maco018/billboard-detection-Yolo11

General description

All of Ultralytics' Yolo V11 models model fined tuned for billboard detection using the Billboard dataset.

This model was created with 100 epochs using CUDA 12.4 and Pytorch 2.6.0.

Best Metrics Comparison

Model	Precision (Epoch)	Recall (Epoch)	mAP50 (Epoch)	mAP50-95 (Epoch)
YOLO_11n	0.73613 (epoch: 66)	0.67308 (epoch: 88)	0.70351 (epoch: 87)	0.43033 (epoch: 80)
YOLO_11s	0.7225 (epoch: 98)	0.67735 (epoch: 81)	0.70855 (epoch: 76)	0.43518 (epoch: 77)
YOLO_11m	0.73249 (epoch: 80)	0.6745 (epoch: 73)	0.71053 (epoch: 87)	0.43404 (epoch: 62)
YOLO_11l	0.74729 (epoch: 98)	0.68174 (epoch: 49)	0.71778 (epoch: 75)	0.44731 (epoch: 89)
YOLO_11x	0.74299 (epoch: 94)	0.6688 (epoch: 80)	0.7113 (epoch: 60)	0.4437 (epoch: 89)

Further results can be found in Results Folder.

Created by Mark Colley - supported by Zefwih