How to add the bounding box values to the labels text files during prediction with a trained YOLO-V8 instance segmentation model? about ultralytics

[github-actions]

👋 Hello @sivaramakrishnan-rajaraman, thank you for your interest in Ultralytics YOLOv8 🚀! We recommend a visit to the Docs for new users where you can find many Python and CLI usage examples and where many of the most common questions may already be answered.

If this is a 🐛 Bug Report, please provide a minimum reproducible example to help us debug it.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset image examples and training logs, and verify you are following our Tips for Best Training Results.

Join the vibrant Ultralytics Discord 🎧 community for real-time conversations and collaborations. This platform offers a perfect space to inquire, showcase your work, and connect with fellow Ultralytics users.

Install

Pip install the ultralytics package including all requirements in a Python>=3.8 environment with PyTorch>=1.8.

pip install ultralytics

Environments

YOLOv8 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all Ultralytics CI tests are currently passing. CI tests verify correct operation of all YOLOv8 Modes and Tasks on macOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@sivaramakrishnan-rajaraman hi there,

Thank you for reaching out! To include bounding box coordinates (x-center, y-center, width, height) in the label files during prediction with your YOLOv8 instance segmentation model, you can modify the code to save these additional details.

While the CLI currently does not directly support adding bounding box coordinates to the label files, you can achieve this by using the Python API. Below is an example of how you can modify your prediction script to include the bounding box coordinates in the label files:

from ultralytics import YOLO

# Load the model
model = YOLO('/weights/best.pt')

# Run prediction
results = model.predict(source='/test/images', conf=0.25, imgsz=1024, save=True, save_txt=True, save_conf=True)

# Save predictions with bounding box coordinates
for result in results:
    for i, (box, mask, conf, cls) in enumerate(zip(result.boxes.xywh, result.masks.xy, result.boxes.conf, result.boxes.cls)):
        # Prepare the label content
        label_content = f"{int(cls)} " + " ".join(map(str, mask.flatten().tolist())) + f" {conf:.6f} " + " ".join(map(str, box.tolist()))
        
        # Save to file
        label_file = f"{result.path.stem}_{i}.txt"
        with open(label_file, 'w') as f:
            f.write(label_content)

This script will save the bounding box coordinates along with the polygonal coordinates and confidence scores in the label files.

If you prefer to stick with the CLI, you might need to run the predictions first and then post-process the results to add the bounding box coordinates to the label files. However, using the Python API as shown above provides a more streamlined approach.

Please ensure you are using the latest versions of torch and ultralytics to avoid any compatibility issues. You can update your packages using:

pip install --upgrade torch ultralytics

For further details, you can refer to the Ultralytics documentation.

Feel free to reach out if you have any more questions. Happy coding! 😊

[sivaramakrishnan-rajaraman]

Thanks, it works this way :)

[glenn-jocher]

Hi @sivaramakrishnan-rajaraman,

I'm glad to hear that it worked for you! 😊 If you have any more questions or run into any other issues, feel free to reach out. We're here to help!

Happy coding and best of luck with your project!