YOLO-Tutorial-v2/yolo/models/yolov8

YOLOv8:

• VOC

• COCO

Model	Batch	Scale	APval 0.5	Weight	Logs
YOLOv8-S	1xb16	640	83.6	ckpt	log

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

© 2025 Gogs

Página: 195ms Plantilla: 3ms

español

español English 简体中文 繁體中文（香港） 繁體中文（臺灣） Deutsch français Nederlands latviešu русский 日本語 português do Brasil polski български italiano suomi Türkçe čeština српски svenska 한국어 galego українська English (United Kingdom) Magyar Slovenčina Indonesian Persian Vietnamese Português Монгол Română

Javascript Licenses Página web

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