You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

429 lines
17 KiB

{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "YOLOv8 Tutorial",
"provenance": [],
"toc_visible": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "t6MPjfT5NrKQ"
},
"source": [
"<div align=\"center\">\n",
"\n",
" <a href=\"https://ultralytics.com/yolov8\" target=\"_blank\">\n",
" <img width=\"1024\", src=\"https://raw.githubusercontent.com/ultralytics/assets/main/yolov8/banner-yolov8.png\"></a>\n",
"\n",
"\n",
"<br>\n",
" <a href=\"https://console.paperspace.com/github/ultralytics/ultralytics\"><img src=\"https://assets.paperspace.io/img/gradient-badge.svg\" alt=\"Run on Gradient\"/></a>\n",
" <a href=\"https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"></a>\n",
" <a href=\"https://www.kaggle.com/ultralytics/yolov8\"><img src=\"https://kaggle.com/static/images/open-in-kaggle.svg\" alt=\"Open In Kaggle\"></a>\n",
"<br>\n",
"\n",
"Welcome to the Ultralytics YOLOv8 🚀 notebook! <a href=\"https://github.com/ultralytics/ultralytics\">YOLOv8</a> is the latest version of the YOLO (You Only Look Once) object detection and image segmentation model developed by <a href=\"https://ultralytics.com\">Ultralytics</a>. This notebook serves as the starting point for exploring the various resources available to help you get started with YOLOv8 and understand its features and capabilities.\n",
"\n",
"The YOLOv8 models are designed to be fast, accurate, and easy to use, making them an excellent choice for a wide range of object detection and image segmentation tasks. They can be trained on large datasets and are capable of running on a variety of hardware platforms, from CPUs to GPUs.\n",
"\n",
"Whether you are a seasoned machine learning practitioner or new to the field, we hope that the resources in this notebook will help you get the most out of YOLOv8. Please feel free to browse the <a href=\"https://docs.ultralytics.com/\">YOLOv8 Docs</a> and reach out to us with any questions or feedback.\n",
"\n",
"</div>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "7mGmQbAO5pQb"
},
"source": [
"# Setup\n",
"\n",
"Pip install `ultralytics` and [dependencies](https://github.com/ultralytics/ultralytics/blob/main/requirements.txt) and check PyTorch and GPU."
]
},
{
"cell_type": "code",
"metadata": {
"id": "wbvMlHd_QwMG",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"outputId": "9012b4cd-53eb-4c84-f5b7-4976d4b4e58a"
},
"source": [
"# Pip install method (recommended)\n",
"%pip install ultralytics\n",
"import ultralytics\n",
"ultralytics.checks()"
],
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"Ultralytics YOLOv8.0.5 🚀 Python-3.8.16 torch-1.13.1+cu116 CUDA:0 (Tesla T4, 15110MiB)\n",
"Setup complete ✅ (2 CPUs, 12.7 GB RAM, 23.0/166.8 GB disk)\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Git clone method (for development)\n",
"!git clone https://github.com/ultralytics/ultralytics\n",
"%pip install -qe ultralytics"
],
"metadata": {
"id": "TUFPge7f_1ms"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "4JnkELT0cIJg"
},
"source": [
"# 1. Predict\n",
"\n",
"YOLOv8 may be used directly in the Command Line Interface (CLI) with a `yolo` command for a variety of tasks and modes and accepts additional arguments, i.e. `imgsz=640`. See a full list of available `yolo` [arguments](https://docs.ultralytics.com/config/) in the YOLOv8 [Docs](https://docs.ultralytics.com).\n"
]
},
{
"cell_type": "code",
"metadata": {
"id": "zR9ZbuQCH7FX",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "3136de6b-2995-4731-e84c-962acb233d89"
},
"source": [
"# Run inference on an image with YOLOv8n\n",
"!yolo task=detect mode=predict model=yolov8n.pt conf=0.25 source='https://ultralytics.com/images/zidane.jpg'"
],
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Downloading https://ultralytics.com/images/zidane.jpg to zidane.jpg...\n",
"100% 165k/165k [00:00<00:00, 12.0MB/s]\n",
"Ultralytics YOLOv8.0.5 🚀 Python-3.8.16 torch-1.13.1+cu116 CUDA:0 (Tesla T4, 15110MiB)\n",
"Downloading https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt to yolov8n.pt...\n",
"100% 6.24M/6.24M [00:00<00:00, 58.7MB/s]\n",
"\n",
"Fusing layers... \n",
"YOLOv8n summary: 168 layers, 3151904 parameters, 0 gradients, 8.7 GFLOPs\n",
"image 1/1 /content/zidane.jpg: 384x640 2 persons, 1 tie, 13.6ms\n",
"Speed: 0.4ms pre-process, 13.6ms inference, 52.1ms postprocess per image at shape (1, 3, 640, 640)\n",
"Results saved to \u001b[1mruns/detect/predict\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. Val\n",
"Validate a model's accuracy on the [COCO](https://cocodataset.org/#home) dataset's `val` or `test` splits. The latest YOLOv8 [models](https://github.com/ultralytics/ultralytics#models) are downloaded automatically the first time they are used."
]
},
{
"cell_type": "code",
"metadata": {
"id": "WQPtK1QYVaD_"
},
"source": [
"# Download COCO val\n",
"import torch\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": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "X58w8JLpMnjH"
},
"source": [
"# Validate YOLOv8n on COCO128 val\n",
"!yolo task=detect mode=val model=yolov8n.pt data=coco128.yaml"
],
"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://github.com/ultralytics/assets/raw/main/yolov8/banner-integrations.png\"/></a></p>\n",
"\n",
"Train YOLOv8 on [Detection](https://docs.ultralytics.com/tasks/detection/), [Segmentation](https://docs.ultralytics.com/tasks/segmentation/) and [Classification](https://docs.ultralytics.com/tasks/classification/) datasets."
]
},
{
"cell_type": "code",
"metadata": {
"id": "1NcFxRcFdJ_O"
},
"source": [
"# Train YOLOv8n on COCO128 for 3 epochs\n",
"!yolo task=detect mode=train model=yolov8n.pt data=coco128.yaml epochs=3 imgsz=640"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"# 4. Export\n",
"\n",
"Export a YOLOv8 model to any supported format with the `format` argument, i.e. `format=onnx`.\n",
"\n",
"- 💡 ProTip: Export to ONNX or OpenVINO for up to 3x CPU speedup. \n",
"- 💡 ProTip: Export to TensorRT for up to 5x GPU speedup.\n",
"\n",
"\n",
"| Format | `format=` | Model |\n",
"|----------------------------------------------------------------------------|--------------------|---------------------------|\n",
"| [PyTorch](https://pytorch.org/) | - | `yolov8n.pt` |\n",
"| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n.torchscript` |\n",
"| [ONNX](https://onnx.ai/) | `onnx` | `yolov8n.onnx` |\n",
"| [OpenVINO](https://docs.openvino.ai/latest/index.html) | `openvino` | `yolov8n_openvino_model/` |\n",
"| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n.engine` |\n",
"| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n.mlmodel` |\n",
"| [TensorFlow SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n_saved_model/` |\n",
"| [TensorFlow GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n.pb` |\n",
"| [TensorFlow Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n.tflite` |\n",
"| [TensorFlow Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` |\n",
"| [TensorFlow.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` |\n",
"| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` |\n",
"\n"
],
"metadata": {
"id": "nPZZeNrLCQG6"
}
},
{
"cell_type": "code",
"source": [
"!yolo mode=export model=yolov8n.pt format=torchscript"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "CYIjW4igCjqD",
"outputId": "f0910315-d678-45b4-c283-3ccd018a5024"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Ultralytics YOLOv8.0.1 🚀 Python-3.8.16 torch-1.13.0+cu116 CPU\n",
"Fusing layers... \n",
"YOLOv8n summary: 168 layers, 3151904 parameters, 0 gradients, 8.7 GFLOPs\n",
"\n",
"\u001b[34m\u001b[1mPyTorch:\u001b[0m starting from yolov8n.pt with output shape (1, 84, 8400) (6.2 MB)\n",
"\n",
"\u001b[34m\u001b[1mTorchScript:\u001b[0m starting export with torch 1.13.0+cu116...\n",
"\u001b[34m\u001b[1mTorchScript:\u001b[0m export success ✅ 1.8s, saved as yolov8n.torchscript (12.4 MB)\n",
"\n",
"Export complete (2.5s)\n",
"Results saved to \u001b[1m/content\u001b[0m\n",
"Predict: yolo task=detect mode=predict model=yolov8n.torchscript -WARNING ⚠ not yet supported for YOLOv8 exported models\n",
"Validate: yolo task=detect mode=val model=yolov8n.torchscript -WARNING ⚠ not yet supported for YOLOv8 exported models\n",
"Visualize: https://netron.app\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"# 5. Python Usage\n",
"\n",
"YOLOv8 was reimagined using Python-first principles for the most seamless Python YOLO experience yet. YOLOv8 models can be loaded from a trained checkpoint or created from scratch. Then methods are used to train, val, predict, and export the model. See a detailed Python usage examples in the YOLOv8 [Docs](https://docs.ultralytics.com/python/)."
],
"metadata": {
"id": "kUMOQ0OeDBJG"
}
},
{
"cell_type": "code",
"source": [
"from ultralytics import YOLO\n",
"\n",
"# Load a model\n",
"model = YOLO('yolov8n.yaml') # build a new model from scratch\n",
"model = YOLO('yolov8n.pt') # load a pretrained model (recommended for training)\n",
"\n",
"# Use the model\n",
"results = model.train(data='coco128.yaml', epochs=3) # train the model\n",
"results = model.val() # evaluate model performance on the validation set\n",
"results = model('https://ultralytics.com/images/bus.jpg') # predict on an image\n",
"success = model.export(format='onnx') # export the model to ONNX format"
],
"metadata": {
"id": "bpF9-vS_DAaf"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"# 6. Tasks\n",
"\n",
"YOLOv8 can train, val, predict and export models for the 3 primary tasks in vision AI: detection, segmentation and classification.\n",
"\n",
"<img width=\"1024\" src=\"https://user-images.githubusercontent.com/26833433/212094133-6bb8c21c-3d47-41df-a512-81c5931054ae.png\">\n"
],
"metadata": {
"id": "Phm9ccmOKye5"
}
},
{
"cell_type": "markdown",
"source": [
"## 1. Detection\n",
"\n",
"YOLOv8 _detection_ models have no suffix and are the default YOLOv8 models, i.e. `yolov8n.pt` and are pretrained on COCO. See [Detection Docs](https://docs.ultralytics.com/tasks/detection/) for full details.\n"
],
"metadata": {
"id": "yq26lwpYK1lq"
}
},
{
"cell_type": "code",
"source": [
"# Load YOLOv8n, train it on COCO128 for 3 epochs and predict an image with it\n",
"from ultralytics import YOLO\n",
"\n",
"model = YOLO('yolov8n.pt') # load a pretrained YOLOv8n detection model\n",
"model.train(data='coco128.yaml', epochs=3) # train the model\n",
"model('https://ultralytics.com/images/bus.jpg') # predict on an image"
],
"metadata": {
"id": "8Go5qqS9LbC5"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"## 2. Segmentation\n",
"\n",
"YOLOv8 _segmentation_ models use the `-seg` suffix, i.e. `yolov8n-seg.pt` and are pretrained on COCO. See [Segmentation Docs](https://docs.ultralytics.com/tasks/segmentation/) for full details.\n"
],
"metadata": {
"id": "7ZW58jUzK66B"
}
},
{
"cell_type": "code",
"source": [
"# Load YOLOv8n-seg, train it on COCO128-seg for 3 epochs and predict an image with it\n",
"from ultralytics import YOLO\n",
"\n",
"model = YOLO('yolov8n-seg.pt') # load a pretrained YOLOv8n segmentation model\n",
"model.train(data='coco128-seg.yaml', epochs=3) # train the model\n",
"model('https://ultralytics.com/images/bus.jpg') # predict on an image"
],
"metadata": {
"id": "WFPJIQl_L5HT"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"## 3. Classification\n",
"\n",
"YOLOv8 _classification_ models use the `-cls` suffix, i.e. `yolov8n-cls.pt` and are pretrained on ImageNet. See [Classification Docs](https://docs.ultralytics.com/tasks/classification/) for full details.\n"
],
"metadata": {
"id": "ax3p94VNK9zR"
}
},
{
"cell_type": "code",
"source": [
"# Load YOLOv8n-cls, train it on imagenette160 for 3 epochs and predict an image with it\n",
"from ultralytics import YOLO\n",
"\n",
"model = YOLO('yolov8n-cls.pt') # load a pretrained YOLOv8n classification model\n",
"model.train(data='imagenette160', epochs=3) # train the model\n",
"model('https://ultralytics.com/images/bus.jpg') # predict on an image"
],
"metadata": {
"id": "5q9Zu6zlL5rS"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "IEijrePND_2I"
},
"source": [
"# Appendix\n",
"\n",
"Additional content below."
]
},
{
"cell_type": "code",
"metadata": {
"id": "GMusP4OAxFu6"
},
"source": [
"# Run YOLOv8 tests (git clone install only)\n",
"!pytest ultralytics/tests"
],
"execution_count": null,
"outputs": []
}
]
}