yjh0410 3e72bd7a3a add odlab including detr		10 mesi fa
..
README.md	3e72bd7a3a add odlab including detr	10 mesi fa
build.py	3e72bd7a3a add odlab including detr	10 mesi fa
criterion.py	3e72bd7a3a add odlab including detr	10 mesi fa
matcher.py	3e72bd7a3a add odlab including detr	10 mesi fa
yolof.py	3e72bd7a3a add odlab including detr	10 mesi fa

YOLOF: You Only Look One-level Feature

COCO

Train YOLOF

Single GPU

Taking training YOLOF_R18_C5_1x on COCO as the example,

python main.py --cuda -d coco --root path/to/coco -m yolof_r18_c5_1x --batch_size 16 --eval_epoch 2

Multi GPU

Taking training YOLOF_R18_C5_1x on COCO as the example,

python -m torch.distributed.run --nproc_per_node=8 train.py --cuda -dist -d coco --root path/to/coco -m yolof_r18_c5_1x --batch_size 16 --eval_epoch 2

Test YOLOF

Taking testing YOLOF_R18_C5_1x on COCO-val as the example,

python test.py --cuda -d coco --root path/to/coco -m yolof_r18_c5_1x --weight path/to/yolof_r18_c5_1x.pth -vt 0.4 --show

Evaluate YOLOF

Taking evaluating YOLOF_R18_C5_1x on COCO-val as the example,

python main.py --cuda -d coco --root path/to/coco -m yolof_r18_c5_1x --resume path/to/yolof_r18_c5_1x.pth --eval_first

Demo

Detect with Image

python demo.py --mode image --path_to_img path/to/image_dirs/ --cuda -m yolof_r18_c5_1x --weight path/to/weight -vt 0.4 --show

Detect with Video

python demo.py --mode video --path_to_vid path/to/video --cuda -m yolof_r18_c5_1x --weight path/to/weight -vt 0.4 --show --gif

Detect with Camera

python demo.py --mode camera --cuda -m yolof_r18_c5_1x --weight path/to/weight -vt 0.4 --show --gif

Model	scale	FPS^{FP32 RTX 4060}	AP^val 0.5:0.95	AP^val 0.5	Weight	Logs
YOLOF_R18_C5_1x	800,1333	54	32.8	51.4	ckpt	log
YOLOF_R50_C5_1x	800,1333	21	37.7	57.2	ckpt	log

README.md