Yolov10x

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

YOLOv10 is a real - time end - to - end object detection model, which provides solutions for computer vision tasks such as object detection.

🚀 Quick Start

YOLOv10 is a powerful real - time end - to - end object detection model. You can quickly start using it by following the steps below.

✨ Features

• Object Detection: Specialized in real - time end - to - end object detection.
• Computer Vision: Applicable to various computer vision tasks.
• Pytorch Integration: Integrated with the PyTorch framework.

📦 Installation

You can install YOLOv10 using the following command:

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

💻 Usage Examples

Basic Usage

Training and validation

from ultralytics import YOLOv10

model = YOLOv10.from_pretrained('jameslahm/yolov10x')
# Training
model.train(...)
# after training, one can push to the hub
model.push_to_hub("your-hf-username/yolov10-finetuned")

# Validation
model.val(...)

Inference

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

from ultralytics import YOLOv10

model = YOLOv10.from_pretrained('jameslahm/yolov10x')
source = 'http://images.cocodataset.org/val2017/000000039769.jpg'
model.predict(source=source, save=True)

This code will perform inference on the specified image and save the result. The following is the result image:

📚 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

📄 License

This project is licensed under the AGPL - 3.0 license.

📚 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}
}