Skip to content

Référence pour ultralytics/models/yolo/detect/train.py

Note

Ce fichier est disponible à l'adresse https://github.com/ultralytics/ ultralytics/blob/main/ ultralytics/models/ yolo/detect/train .py. Si tu repères un problème, aide à le corriger en contribuant à une Pull Request 🛠️. Merci 🙏 !



ultralytics.models.yolo.detect.train.DetectionTrainer

Bases : BaseTrainer

Une classe étendant la classe BaseTrainer pour une formation basée sur un modèle de détection.

Exemple
from ultralytics.models.yolo.detect import DetectionTrainer

args = dict(model='yolov8n.pt', data='coco8.yaml', epochs=3)
trainer = DetectionTrainer(overrides=args)
trainer.train()
Code source dans ultralytics/models/yolo/detect/train.py
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"}, f"Mode must be 'train' or 'val', not {mode}."
        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
        if self.args.multi_scale:
            imgs = batch["img"]
            sz = (
                random.randrange(self.args.imgsz * 0.5, self.args.imgsz * 1.5 + self.stride)
                // self.stride
                * self.stride
            )  # size
            sf = sz / max(imgs.shape[2:])  # scale factor
            if sf != 1:
                ns = [
                    math.ceil(x * sf / self.stride) * self.stride for x in imgs.shape[2:]
                ]  # new shape (stretched to gs-multiple)
                imgs = nn.functional.interpolate(imgs, size=ns, mode="bilinear", align_corners=False)
            batch["img"] = imgs
        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), _callbacks=self.callbacks
        )

    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)

build_dataset(img_path, mode='train', batch=None)

Construis l'ensemble de données YOLO .

Paramètres :

Nom Type Description DĂ©faut
img_path str

Chemin d'accès au dossier contenant les images.

requis
mode str

train ou val les utilisateurs peuvent personnaliser différentes augmentations pour chaque mode.

'train'
batch int

Taille des lots, c'est pour rect. La valeur par défaut est Aucun.

None
Code source dans ultralytics/models/yolo/detect/train.py
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)

get_dataloader(dataset_path, batch_size=16, rank=0, mode='train')

Construit et renvoie le chargeur de données.

Code source dans ultralytics/models/yolo/detect/train.py
def get_dataloader(self, dataset_path, batch_size=16, rank=0, mode="train"):
    """Construct and return dataloader."""
    assert mode in {"train", "val"}, f"Mode must be 'train' or 'val', not {mode}."
    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

get_model(cfg=None, weights=None, verbose=True)

Retourne un modèle de détection YOLO .

Code source dans ultralytics/models/yolo/detect/train.py
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

get_validator()

Renvoie un DetectionValidator pour la validation du modèle YOLO .

Code source dans ultralytics/models/yolo/detect/train.py
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), _callbacks=self.callbacks
    )

label_loss_items(loss_items=None, prefix='train')

Renvoie un dict de perte avec des éléments de perte d'entraînement étiquetés tensor.

Pas nécessaire pour la classification mais nécessaire pour la segmentation et la détection.

Code source dans ultralytics/models/yolo/detect/train.py
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

plot_metrics()

Trace les métriques à partir d'un fichier CSV.

Code source dans ultralytics/models/yolo/detect/train.py
def plot_metrics(self):
    """Plots metrics from a CSV file."""
    plot_results(file=self.csv, on_plot=self.on_plot)  # save results.png

plot_training_labels()

Crée un graphique d'apprentissage étiqueté du modèle YOLO .

Code source dans ultralytics/models/yolo/detect/train.py
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)

plot_training_samples(batch, ni)

Représente les échantillons de formation avec leurs annotations.

Code source dans ultralytics/models/yolo/detect/train.py
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,
    )

preprocess_batch(batch)

Prétraite un lot d'images en les mettant à l'échelle et en les convertissant en format flottant.

Code source dans ultralytics/models/yolo/detect/train.py
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
    if self.args.multi_scale:
        imgs = batch["img"]
        sz = (
            random.randrange(self.args.imgsz * 0.5, self.args.imgsz * 1.5 + self.stride)
            // self.stride
            * self.stride
        )  # size
        sf = sz / max(imgs.shape[2:])  # scale factor
        if sf != 1:
            ns = [
                math.ceil(x * sf / self.stride) * self.stride for x in imgs.shape[2:]
            ]  # new shape (stretched to gs-multiple)
            imgs = nn.functional.interpolate(imgs, size=ns, mode="bilinear", align_corners=False)
        batch["img"] = imgs
    return batch

progress_string()

Renvoie une chaîne formatée de la progression de l'entraînement avec l'époque, GPU memory, la perte, les instances et la taille.

Code source dans ultralytics/models/yolo/detect/train.py
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",
    )

set_model_attributes()

Nl = de_parallel(self.model).model[-1].nl # nombre de couches de détection (pour mettre à l'échelle les hyps).

Code source dans ultralytics/models/yolo/detect/train.py
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





Création : 2023-11-12, mise à jour : 2024-06-02
Auteur(s) : glenn-jocher (5), Burhan-Q (1)