YOLOv8实战debug

1、训练篇

开始run.py

from ultralytics import YOLO

# Load a model
#model = YOLO('yolov8n.yaml')  # build a new model from YAML
#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
model.train(data='D:/0000/YOLOv8/ultralytics-main/ultralytics/cfg/datasets/URPC2019.yaml', epochs=100 ,batch=2, resume=True, device=0, workers=0)

实例YOLO类，YOLO类继承于Model，先定义Model。

传入字符串yolov8n.yaml

 1、初始化YOLO模型Model

    def __init__(self, model: Union[str, Path] = 'yolov8n.pt', task=None) -> None:
        """
        Initializes the YOLO model.

        Args:
            model (Union[str, Path], optional): Path or name of the model to load or create. Defaults to 'yolov8n.pt'.
            task (Any, optional): Task type for the YOLO model. Defaults to None.
        """
        super().__init__()
        self.callbacks = callbacks.get_default_callbacks()
        self.predictor = None  # reuse predictor
        self.model = None  # model object
        self.trainer = None  # trainer object
        self.ckpt = None  # if loaded from *.pt
        self.cfg = None  # if loaded from *.yaml
        self.ckpt_path = None
        self.overrides = {}  # overrides for trainer object
        self.metrics = None  # validation/training metrics
        self.session = None  # HUB session
        self.task = task  # task type
        model = str(model).strip()  # strip spaces

        # Check if Ultralytics HUB model from https://hub.ultralytics.com
        if self.is_hub_model(model):   #Check if the provided model is a HUB model.model=yolov8n.yaml 不执行
            from ultralytics.hub.session import HUBTrainingSession
            self.session = HUBTrainingSession(model)
            model = self.session.model_file   

        # Check if Triton Server model  #也没有执行
        elif self.is_triton_model(model):
            self.model = model
            self.task = task
            return

        # Load or create new YOLO model
        model = checks.check_model_file_from_stem(model)  # add suffix, i.e. yolov8n -> yolov8n.pt  #如果.yaml后缀 就new一个 如果.pt结尾，就导入一个预训练模型
        if Path(model).suffix in ('.yaml', '.yml'):
            self._new(model, task)
        else:
            self._load(model, task)

本次debug为.yaml 即new一个 task我没有传参数，所以还是为None。

执行self._new(model,task)。

    def _new(self, cfg: str, task=None, model=None, verbose=True):
        """
        Initializes a new model and infers the task type from the model definitions.

        Args:
            cfg (str): model configuration file
            task (str | None): model task
            model (BaseModel): Customized model.
            verbose (bool): display model info on load
        """
        cfg_dict = yaml_model_load(cfg)
        self.cfg = cfg
        self.task = task or guess_model_task(cfg_dict)  #从模型字典中得到task,即yaml最后一层detect得到task为detect
        self.model = (model or self._smart_load('model'))(cfg_dict, verbose=verbose and RANK == -1)  # build model
        self.overrides['model'] = self.cfg
        self.overrides['task'] = self.task

        # Below added to allow export from YAMLs
        self.model.args = {**DEFAULT_CFG_DICT, **self.overrides}  # combine default and model args (prefer model args)
        self.model.task = self.task

调用yaml_model_load(cfg)函数 cfg='yolov8n.yaml'

def yaml_model_load(path):   #path:'yolov8.yaml'
    """Load a YOLOv8 model from a YAML file."""
    import re

    path = Path(path)
    if path.stem in (f'yolov{d}{x}6' for x in 'nsmlx' for d in (5, 8)): #判断模型型号 本次debug不执行
        new_stem = re.sub(r'(\d+)([nslmx])6(.+)?$', r'\1\2-p6\3', path.stem) 
        LOGGER.warning(f'WARNING ⚠️ Ultralytics YOLO P6 models now use -p6 suffix. Renaming {path.stem} to {new_stem}.')
        path = path.with_name(new_stem + path.suffix)

    unified_path = re.sub(r'(\d+)([nslmx])(.+)?$', r'\1\3', str(path))  # i.e. yolov8x.yaml -> yolov8.yaml
    yaml_file = check_yaml(unified_path, hard=False) or check_yaml(path) #调用check_yaml(),里面又调用check_file() check_file()查找或者下载  files = glob.glob(str(ROOT / 'cfg' / '**' / file), recursive=True)  # find file 查找路径 绝对路径 这时yaml_file 为绝对路径
    d = yaml_load(yaml_file)  # model dict  #和yolov5一样的yaml导入 
    d['scale'] = guess_model_scale(path)
    d['yaml_file'] = str(path)
    return d

此时cfg_dict：self._smart_load('model') 调用YOLO重写的task_map，返回一个DetectionModel类（为YOLOv8的检测模型）

self.model=DetectionModel(cfg_dict, verbose=verbose and RANK == -1) 实例化类，初始化

class DetectionModel(BaseModel):
    """YOLOv8 detection model."""

    def __init__(self, cfg='yolov8n.yaml', ch=3, nc=None, verbose=True):  # model, input channels, number of classes
        """Initialize the YOLOv8 detection model with the given config and parameters."""
        super().__init__()
        self.yaml = cfg if isinstance(cfg, dict) else yaml_model_load(cfg)  # cfg dict

        # Define model
        ch = self.yaml['ch'] = self.yaml.get('ch', ch)  # input channels   3
        if nc and nc != self.yaml['nc']:
            LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
            self.yaml['nc'] = nc  # override YAML value
        self.model, self.save = parse_model(deepcopy(self.yaml), ch=ch, verbose=verbose)   # model, savelist 调用parse_model函数得到self.model和.save。代码基本和v5的一样
        self.names = {i: f'{i}' for i in range(self.yaml['nc'])}  # default names dict
        self.inplace = self.yaml.get('inplace', True)

        # Build strides
        m = self.model[-1]  # Detect()
        if isinstance(m, (Detect, Segment, Pose)):
            s = 256  # 2x min stride
            m.inplace = self.inplace
            forward = lambda x: self.forward(x)[0] if isinstance(m, (Segment, Pose)) else self.forward(x)
            m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))])  # forward
            self.stride = m.stride
            m.bias_init()  # only run once
        else:
            self.stride = torch.Tensor([32])  # default stride for i.e. RTDETR

        # Init weights, biases
        initialize_weights(self)
        if verbose:
            self.info()
            LOGGER.info('')

已经完成了第一步

model = YOLO('yolov8n.yaml') 此时model:

2、下一步导入预训练权重：

    def load(self, weights='yolov8n.pt'):
        """Transfers parameters with matching names and shapes from 'weights' to model."""
        self._check_is_pytorch_model()
        if isinstance(weights, (str, Path)):
            weights, self.ckpt = attempt_load_one_weight(weights)
        self.model.load(weights)
        return self

model.train()

 def train(self, trainer=None, **kwargs):
        """
        Trains the model on a given dataset.

        Args:
            trainer (BaseTrainer, optional): Customized trainer.
            **kwargs (Any): Any number of arguments representing the training configuration.
        """
        self._check_is_pytorch_model()
        if hasattr(self.session, "model") and self.session.model.id:  # Ultralytics HUB session with loaded model
            if any(kwargs):
                LOGGER.warning("WARNING ⚠️ using HUB training arguments, ignoring local training arguments.")
            kwargs = self.session.train_args  # overwrite kwargs

        checks.check_pip_update_available()

        overrides = yaml_load(checks.check_yaml(kwargs["cfg"])) if kwargs.get("cfg") else self.overrides
        custom = {"data": DEFAULT_CFG_DICT["data"] or TASK2DATA[self.task]}  # method defaults
        args = {**overrides, **custom, **kwargs, "mode": "train"}  # highest priority args on the right
        if args.get("resume"):
            args["resume"] = self.ckpt_path

        self.trainer = (trainer or self._smart_load("trainer"))(overrides=args, _callbacks=self.callbacks)
        if not args.get("resume"):  # manually set model only if not resuming
            self.trainer.model = self.trainer.get_model(weights=self.model if self.ckpt else None, cfg=self.model.yaml)
            self.model = self.trainer.model

            if SETTINGS["hub"] is True and not self.session:
                # Create a model in HUB
                try:
                    self.session = self._get_hub_session(self.model_name)
                    if self.session:
                        self.session.create_model(args)
                        # Check model was created
                        if not getattr(self.session.model, "id", None):
                            self.session = None
                except (PermissionError, ModuleNotFoundError):
                    # Ignore PermissionError and ModuleNotFoundError which indicates hub-sdk not installed
                    pass

        self.trainer.hub_session = self.session  # attach optional HUB session
        self.trainer.train()
        # Update model and cfg after training
        if RANK in (-1, 0):
            ckpt = self.trainer.best if self.trainer.best.exists() else self.trainer.last
            self.model, _ = attempt_load_one_weight(ckpt)
            self.overrides = self.model.args
            self.metrics = getattr(self.trainer.validator, "metrics", None)  # TODO: no metrics returned by DDP
        return self.metrics

未完待续。。。