Yolov10m

🚀 YOLOv10

YOLOv10 is a real-time end-to-end object detection model, offering efficient solutions for computer vision tasks.

🚀 Quick Start

This guide provides a comprehensive overview of YOLOv10, including installation, training, validation, and inference steps.

✨ Features

• Object Detection: Specialized in real-time end-to-end object detection.
• Computer Vision: Applicable to a wide range of computer vision tasks.
• YOLOv10 Architecture: Built on the advanced YOLOv10 architecture.
• Pytorch Model Hub Mixin: Compatible with the PyTorch model hub.

📦 Installation

You can install YOLOv10 using the following command:

pip install git+https://github.com/THU-MIG/yolov10.git

💻 Usage Examples

Basic Usage

The following code demonstrates how to train and validate the YOLOv10 model:

from ultralytics import YOLOv10

model = YOLOv10.from_pretrained('jameslahm/yolov10m')
# Training
model.train(...)
# after training, one can push to the hub
model.push_to_hub("your-hf-username/yolov10-finetuned")

# Validation
model.val(...)

Advanced Usage

Here's an end-to-end example showcasing inference on a cats image:

from ultralytics import YOLOv10

model = YOLOv10.from_pretrained('jameslahm/yolov10m')
source = 'http://images.cocodataset.org/val2017/000000039769.jpg'
model.predict(source=source, save=True)

The result of the inference is shown below:

📚 Documentation

Model Description

YOLOv10: Real-Time End-to-End Object Detection

• arXiv: https://arxiv.org/abs/2405.14458v1
• github: https://github.com/THU-MIG/yolov10

BibTeX Entry and Citation Info

@article{wang2024yolov10,
  title={YOLOv10: Real-Time End-to-End Object Detection},
  author={Wang, Ao and Chen, Hui and Liu, Lihao and Chen, Kai and Lin, Zijia and Han, Jungong and Ding, Guiguang},
  journal={arXiv preprint arXiv:2405.14458},
  year={2024}
}

📄 License

This project is licensed under the AGPL-3.0 license.