YOLOv4:

For training, we train YOLOv4 and YOLOv4-Tiny with 250 epochs on COCO.
For data augmentation, we use the large scale jitter (LSJ), Mosaic augmentation and Mixup augmentation, following the setting of YOLOv5.
For optimizer, we use SGD with momentum 0.937, weight decay 0.0005 and base lr 0.01.
For learning rate scheduler, we use linear decay scheduler.
For YOLOv4's structure, we use decoupled head, following the setting of YOLOX.

Model	Backbone	Batch	Scale	AP^val 0.5:0.95	AP^val 0.5	FLOPs ^(G)	Params ^(M)	Weight
YOLOv4-Tiny	CSPDarkNet-Tiny	1xb16	640	31.0	49.1	8.1	2.9	ckpt
YOLOv4	CSPDarkNet-53	1xb16	640	46.6	65.8	162.7	61.5	ckpt