Table 3 The comprehensive training outcomes are derived from both the training and validation datasets.
Submodels | Pr | Rc | mAP-0.5 | mAP-0.5:0.95 |
---|---|---|---|---|
YOLOv8 | 0.82 | 0.74 | 0.81 | 0.49 |
YOLOv8-iRMB | 0.82 | 0.76 | 0.82 | 0.54 |
YOLOv8-EVC | 0.85 | 0.77 | 0.85 | 0.57 |
YOLOv8-IE | 0.86 | 0.84 | 0.89 | 0.72 |