GrainNet: efficient detection and counting of wheat grains based on an improved YOLOv7 modeling

Table 6 Comparison of the counting performances of different models

Models	Projected results	R²	MAE	RMSE	Precision (%)
Faster-RCNN	59,747	0.56	30.06	61.54	69.97
YOLOv5	88,216	0.91	6.62	22.13	91.52
YOLOv7	82,721	0.84	9.72	32.37	90.91
YOLOv8	94,012	0.89	10.28	25.28	89.27
GrainNet	86,709	0.93	5.97	23.15	94.47

ISSN: 1746-4811