| Model | scales | Parameters | GFLOPs | pretrained | epoch | time | train/box_loss | train/cls_loss | train/dfl_loss | metrics/precision(B) | metrics/recall(B) | metrics/mAP50(B) | metrics/mAP50-95(B) | val/box_loss | val/cls_loss | val/dfl_loss | lr/pg0 | lr/pg1 | lr/pg2 | AP[.50:.95|all|M100] | AP[.50|all|M100] | AP[.75|all|M100] | AP[.50:.95|small|M100] | AP[.50:.95|medium|M100] | AP[.50:.95|large|M100] | AR[.50:.95|all|M1] | AR[.50:.95|all|M10] | AR[.50:.95|all|M100] | AR[.50:.95|small|M100] | AR[.50:.95|medium|M100] | AR[.50:.95|large|M100] | AR[.50|all|M100] | AR[.75|all|M100] | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |

seg

Untitled

Model	scales	状态	Parameters	GFLOPs	epoch	time	train/box_loss	train/seg_loss	train/cls_loss	train/dfl_loss	metrics/precision(B)	metrics/recall(B)	metrics/mAP50(B)	metrics/mAP50-95(B)	metrics/precision(M)	metrics/recall(M)	metrics/mAP50(M)	metrics/mAP50-95(M)	val/box_loss	val/seg_loss	val/cls_loss	val/dfl_loss	lr/pg0	lr/pg1	lr/pg2

mmdetection

model	coco/car_precision	coco/truck_precision	coco/motor_precision	coco/pedestrian_precision	coco/van_precision	coco/tricycle_precision	coco/people_precision	coco/bus_precision	coco/bbox_mAP	coco/bbox_mAP_50	coco/bbox_mAP_75	coco/bbox_mAP_s	coco/bbox_mAP_m	coco/bbox_mAP_l	data_time	time
faster-rcnn_r50_fpn_2x_nightdrone	0.4090	0.3040	0.1680	0.0450	0.2110	0.3720	0.0680	0.4350	0.2510	0.4430	0.2680	0.1230	0.2900	0.3960	0.0016	0.0614
faster-rcnn_r50_fpn_2x_nightdrone_ADownGatedV3_V3d	0.4040	0.3120	0.1640	0.0450	0.2100	0.3710	0.0780	0.4470	0.2540	0.4490	0.2640	0.1190	0.2950	0.3770	0.0016	0.0479

Visdrone

model	bbox_mAP	bbox_mAP_50	bbox_mAP_75	bbox_mAP_s	bbox_mAP_m	bbox_mAP_l	bbox_mAP_copypaste
overlock_t	0.1130	0.1977	0.1157	0.0997	0.1551	0.0721	0.1130 0.1977 0.1157 0.0997 0.1551 0.0721