LibreRFDETRm-obb

LibreYOLO RF-DETR medium checkpoint fine-tuned for oriented bounding box detection.

Fine-tuned on My First Project - v8, a Roboflow Universe UAV vehicle OBB dataset provided by a Roboflow user: https://universe.roboflow.com/bobo-48pem/my-first-project-ewwrm

This model was not trained on DOTA.

Files

• LibreRFDETRm-obb.pt: lean LibreYOLO PyTorch checkpoint with EMA inference weights and checkpoint schema metadata.

Dataset

Dataset license: Creative Commons Attribution 4.0 International (CC BY 4.0).

Classes:

• bike
• bus
• car
• other_vehicle
• taxi
• truck

Local development export metadata reported 932 source/export images, YOLOv8 Oriented Object Detection format, and Roboflow preprocessing/augmentation.

Metrics

UAV-OBB validation split, current LibreYOLO dev evaluator:

• mAP50: 0.778212
• mAP50-95: 0.369263
• mAP75: 0.326096
• precision: 0.072214
• recall: 0.900434
• best epoch: 10

Usage

from libreyolo import LibreRFDETR

model = LibreRFDETR("LibreRFDETRm-obb.pt", task="obb")
results = model.predict("image.jpg")

License

These fine-tuned weights are released under CC BY 4.0 to preserve the attribution requirements of the training dataset. See LICENSE and NOTICE.