Yolov8中断后继续训练，resume方法，断点训练

1.错误尝试
在训练YOLOv8的时候，因为开太多其他程序，导致在100多次的时候崩溃，查询网上相关知识如何接着训练，在yolo5中把resume改成True就可以。
在yolov8中也这样尝试，将ultralytics/yolo/cfg/default.yaml中的resume改成True发现并没有作用，感觉yolov8代码还是有很多bug

2.可行的方法

2.1 ultralytics/yolo/engine/trainer.py
找到check_resume和resume_training方法
在check_resume方法里面将resume=中断地方的last.pt
在resume_training里面将ckpt=中断地方的last.pt

    def check_resume(self, overrides):
        """Check if resume checkpoint exists and update arguments accordingly."""
        #resume = self.args.resume
        resume = 'runs/detect/train9/weights/last.pt'     #🚀🚀🚀🚀🚀手动resume修改完毕记得该回去
        if resume:
            try:
                exists = isinstance(resume, (str, Path)) and Path(resume).exists()
                last = Path(check_file(resume) if exists else get_latest_run())

                # Check that resume data YAML exists, otherwise strip to force re-download of dataset
                ckpt_args = attempt_load_weights(last).args
                if not Path(ckpt_args["data"]).exists():
                    ckpt_args["data"] = self.args.data

                resume = True
                self.args = get_cfg(ckpt_args)
                self.args.model = str(last)  # reinstate model
                for k in "imgsz", "batch":  # allow arg updates to reduce memory on resume if crashed due to CUDA OOM
                    if k in overrides:
                        setattr(self.args, k, overrides[k])

            except Exception as e:
                raise FileNotFoundError(
                    "Resume checkpoint not found. Please pass a valid checkpoint to resume from, "
                    "i.e. 'yolo train resume model=path/to/last.pt'"
                ) from e
        self.resume = resume

    def resume_training(self, ckpt):
        """Resume YOLO training from given epoch and best fitness."""
        ckpt = torch.load('runs/detect/train9/weights/last.pt')  #🚀🚀🚀🚀🚀手动resume修改完毕记得该回去
        if ckpt is None:
            return
        best_fitness = 0.0
        start_epoch = ckpt["epoch"] + 1
        if ckpt["optimizer"] is not None:
            self.optimizer.load_state_dict(ckpt["optimizer"])  # optimizer
            best_fitness = ckpt["best_fitness"]
        if self.ema and ckpt.get("ema"):
            self.ema.ema.load_state_dict(ckpt["ema"].float().state_dict())  # EMA
            self.ema.updates = ckpt["updates"]
        if self.resume:
            assert start_epoch > 0, (
                f"{self.args.model} training to {self.epochs} epochs is finished, nothing to resume.\n"
                f"Start a new training without resuming, i.e. 'yolo train model={self.args.model}'"
            )
            LOGGER.info(
                f"Resuming training from {self.args.model} from epoch {start_epoch + 1} to {self.epochs} total epochs"
            )
        if self.epochs < start_epoch:
            LOGGER.info(
                f"{self.model} has been trained for {ckpt['epoch']} epochs. Fine-tuning for {self.epochs} more epochs."
            )
            self.epochs += ckpt["epoch"]  # finetune additional epochs
        self.best_fitness = best_fitness
        self.start_epoch = start_epoch
        if start_epoch > (self.epochs - self.args.close_mosaic):
            self._close_dataloader_mosaic()

3.运行代码

没有在中断的train9训练，可以继续训练，

运行指令多种，这里用的自定义文件训练

from ultralytics import YOLO

if __name__=='__main__':
    #预训练模型创建模型
    # model = YOLO('yolov8s.pt')
    # model.train(**{'cfg':'ultralytics/cfg/exp.yaml','data':'dataset/limit.yaml'})

    #🥭pip setup.py install 

    #使用yaml文件来创建模型，并且导入与训练权重
    model = YOLO('ultralytics/cfg/models/v8/magickv8.yaml')
    #model.load('yoov8s.pt')
    model.train(**{'cfg':'ultralytics/cfg/exp.yaml','data':'datasets/limit.yaml'})      # ultralytics\cfg\datasets\limit.yaml

    # #模型验证
    # model =YOLO('runs/detect/train/weights/best.pt')
    # model.val(**{'data':'dataset/data.yaml','split':'test'})

    

    # #模型推理  检测
    # model =YOLO ('runs/detect/train34/weights/best.pt')    #runs/detect/train/weights/best.pt
    # model.predict(source='datasets/limit/images/val',**{'save':True})

    
    # model=YOLO ('runs/detect/train34/weights/best.pt'  )
    # model.export('runs/detect/train34/weights/best.pt',format=onnx opset=12)

     #yolo export model=runs/detect/train4/weights/best.pt format=onnx imgsz=768 simplify=True     console输出

结果显示：

重要提示

训练完成后请把所有代码复原！！！
训练完成后请把所有代码复原！！！
训练完成后请把所有代码复原！！！

yolov8版本自2023.1开始，现在使用的为2024.5.1发布代码，依然存在各种bug

有文章说还需改动如下，但新代码不需要做改动

 ultralytics/yolo/engine/model.py

打开ultralytics/yolo/engine/model.py代码，找到train方法，如下
将self.trainer.model = self.model注释掉

        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      #🚀🚀🚀🚀🚀此处

            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

参考文章