Support for YOLOv11 in the conversion script

[ainayves]

Hello,

Does this conversion script support YOLOv11, or is it still limited to YOLOv8?

Thanks in advance for your response! 😊

[UltralyticsAssistant]

👋 Hello @ainayves, thank you for submitting a ultralytics/JSON2YOLO 🚀 Issue. To help us address your concern efficiently, please ensure you've provided the following information:

1. For questions:

   • Provide as much context as possible about your question
   • Include any research you've already done on the topic
   • Specify which parts of the documentation, if any, you've already consulted

2. For bug reports:

   • A clear and concise description of the bug
   • A minimum reproducible example MRE that demonstrates the issue
   • Your environment details (OS, Python version, package versions)
   • Expected behavior vs. actual behavior
   • Any error messages or logs related to the issue

3. For feature requests:

   • A clear and concise description of the proposed feature
   • The problem this feature would solve
   • Any alternative solutions you've considered

Before proceeding, please ensure you've searched existing issues to avoid duplicates. If you have additional information or context to provide about your question regarding YOLOv11 support, kindly comment on this issue thread.

This is an automated response to help streamline issue management, but don’t worry—a member of the Ultralytics team will assist you shortly! 🚀✨

Thank you for contributing and helping improve our project!

[pderrenger]

@ainayves thanks for your question! The Ultralytics package supports YOLOv11, including model conversion/export to formats like ONNX and TensorRT. To use YOLOv11, simply specify model='yolov11' in your code. For details, see our Export documentation. Ensure you're using the latest ultralytics>=8.2.0 package.

[ainayves]

@pderrenger , Thank you for your response.

I realize my previous message was not very clear, and I apologize for that. My question is actually about the dataset format. If I’m not mistaken, this repository contains a script for converting COCO to YOLO. I would like to know if the dataset is converted to the YOLOv11 format, following a structure of this kind or another :

archive.zip/
├── obj.data
├── obj.names
├── obj__data
│ ├── image1.txt
│ └── image2.txt
└── train.txt # List of subset image paths

[pderrenger]

@ainayves the Ultralytics YOLOv11 dataset format uses a simplified structure with a data.yaml file and organized image/label directories, not the legacy obj.data/obj.names format. The converted COCO dataset will follow this structure:

dataset/
├── data.yaml
├── train/
│   ├── images/
│   └── labels/
├── val/
│   ├── images/
│   └── labels/

The convert_coco() function handles this conversion automatically. For details, see our Dataset Format Documentation and Converter Examples.