RTCDet: My Empirical Study of Real-Time Convolutional Object Detectors.

Model	Batch	Scale	AP^val 0.5	Weight	Logs
RTCDet-S	1xb16	640

Train RTCDet

Taking training RTCDet-S on COCO as the example,

python train.py --cuda -d coco --root path/to/coco -m rtcdet_s -bs 16 --fp16

Taking training RTCDet-S on COCO as the example,

python -m torch.distributed.run --nproc_per_node=8 train.py --cuda --distributed -d coco --root path/to/coco -m rtcdet_s -bs 256 --fp16

Taking testing RTCDet-S on COCO-val as the example,

python test.py --cuda -d coco --root path/to/coco -m rtcdet_s --weight path/to/RTCDet.pth --show

Taking evaluating RTCDet-S on COCO-val as the example,

python eval.py --cuda -d coco --root path/to/coco -m rtcdet_s --weight path/to/RTCDet.pth

python demo.py --mode image --path_to_img path/to/image_dirs/ --cuda -m rtcdet_s --weight path/to/weight --show

python demo.py --mode video --path_to_vid path/to/video --cuda -m rtcdet_s --weight path/to/weight --show --gif

python demo.py --mode camera --cuda -m rtcdet_s --weight path/to/weight --show --gif

Model	Batch	Scale	AP^val 0.5:0.95	AP^val 0.5	FLOPs ^(G)	Params ^(M)	Weight	Logs
RTCDet-S	1xb16	640			26.9	8.9