs": [
|
||
{
|
||
"output_type": "stream",
|
||
"name": "stdout",
|
||
"text": [
|
||
"Setup complete ✅\n"
|
||
]
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {
|
||
"id": "4JnkELT0cIJg"
|
||
},
|
||
"source": [
|
||
"# 1. Inference\n",
|
||
"\n",
|
||
"`detect.py` runs YOLOv3 inference on a variety of sources, downloading models automatically from the [latest YOLOv3 release](https://github.com/ultralytics/yolov3/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": "c29b082a-8e56-4799-b32a-056425f130d1"
|
||
},
|
||
"source": [
|
||
"!python detect.py --weights yolov3.pt --img 640 --conf 0.25 --source data/images\n",
|
||
"# display.Image(filename='runs/detect/exp/zidane.jpg', width=600)"
|
||
],
|
||
"execution_count": 4,
|
||
"outputs": [
|
||
{
|
||
"output_type": "stream",
|
||
"name": "stdout",
|
||
"text": [
|
||
"\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov3.pt'], source=data/images, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False\n",
|
||
"YOLOv3 🚀 v9.6.0-29-ga441ab1 torch 1.13.0+cu116 CUDA:0 (Tesla T4, 15110MiB)\n",
|
||
"\n",
|
||
"Fusing layers... \n",
|
||
"Model Summary: 261 layers, 61922845 parameters, 0 gradients\n",
|
||
"image 1/2 /content/yolov3/data/images/bus.jpg: 640x480 4 persons, 1 bicycle, 1 bus, Done. (0.050s)\n",
|
||
"image 2/2 /content/yolov3/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.038s)\n",
|
||
"Speed: 0.5ms pre-process, 44.3ms inference, 1.3ms NMS per image at shape (1, 3, 640, 640)\n",
|
||
"Results saved to \u001b[1mruns/detect/exp2\u001b[0m\n"
|
||
]
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {
|
||
"id": "hkAzDWJ7cWTr"
|
||
},
|
||
"source": [
|
||
" \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 YOLOv3 release](https://github.com/ultralytics/yolov3/releases). To show results by class use the `--verbose` flag. Note that `pycocotools` metrics may be ~1% better than the equivalent repo metrics, as is visible below, due to slight differences in mAP computation."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {
|
||
"id": "eyTZYGgRjnMc"
|
||
},
|
||
"source": [
|
||
"## COCO val\n",
|
||
"Download [COCO val 2017](https://github.com/ultralytics/yolov3/blob/master/data/coco.yaml) dataset (1GB - 5000 images), and test model accuracy."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"metadata": {
|
||
"id": "WQPtK1QYVaD_",
|
||
"colab": {
|
||
"base_uri": "https://localhost:8080/",
|
||
"height": 48,
|
||
"referenced_widgets": [
|
||
"eeda9d6850e8406f9bbc5b06051b3710",
|
||
"1e823c45174a4216be7234a6cc5cfd99",
|
||
"cd8efd6c5de94ea8848a7d5b8766a4d6",
|
||
"a4ec69c4697c4b0e84e6193be227f63e",
|
||
"9a5694c133be46df8d2fe809b77c1c35",
|
||
"d584167143f84a0484006dded3fd2620",
|
||
"b9a25c0d425c4fe4b8cd51ae6a301b0d",
|
||
"654525fe1ed34d5fbe1c36ed80ae1c1c",
|
||
"09544845070e47baafc5e37d45ff23e9",
|
||
"1066f1d5b6104a3dae19f26269745bd0",
|
||
"dd3a70e1ef4547ec8d3463749ce06285"
|
||
]
|
||
},
|
||
"outputId": "56199bac-5a5e-41eb-8892-bf387a1ec7cb"
|
||
},
|
||
"source": [
|
||
"# Download COCO val\n",
|
||
"torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017val.zip', 'tmp.zip')\n",
|
||
"!unzip -q tmp.zip -d ../datasets && rm tmp.zip"
|
||
],
|
||
"execution_count": null,
|
||
"outputs": [
|
||
{
|
||
"output_type": "display_data",
|
||
"data": {
|
||
"application/vnd.jupyter.widget-view+json": {
|
||
"model_id": "eeda9d6850e8406f9bbc5b06051b3710",
|
||
"version_minor": 0,
|
||
"version_major": 2
|
||
},
|
||
"text/plain": [
|
||
" 0%| | 0.00/780M [00:00<?, ?B/s]"
|
||
]
|
||
},
|
||
"metadata": {}
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"metadata": {
|
||
"id": "X58w8JLpMnjH",
|
||
"colab": {
|
||
"base_uri": "https://localhost:8080/"
|
||
},
|
||
"outputId": "15c92efb-05ec-48e0-b9ef-ff34871354c8"
|
||
},
|
||
"source": [
|
||
"# Run YOLOv3 on COCO val\n",
|
||
"!python val.py --weights yolov3.pt --data coco.yaml --img 640 --iou 0.65 --half"
|
||
],
|
||
"execution_count": null,
|
||
"outputs": [
|
||
{
|
||
"output_type": "stream",
|
||
"name": "stdout",
|
||
"text": [
|
||
"\u001b[34m\u001b[1mval: \u001b[0mdata=/content/yolov3/data/coco.yaml, weights=['yolov3.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, dnn=False\n",
|
||
"YOLOv3 🚀 v9.6.0-1-g93a2bcc torch 1.10.0+cu111 CUDA:0 (A100-SXM4-40GB, 40536MiB)\n",
|
||
"\n",
|
||
"Fusing layers... \n",
|
||
"Model Summary: 261 layers, 61922845 parameters, 0 gradients, 156.1 GFLOPs\n",
|
||
"\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco/val2017.cache' images and labels... 4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:00<?, ?it/s]\n",
|
||
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [00:45<00:00, 3.45it/s]\n",
|
||
" all 5000 36335 0.71 0.602 0.649 0.453\n",
|
||
"Speed: 0.1ms pre-process, 2.1ms inference, 1.5ms NMS per image at shape (32, 3, 640, 640)\n",
|
||
"\n",
|
||
"Evaluating pycocotools mAP... saving runs/val/exp/yolov3_predictions.json...\n",
|
||
"loading annotations into memory...\n",
|
||
"Done (t=0.44s)\n",
|
||
"creating index...\n",
|
||
"index created!\n",
|
||
"Loading and preparing results...\n",
|
||
"DONE (t=4.99s)\n",
|
||
"creating index...\n",
|
||
"index created!\n",
|
||
"Running per image evaluation...\n",
|
||
"Evaluate annotation type *bbox*\n",
|
||
"DONE (t=91.45s).\n",
|
||
"Accumulating evaluation results...\n",
|
||
"DONE (t=15.18s).\n",
|
||
" Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.464\n",
|
||
" Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.655\n",
|
||
" Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.507\n",
|
||
" Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.298\n",
|
||
" Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.515\n",
|
||
" Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.585\n",
|
||
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.359\n",
|
||
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.594\n",
|
||
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.649\n",
|
||
" Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.476\n",
|
||
" Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.698\n",
|
||
" Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.779\n",
|
||
"Results saved to \u001b[1mruns/val/exp\u001b[0m\n"
|
||
]
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {
|
||
"id": "rc_KbFk0juX2"
|
||
},
|
||
"source": [
|
||
"## COCO test\n",
|
||
"Download [COCO test2017](https://github.com/ultralytics/yolov3/blob/master/data/coco.yaml) 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://ultralytics.com/assets/coco2017labels.zip', 'tmp.zip')\n",
|
||
"!unzip -q tmp.zip -d ../datasets && rm tmp.zip\n",
|
||
"!f=\"test2017.zip\" && curl http://images.cocodataset.org/zips/$f -o $f && unzip -q $f -d ../datasets/coco/images"
|
||
],
|
||
"execution_count": null,
|
||
"outputs": []
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"metadata": {
|
||
"id": "29GJXAP_lPrt"
|
||
},
|
||
"source": [
|
||
"# Run YOLOv3 on COCO test\n",
|
||
"!python val.py --weights yolov3.pt --data coco.yaml --img 640 --iou 0.65 --half --task test"
|
||
],
|
||
"execution_count": null,
|
||
"outputs": []
|
||
},
|
||
{
|
||
"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 YOLOv3 model on the [COCO128](https://www.kaggle.com/ultralytics/coco128) dataset with `--data coco128.yaml`, starting from pretrained `--weights yolov3.pt`, or from randomly initialized `--weights '' --cfg yolov3yaml`.\n",
|
||
"\n",
|
||
"- **Pretrained [Models](https://github.com/ultralytics/yolov3/tree/master/models)** are downloaded\n",
|
||
"automatically from the [latest YOLOv3 release](https://github.com/ultralytics/yolov3/releases)\n",
|
||
"- **[Datasets](https://github.com/ultralytics/yolov3/tree/master/data)** available for autodownload include: [COCO](https://github.com/ultralytics/yolov3/blob/master/data/coco.yaml), [COCO128](https://github.com/ultralytics/yolov3/blob/master/data/coco128.yaml), [VOC](https://github.com/ultralytics/yolov3/blob/master/data/VOC.yaml), [Argoverse](https://github.com/ultralytics/yolov3/blob/master/data/Argoverse.yaml), [VisDrone](https://github.com/ultralytics/yolov3/blob/master/data/VisDrone.yaml), [GlobalWheat](https://github.com/ultralytics/yolov3/blob/master/data/GlobalWheat2020.yaml), [xView](https://github.com/ultralytics/yolov3/blob/master/data/xView.yaml), [Objects365](https://github.com/ultralytics/yolov3/blob/master/data/Objects365.yaml), [SKU-110K](https://github.com/ultralytics/yolov3/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"
|
||
]
|
||
},
|
||
{
|
||
"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": "1NcFxRcFdJ_O",
|
||
"colab": {
|
||
"base_uri": "https://localhost:8080/"
|
||
},
|
||
"outputId": "c77013e3-347d-42a4-84de-3ca42ea3aee9"
|
||
},
|
||
"source": [
|
||
"# Train YOLOv3 on COCO128 for 3 epochs\n",
|
||
"!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov3.pt --cache"
|
||
],
|
||
"execution_count": 3,
|
||
"outputs": [
|
||
{
|
||
"output_type": "stream",
|
||
"name": "stdout",
|
||
"text": [
|
||
"\u001b[34m\u001b[1mtrain: \u001b[0mweights=yolov3.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, name=exp, exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, patience=100, freeze=0, save_period=-1, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest\n",
|
||
"\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov3 ✅\n",
|
||
"YOLOv3 🚀 v9.6.0-29-ga441ab1 torch 1.13.0+cu116 CUDA:0 (Tesla T4, 15110MiB)\n",
|
||
"\n",
|
||
"\u001b[34m\u001b[1mhyperparameters: \u001b[0mlr0=0.01, lrf=0.1, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0\n",
|
||
"\u001b[34m\u001b[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv3 🚀 runs (RECOMMENDED)\n",
|
||
"\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/\n",
|
||
"\n",
|
||
"WARNING: Dataset not found, nonexistent 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, 10.2MB/s]\n",
|
||
"Dataset autodownload success, saved to ../datasets\n",
|
||
"\n",
|
||
"\n",
|
||
" from n params module arguments \n",
|
||
" 0 -1 1 928 models.common.Conv [3, 32, 3, 1] \n",
|
||
" 1 -1 1 18560 models.common.Conv [32, 64, 3, 2] \n",
|
||
" 2 -1 1 20672 models.common.Bottleneck [64, 64] \n",
|
||
" 3 -1 1 73984 models.common.Conv [64, 128, 3, 2] \n",
|
||
" 4 -1 2 164608 models.common.Bottleneck [128, 128] \n",
|
||
" 5 -1 1 295424 models.common.Conv [128, 256, 3, 2] \n",
|
||
" 6 -1 8 2627584 models.common.Bottleneck [256, 256] \n",
|
||
" 7 -1 1 1180672 models.common.Conv [256, 512, 3, 2] \n",
|
||
" 8 -1 8 10498048 models.common.Bottleneck [512, 512] \n",
|
||
" 9 -1 1 4720640 models.common.Conv [512, 1024, 3, 2] \n",
|
||
" 10 -1 4 20983808 models.common.Bottleneck [1024, 1024] \n",
|
||
" 11 -1 1 5245952 models.common.Bottleneck [1024, 1024, False] \n",
|
||
" 12 -1 1 525312 models.common.Conv [1024, 512, 1, 1] \n",
|
||
" 13 -1 1 4720640 models.common.Conv [512, 1024, 3, 1] \n",
|
||
" 14 -1 1 525312 models.common.Conv [1024, 512, 1, 1] \n",
|
||
" 15 -1 1 4720640 models.common.Conv [512, 1024, 3, 1] \n",
|
||
" 16 -2 1 131584 models.common.Conv [512, 256, 1, 1] \n",
|
||
" 17 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n",
|
||
" 18 [-1, 8] 1 0 models.common.Concat [1] \n",
|
||
" 19 -1 1 1377792 models.common.Bottleneck [768, 512, False] \n",
|
||
" 20 -1 1 1312256 models.common.Bottleneck [512, 512, False] \n",
|
||
" 21 -1 1 131584 models.common.Conv [512, 256, 1, 1] \n",
|
||
" 22 -1 1 1180672 models.common.Conv [256, 512, 3, 1] \n",
|
||
" 23 -2 1 33024 models.common.Conv [256, 128, 1, 1] \n",
|
||
" 24 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n",
|
||
" 25 [-1, 6] 1 0 models.common.Concat [1] \n",
|
||
" 26 -1 1 344832 models.common.Bottleneck [384, 256, False] \n",
|
||
" 27 -1 2 656896 models.common.Bottleneck [256, 256, False] \n",
|
||
" 28 [27, 22, 15] 1 457725 models.yolo.Detect [80, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [256, 512, 1024]]\n",
|
||
"Model Summary: 333 layers, 61949149 parameters, 61949149 gradients, 156.6 GFLOPs\n",
|
||
"\n",
|
||
"Transferred 439/439 items from yolov3.pt\n",
|
||
"Scaled weight_decay = 0.0005\n",
|
||
"\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 72 weight, 75 weight (no decay), 75 bias\n",
|
||
"\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(always_apply=False, p=0.01, blur_limit=(3, 7)), MedianBlur(always_apply=False, p=0.01, blur_limit=(3, 7)), ToGray(always_apply=False, p=0.01), CLAHE(always_apply=False, p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8))\n",
|
||
"\u001b[34m\u001b[1mtrain: \u001b[0mScanning '../datasets/coco128/labels/train2017' images and labels...126 found, 2 missing, 0 empty, 0 corrupted: 100% 128/128 [00:00<00:00, 1542.80it/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, 327.35it/s]\n",
|
||
"\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco128/labels/train2017.cache' images and labels... 126 found, 2 missing, 0 empty, 0 corrupted: 100% 128/128 [00:00<?, ?it/s]\n",
|
||
"\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:01<00:00, 124.89it/s]\n",
|
||
"Plotting labels to runs/train/exp/labels.jpg... \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",
|
||
"Image sizes 640 train, 640 val\n",
|
||
"Using 2 dataloader workers\n",
|
||
"Logging results to \u001b[1mruns/train/exp\u001b[0m\n",
|
||
"Starting training for 3 epochs...\n",
|
||
"\n",
|
||
" Epoch gpu_mem box obj cls labels img_size\n",
|
||
" 0/2 11.9G 0.03646 0.05139 0.01218 170 640: 100% 8/8 [00:11<00:00, 1.41s/it]\n",
|
||
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.18it/s]\n",
|
||
" all 128 929 0.701 0.771 0.81 0.578\n",
|
||
"\n",
|
||
" Epoch gpu_mem box obj cls labels img_size\n",
|
||
" 1/2 10.7G 0.03638 0.05337 0.01048 204 640: 100% 8/8 [00:06<00:00, 1.28it/s]\n",
|
||
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.94it/s]\n",
|
||
" all 128 929 0.708 0.774 0.814 0.58\n",
|
||
"\n",
|
||
" Epoch gpu_mem box obj cls labels img_size\n",
|
||
" 2/2 12.1G 0.03671 0.05941 0.01124 281 640: 100% 8/8 [00:06<00:00, 1.26it/s]\n",
|
||
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.91it/s]\n",
|
||
" all 128 929 0.706 0.776 0.816 0.583\n",
|
||
"\n",
|
||
"3 epochs completed in 0.012 hours.\n",
|
||
"Optimizer stripped from runs/train/exp/weights/last.pt, 124.4MB\n",
|
||
"Optimizer stripped from runs/train/exp/weights/best.pt, 124.4MB\n",
|
||
"\n",
|
||
"Validating runs/train/exp/weights/best.pt...\n",
|
||
"Fusing layers... \n",
|
||
"Model Summary: 261 layers, 61922845 parameters, 0 gradients, 155.9 GFLOPs\n",
|
||
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:04<00:00, 1.11s/it]\n",
|
||
" all 128 929 0.733 0.755 0.814 0.583\n",
|
||
" person 128 254 0.827 0.803 0.861 0.627\n",
|
||
" bicycle 128 6 0.534 0.58 0.586 0.386\n",
|
||
" car 128 46 0.847 0.565 0.688 0.331\n",
|
||
" motorcycle 128 5 0.776 1 0.995 0.817\n",
|
||
" airplane 128 6 0.915 1 0.995 0.837\n",
|
||
" bus 128 7 1 0.764 0.978 0.817\n",
|
||
" train 128 3 0.844 1 0.995 0.797\n",
|
||
" truck 128 12 0.644 0.583 0.649 0.417\n",
|
||
" boat 128 6 0.6 0.501 0.695 0.493\n",
|
||
" traffic light 128 14 0.854 0.429 0.539 0.276\n",
|
||
" stop sign 128 2 0.723 1 0.995 0.796\n",
|
||
" bench 128 9 1 0.657 0.796 0.369\n",
|
||
" bird 128 16 0.962 1 0.995 0.672\n",
|
||
" cat 128 4 0.751 1 0.995 0.933\n",
|
||
" dog 128 9 0.773 1 0.955 0.746\n",
|
||
" horse 128 2 0.638 1 0.995 0.623\n",
|
||
" elephant 128 17 0.995 0.941 0.947 0.782\n",
|
||
" bear 128 1 0.604 1 0.995 0.895\n",
|
||
" zebra 128 4 0.863 1 0.995 0.946\n",
|
||
" giraffe 128 9 0.962 1 0.995 0.822\n",
|
||
" backpack 128 6 0.874 0.667 0.714 0.486\n",
|
||
" umbrella 128 18 0.792 0.833 0.867 0.564\n",
|
||
" handbag 128 19 0.644 0.526 0.544 0.359\n",
|
||
" tie 128 7 0.872 0.857 0.858 0.604\n",
|
||
" suitcase 128 4 0.61 1 0.995 0.672\n",
|
||
" frisbee 128 5 0.717 0.8 0.76 0.61\n",
|
||
" skis 128 1 0.672 1 0.995 0.597\n",
|
||
" snowboard 128 7 0.852 0.829 0.873 0.632\n",
|
||
" sports ball 128 6 0.766 0.833 0.78 0.559\n",
|
||
" kite 128 10 0.377 0.6 0.57 0.172\n",
|
||
" baseball bat 128 4 0.637 0.888 0.912 0.365\n",
|
||
" baseball glove 128 7 0.512 0.571 0.597 0.428\n",
|
||
" skateboard 128 5 0.625 0.8 0.803 0.427\n",
|
||
" tennis racket 128 7 0.776 0.714 0.718 0.36\n",
|
||
" bottle 128 18 0.744 0.889 0.741 0.482\n",
|
||
" wine glass 128 16 0.82 0.688 0.888 0.494\n",
|
||
" cup 128 36 0.801 0.889 0.884 0.628\n",
|
||
" fork 128 6 0.565 0.5 0.596 0.418\n",
|
||
" knife 128 16 0.829 0.812 0.822 0.519\n",
|
||
" spoon 128 22 0.593 0.5 0.583 0.397\n",
|
||
" bowl 128 28 0.869 0.75 0.798 0.635\n",
|
||
" banana 128 1 0.694 1 0.995 0.895\n",
|
||
" sandwich 128 2 0 0 0.497 0.202\n",
|
||
" orange 128 4 1 0.679 0.888 0.691\n",
|
||
" broccoli 128 11 0.449 0.364 0.469 0.353\n",
|
||
" carrot 128 24 0.727 0.777 0.814 0.526\n",
|
||
" hot dog 128 2 0.56 1 0.828 0.828\n",
|
||
" pizza 128 5 0.722 1 0.962 0.689\n",
|
||
" donut 128 14 0.716 1 0.973 0.875\n",
|
||
" cake 128 4 0.714 1 0.995 0.871\n",
|
||
" chair 128 35 0.65 0.857 0.856 0.546\n",
|
||
" couch 128 6 0.983 0.833 0.899 0.583\n",
|
||
" potted plant 128 14 0.832 0.857 0.92 0.567\n",
|
||
" bed 128 3 0.474 0.316 0.608 0.487\n",
|
||
" dining table 128 13 0.663 0.615 0.666 0.4\n",
|
||
" toilet 128 2 0.744 1 0.995 0.896\n",
|
||
" tv 128 2 0.685 1 0.995 0.846\n",
|
||
" laptop 128 3 1 0 0.913 0.445\n",
|
||
" mouse 128 2 0.962 0.5 0.745 0.35\n",
|
||
" remote 128 8 0.856 0.625 0.712 0.581\n",
|
||
" cell phone 128 8 0.598 0.5 0.637 0.386\n",
|
||
" microwave 128 3 0.723 1 0.995 0.852\n",
|
||
" oven 128 5 0.556 0.6 0.499 0.379\n",
|
||
" sink 128 6 0.549 0.416 0.528 0.31\n",
|
||
" refrigerator 128 5 0.6 0.8 0.845 0.587\n",
|
||
" book 128 29 0.552 0.276 0.411 0.216\n",
|
||
" clock 128 9 0.731 1 0.975 0.798\n",
|
||
" vase 128 2 0.588 1 0.995 0.995\n",
|
||
" scissors 128 1 1 0 0.332 0.0663\n",
|
||
" teddy bear 128 21 0.898 0.838 0.934 0.631\n",
|
||
" toothbrush 128 5 0.791 1 0.995 0.754\n",
|
||
"Results saved to \u001b[1mruns/train/exp\u001b[0m\n"
|
||
]
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {
|
||
"id": "15glLzbQx5u0"
|
||
},
|
||
"source": [
|
||
"# 4. Visualize"
|
||
]
|
||
},
|
||
{
|
||
"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",
|
||
"YOLOv3 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/yolov3/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/yolov3\"><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/yolov3/wiki/GCP-Quickstart)\n",
|
||
"- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov3/wiki/AWS-Quickstart)\n",
|
||
"- **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov3/wiki/Docker-Quickstart) <a href=\"https://hub.docker.com/r/ultralytics/yolov3\"><img src=\"https://img.shields.io/docker/pulls/ultralytics/yolov3?logo=docker\" alt=\"Docker Pulls\"></a>\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {
|
||
"id": "6Qu7Iesl0p54"
|
||
},
|
||
"source": [
|
||
"# Status\n",
|
||
"\n",
|
||
"\n",
|
||
"\n",
|
||
"If this badge is green, all [YOLOv3 GitHub Actions](https://github.com/ultralytics/yolov3/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv3 training ([train.py](https://github.com/ultralytics/yolov3/blob/master/train.py)), testing ([val.py](https://github.com/ultralytics/yolov3/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov3/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov3/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 'yolov3', 'yolov3-spp', 'yolov3-tiny':\n",
|
||
" !python val.py --weights {x}.pt --data coco.yaml --img 640 --task speed # speed\n",
|
||
" !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.001 --iou 0.65 # mAP"
|
||
],
|
||
"execution_count": null,
|
||
"outputs": []
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"metadata": {
|
||
"id": "GMusP4OAxFu6"
|
||
},
|
||
"source": [
|
||
"# PyTorch Hub\n",
|
||
"import torch\n",
|
||
"\n",
|
||
"# Model\n",
|
||
"model = torch.hub.load('ultralytics/yolov3', 'yolov3')\n",
|
||
"\n",
|
||
"# Images\n",
|
||
"dir = 'https://ultralytics.com/images/'\n",
|
||
"imgs = [dir + f for f in ('zidane.jpg', 'bus.jpg')] # batch of images\n",
|
||
"\n",
|
||
"# Inference\n",
|
||
"results = model(imgs)\n",
|
||
"results.print() # or .show(), .save()"
|
||
],
|
||
"execution_count": null,
|
||
"outputs": []
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"metadata": {
|
||
"id": "FGH0ZjkGjejy"
|
||
},
|
||
"source": [
|
||
"# CI Checks\n",
|
||
"%%shell\n",
|
||
"export PYTHONPATH=\"$PWD\" # to run *.py. files in subdirectories\n",
|
||
"rm -rf runs # remove runs/\n",
|
||
"for m in yolov3-tiny; do # models\n",
|
||
" python train.py --img 64 --batch 32 --weights $m.pt --epochs 1 --device 0 # train pretrained\n",
|
||
" python train.py --img 64 --batch 32 --weights '' --cfg $m.yaml --epochs 1 --device 0 # train scratch\n",
|
||
" for d in 0 cpu; do # devices\n",
|
||
" python val.py --weights $m.pt --device $d # val official\n",
|
||
" python val.py --weights runs/train/exp/weights/best.pt --device $d # val custom\n",
|
||
" python detect.py --weights $m.pt --device $d # detect official\n",
|
||
" python detect.py --weights runs/train/exp/weights/best.pt --device $d # detect custom\n",
|
||
" done\n",
|
||
" python hubconf.py # hub\n",
|
||
" python models/yolo.py --cfg $m.yaml # build PyTorch model\n",
|
||
" python models/tf.py --weights $m.pt # build TensorFlow model\n",
|
||
" python export.py --img 64 --batch 1 --weights $m.pt --include torchscript onnx # export\n",
|
||
"done"
|
||
],
|
||
"execution_count": null,
|
||
"outputs": []
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"metadata": {
|
||
"id": "gogI-kwi3Tye"
|
||
},
|
||
"source": [
|
||
"# Profile\n",
|
||
"from utils.torch_utils import profile\n",
|
||
"\n",
|
||
"m1 = lambda x: x * torch.sigmoid(x)\n",
|
||
"m2 = torch.nn.SiLU()\n",
|
||
"results = profile(input=torch.randn(16, 3, 640, 640), ops=[m1, m2], n=100)"
|
||
],
|
||
"execution_count": null,
|
||
"outputs": []
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"metadata": {
|
||
"id": "RVRSOhEvUdb5"
|
||
},
|
||
"source": [
|
||
"# Evolve\n",
|
||
"!python train.py --img 640 --batch 64 --epochs 100 --data coco128.yaml --weights yolov3.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([24, 24, 64], ['yolov3', 'yolov3-spp', 'yolov3-tiny']): # 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": []
|
||
}
|
||
]
|
||
}
|