GUV-Detection CV Weights

Trained detector weights for the GUV detection benchmark (YOLOv11n vs RT-DETRv3), accompanying github.com/josephlaurienzo-sudo/guv-detection.v2.0 replaces v1's files with the corrected, converged model set used in the manuscript (v1 shipped a YOLO11s weight and a raw RT-DETR checkpoint; both removed): yolo11n.pt — YOLOv11n deployment model (the selected detector) yolo11n_cv_fold0..4.pt — per-fold YOLOv11n weights (5-fold spatial CV) rtdetrv3_r50_300_deploy.tar — RT-DETRv3-R50, 300-epoch converged, exported PaddleDetection inference model (model.json + model.pdiparams + infer_cfg.yml) rtdetrv3_r50_cv_fold0..4.tar — per-fold RT-DETRv3-R50 (300ep) exported inference models rtdetrv3_r18_cv_fold0..4.tar — per-fold RT-DETRv3-R18 (300ep) exported inference models Each .tar extracts to a PaddleDetection inference directory (point the RT-DETR inference script --model-dir at it). Trained on a 5x air-objective GUV fluorescence dataset; see the repository for the full reproduction pipeline.