| Model |
Batch |
Scale |
APval 0.5:0.95
| APval 0.5
| FLOPs (G)
| Params (M)
| Weight |
Logs |
| YOLOv8-S |
1xb16 |
640 |
|
|
26.9 |
8.9 |
|
|
Train YOLOv8
Single GPU
Taking training YOLOv8-S on COCO as the example,
python train.py --cuda -d coco --root path/to/coco -m yolov8_s -bs 16 --fp16
Multi GPU
Taking training YOLOv8-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 yolov8_s -bs 256 --fp16
Test YOLOv8
Taking testing YOLOv8-S on COCO-val as the example,
python test.py --cuda -d coco --root path/to/coco -m yolov8_s --weight path/to/yolov8.pth --show
Evaluate YOLOv8
Taking evaluating YOLOv8-S on COCO-val as the example,
python eval.py --cuda -d coco --root path/to/coco -m yolov8_s --weight path/to/yolov8.pth
Demo
Detect with Image
python demo.py --mode image --path_to_img path/to/image_dirs/ --cuda -m yolov8_s --weight path/to/weight --show
Detect with Video
python demo.py --mode video --path_to_vid path/to/video --cuda -m yolov8_s --weight path/to/weight --show --gif
Detect with Camera
python demo.py --mode camera --cuda -m yolov8_s --weight path/to/weight --show --gif