这里只说简单的训练步骤
v8实例分割的数据集和v5是通用的也是labelme标记的json文件转txt
from ultralytics import YOLO
from PIL import Image
if __name__ == '__main__':
model = YOLO('yolov8n-seg.yaml') # build a new model from YAML //根据网络模型名称初始化模型结构并返回模型加载信息
# model = YOLO('yolov8n.pt') # load a pretrained model (recommended for training)
# model = YOLO('yolov8n.yaml').load('yolov8n.pt') # build from YAML and transfer weights
# Train the model
results = model.train(data='coco8-seg.yaml', epochs=100, imgsz=640)
4.推理,model里面的模型填自己训练模型路径,训练的模型也在runs下面 ,source里面填自己想推理的图片路径
yolo segment predict model=yolov8n-seg.pt source='https://ultralytics.com/images/bus.jpg'
网络模型配置文件在ultralytics/cfg/models下面
数据集配置文件在ultralytics/cfg/datasets下面