关于yolov8的8.0.176的训练代码报错（Resume checkpoint not found. Please pass a valid checkpoint to resume from）

在上个博客中临时解决了训练的resume问题，现在来深度分析一下相关代码：

    from ultralytics.models.yolo.detect import DetectionTrainer
    args = dict(model='yolov8n.pt', data='coco8.yaml', epochs=3)
    trainer = DetectionTrainer(overrides=args)
    trainer.train()

上面的代码是官方给出的，其中args = dict(model=‘yolov8n.pt’, data=‘coco8.yaml’, epochs=3)是训练需要复写的内容，如果不写，就默认走defaults.yaml。我在训练的时候是全部走default的，下面是我的代码：

# Ultralytics YOLO 🚀, AGPL-3.0 license

from copy import copy

import numpy as np

from ultralytics.data import build_dataloader, build_yolo_dataset
from ultralytics.engine.trainer import BaseTrainer
from ultralytics.models import yolo
from ultralytics.nn.tasks import DetectionModel
from ultralytics.utils import LOGGER, RANK
from ultralytics.utils.plotting import plot_images, plot_labels, plot_results
from ultralytics.utils.torch_utils import de_parallel, torch_distributed_zero_first


class DetectionTrainer(BaseTrainer):
    """
    A class extending the BaseTrainer class for training based on a detection model.

    Example:
        ```python
        from ultralytics.models.yolo.detect import DetectionTrainer

        args = dict(model='yolov8n.pt', data='coco8.yaml', epochs=3)
        trainer = DetectionTrainer(overrides=args)
        trainer.train()
        ```
    """

    def build_dataset(self, img_path, mode='train', batch=None):
        """
        Build YOLO Dataset.

        Args:
            img_path (str): Path to the folder containing images.
            mode (str): `train` mode or `val` mode, users are able to customize different augmentations for each mode.
            batch (int, optional): Size of batches, this is for `rect`. Defaults to None.
        """
        gs = max(int(de_parallel(self.model).stride.max() if self.model else 0), 32)
        return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, rect=mode == 'val', stride=gs)

    def get_dataloader(self, dataset_path, batch_size=16, rank=0, mode='train'):
        """Construct and return dataloader."""
        assert mode in ['train', 'val']
        with torch_distributed_zero_first(rank):  # init dataset *.cache only once if DDP
            dataset = self.build_dataset(dataset_path, mode, batch_size)
        shuffle = mode == 'train'
        if getattr(dataset, 'rect', False) and shuffle:
            LOGGER.warning("WARNING ⚠️ 'rect=True' is incompatible with DataLoader shuffle, setting shuffle=False")
            shuffle = False
        workers = self.args.workers if mode == 'train' else self.args.workers * 2
        return build_dataloader(dataset, batch_size, workers, shuffle, rank)  # return dataloader

    def preprocess_batch(self, batch):
        """Preprocesses a batch of images by scaling and converting to float."""
        batch['img'] = batch['img'].to(self.device, non_blocking=True).float() / 255
        return batch

    def set_model_attributes(self):
        """nl = de_parallel(self.model).model[-1].nl  # number of detection layers (to scale hyps)."""
        # self.args.box *= 3 / nl  # scale to layers
        # self.args.cls *= self.data["nc"] / 80 * 3 / nl  # scale to classes and layers
        # self.args.cls *= (self.args.imgsz / 640) ** 2 * 3 / nl  # scale to image size and layers
        self.model.nc = self.data['nc']  # attach number of classes to model
        self.model.names = self.data['names']  # attach class names to model
        self.model.args = self.args  # attach hyperparameters to model
        # TODO: self.model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc

    def get_model(self, cfg=None, weights=None, verbose=True):
        """Return a YOLO detection model."""
        model = DetectionModel(cfg, nc=self.data['nc'], verbose=verbose and RANK == -1)
        if weights:
            model.load(weights)
        return model

    def get_validator(self):
        """Returns a DetectionValidator for YOLO model validation."""
        self.loss_names = 'box_loss', 'cls_loss', 'dfl_loss'
        return yolo.detect.DetectionValidator(self.test_loader, save_dir=self.save_dir, args=copy(self.args))

    def label_loss_items(self, loss_items=None, prefix='train'):
        """
        Returns a loss dict with labelled training loss items tensor. Not needed for classification but necessary for
        segmentation & detection
        """
        keys = [f'{prefix}/{x}' for x in self.loss_names]
        if loss_items is not None:
            loss_items = [round(float(x), 5) for x in loss_items]  # convert tensors to 5 decimal place floats
            return dict(zip(keys, loss_items))
        else:
            return keys

    def progress_string(self):
        """Returns a formatted string of training progress with epoch, GPU memory, loss, instances and size."""
        return ('\n' + '%11s' *
                (4 + len(self.loss_names))) % ('Epoch', 'GPU_mem', *self.loss_names, 'Instances', 'Size')

    def plot_training_samples(self, batch, ni):
        """Plots training samples with their annotations."""
        plot_images(images=batch['img'],
                    batch_idx=batch['batch_idx'],
                    cls=batch['cls'].squeeze(-1),
                    bboxes=batch['bboxes'],
                    paths=batch['im_file'],
                    fname=self.save_dir / f'train_batch{ni}.jpg',
                    on_plot=self.on_plot)

    def plot_metrics(self):
        """Plots metrics from a CSV file."""
        plot_results(file=self.csv, on_plot=self.on_plot)  # save results.png

    def plot_training_labels(self):
        """Create a labeled training plot of the YOLO model."""
        boxes = np.concatenate([lb['bboxes'] for lb in self.train_loader.dataset.labels], 0)
        cls = np.concatenate([lb['cls'] for lb in self.train_loader.dataset.labels], 0)
        plot_labels(boxes, cls.squeeze(), names=self.data['names'], save_dir=self.save_dir, on_plot=self.on_plot)


if __name__ == '__main__':

    trainer = DetectionTrainer()
    trainer.train()

按照我这么写，如果训练中断，那么resume肯定是要报错的，报错我在上个博客提到过，这个版本我将代码优化了一版如下：

def check_resume(self, overrides):
    """Check if resume checkpoint exists and update arguments accordingly."""
    resume = self.args.resume
    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
            self.args = get_cfg(ckpt_args)
            self.args.model = str(last)  # reinstate model
            if overrides:
                for k in 'imgsz', 'batch':  # allow arg updates to reduce memory on resume if crashed due to CUDA OOM
                    if k in overrides:
                        print(k)
                        setattr(self.args, k, overrides[k])
            else:
                print("do not have arg updates")

        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

这里增加了判断，overrides默认是None，如果训练不传递参数，那么就会进入这个判断的else，如果传了就会更新对应的’imgsz’, 'batch’这两个值。
至于default.yaml只需要将resume 设置为1或者0即可。