yolov8命令梳理

基本格式

	yolo TASK MODE ARGS

其中：
TASK (optional) 在这三个中选其中一个 [detect, segment, classify]
MODE (required) 在这三个中选其中一个 [train, val, predict, export, track]
ARGS (optional) 例如 ‘imgsz=320’

训练：

    yolo train data=coco128.yaml model=yolov8n.pt 
    yolo detect train data=coco128.yaml model=yolov8n.pt epochs=100 imgsz=640
    yolo detect train resume model=last.pt

预测

    yolo predict model=yolov8n-seg.pt source='https://youtu.be/Zgi9g1ksQHc' imgsz=320 
    yolo detect predict model=path/to/best.pt source='https://ultralytics.com/images/bus.jpg'

验证

    yolo val model=yolov8n.pt data=coco128.yaml batch=1 imgsz=640
    yolo detect val model=path/to/best.pt

导出

    yolo export model=yolov8n-cls.pt format=onnx imgsz=224,128
    yolo export model=path/to/best.pt format=onnx

Format	format Argument	Model	Metadata
PyTorch	-	yolov8n.pt	✅
TorchScript	torchscript	yolov8n.torchscript	✅
ONNX	onnx	yolov8n.onnx	✅
OpenVINO	openvino	yolov8n_openvino_model/	✅
TensorRT	engine	yolov8n.engine	✅
CoreML	coreml	yolov8n.mlmodel	✅
TF SavedModel	saved_model	yolov8n_saved_model/	✅
TF GraphDef	pb	yolov8n.pb	❌
TF Lite	tflite	yolov8n.tflite	✅
TF Edge TPU	edgetpu	yolov8n_edgetpu.tflite	✅
TF.js	tfjs	yolov8n_web_model/	✅
PaddlePaddle	paddle	yolov8n_paddle_model/	✅

其他

    yolo help
    yolo checks
    yolo version
    yolo settings
    yolo copy-cfg
    yolo cfg
   `yolo predict model=yolov8n.pt imgsz=640 conf=0.25`   ✅

自定义超参数

    yolo copy-cfg
    yolo cfg=default_copy.yaml imgsz=320