Skip to content

Référence pour ultralytics/models/yolo/classify/val.py

Note

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



ultralytics.models.yolo.classify.val.ClassificationValidator

Bases : BaseValidator

Une classe étendant la classe BaseValidator pour la validation basée sur un modèle de classification.

Notes
  • Les modèles de classification Torchvision peuvent Ă©galement ĂŞtre transmis Ă  l'argument 'model', c'est-Ă -dire model='resnet18'.
Exemple
from ultralytics.models.yolo.classify import ClassificationValidator

args = dict(model='yolov8n-cls.pt', data='imagenet10')
validator = ClassificationValidator(args=args)
validator()
Code source dans ultralytics/models/yolo/classify/val.py
class ClassificationValidator(BaseValidator):
    """
    A class extending the BaseValidator class for validation based on a classification model.

    Notes:
        - Torchvision classification models can also be passed to the 'model' argument, i.e. model='resnet18'.

    Example:
        ```python
        from ultralytics.models.yolo.classify import ClassificationValidator

        args = dict(model='yolov8n-cls.pt', data='imagenet10')
        validator = ClassificationValidator(args=args)
        validator()
        ```
    """

    def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None):
        """Initializes ClassificationValidator instance with args, dataloader, save_dir, and progress bar."""
        super().__init__(dataloader, save_dir, pbar, args, _callbacks)
        self.targets = None
        self.pred = None
        self.args.task = "classify"
        self.metrics = ClassifyMetrics()

    def get_desc(self):
        """Returns a formatted string summarizing classification metrics."""
        return ("%22s" + "%11s" * 2) % ("classes", "top1_acc", "top5_acc")

    def init_metrics(self, model):
        """Initialize confusion matrix, class names, and top-1 and top-5 accuracy."""
        self.names = model.names
        self.nc = len(model.names)
        self.confusion_matrix = ConfusionMatrix(nc=self.nc, conf=self.args.conf, task="classify")
        self.pred = []
        self.targets = []

    def preprocess(self, batch):
        """Preprocesses input batch and returns it."""
        batch["img"] = batch["img"].to(self.device, non_blocking=True)
        batch["img"] = batch["img"].half() if self.args.half else batch["img"].float()
        batch["cls"] = batch["cls"].to(self.device)
        return batch

    def update_metrics(self, preds, batch):
        """Updates running metrics with model predictions and batch targets."""
        n5 = min(len(self.names), 5)
        self.pred.append(preds.argsort(1, descending=True)[:, :n5])
        self.targets.append(batch["cls"])

    def finalize_metrics(self, *args, **kwargs):
        """Finalizes metrics of the model such as confusion_matrix and speed."""
        self.confusion_matrix.process_cls_preds(self.pred, self.targets)
        if self.args.plots:
            for normalize in True, False:
                self.confusion_matrix.plot(
                    save_dir=self.save_dir, names=self.names.values(), normalize=normalize, on_plot=self.on_plot
                )
        self.metrics.speed = self.speed
        self.metrics.confusion_matrix = self.confusion_matrix
        self.metrics.save_dir = self.save_dir

    def get_stats(self):
        """Returns a dictionary of metrics obtained by processing targets and predictions."""
        self.metrics.process(self.targets, self.pred)
        return self.metrics.results_dict

    def build_dataset(self, img_path):
        """Creates and returns a ClassificationDataset instance using given image path and preprocessing parameters."""
        return ClassificationDataset(root=img_path, args=self.args, augment=False, prefix=self.args.split)

    def get_dataloader(self, dataset_path, batch_size):
        """Builds and returns a data loader for classification tasks with given parameters."""
        dataset = self.build_dataset(dataset_path)
        return build_dataloader(dataset, batch_size, self.args.workers, rank=-1)

    def print_results(self):
        """Prints evaluation metrics for YOLO object detection model."""
        pf = "%22s" + "%11.3g" * len(self.metrics.keys)  # print format
        LOGGER.info(pf % ("all", self.metrics.top1, self.metrics.top5))

    def plot_val_samples(self, batch, ni):
        """Plot validation image samples."""
        plot_images(
            images=batch["img"],
            batch_idx=torch.arange(len(batch["img"])),
            cls=batch["cls"].view(-1),  # warning: use .view(), not .squeeze() for Classify models
            fname=self.save_dir / f"val_batch{ni}_labels.jpg",
            names=self.names,
            on_plot=self.on_plot,
        )

    def plot_predictions(self, batch, preds, ni):
        """Plots predicted bounding boxes on input images and saves the result."""
        plot_images(
            batch["img"],
            batch_idx=torch.arange(len(batch["img"])),
            cls=torch.argmax(preds, dim=1),
            fname=self.save_dir / f"val_batch{ni}_pred.jpg",
            names=self.names,
            on_plot=self.on_plot,
        )  # pred

__init__(dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None)

Initialise l'instance de ClassificationValidator avec les arguments, le chargeur de données, le répertoire de sauvegarde et la barre de progression.

Code source dans ultralytics/models/yolo/classify/val.py
def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None):
    """Initializes ClassificationValidator instance with args, dataloader, save_dir, and progress bar."""
    super().__init__(dataloader, save_dir, pbar, args, _callbacks)
    self.targets = None
    self.pred = None
    self.args.task = "classify"
    self.metrics = ClassifyMetrics()

build_dataset(img_path)

Crée et renvoie une instance de ClassificationDataset en utilisant le chemin d'accès à l'image et les paramètres de prétraitement donnés.

Code source dans ultralytics/models/yolo/classify/val.py
def build_dataset(self, img_path):
    """Creates and returns a ClassificationDataset instance using given image path and preprocessing parameters."""
    return ClassificationDataset(root=img_path, args=self.args, augment=False, prefix=self.args.split)

finalize_metrics(*args, **kwargs)

Finalise les métriques du modèle telles que la matrice de confusion et la vitesse.

Code source dans ultralytics/models/yolo/classify/val.py
def finalize_metrics(self, *args, **kwargs):
    """Finalizes metrics of the model such as confusion_matrix and speed."""
    self.confusion_matrix.process_cls_preds(self.pred, self.targets)
    if self.args.plots:
        for normalize in True, False:
            self.confusion_matrix.plot(
                save_dir=self.save_dir, names=self.names.values(), normalize=normalize, on_plot=self.on_plot
            )
    self.metrics.speed = self.speed
    self.metrics.confusion_matrix = self.confusion_matrix
    self.metrics.save_dir = self.save_dir

get_dataloader(dataset_path, batch_size)

Construit et renvoie un chargeur de données pour les tâches de classification avec les paramètres donnés.

Code source dans ultralytics/models/yolo/classify/val.py
def get_dataloader(self, dataset_path, batch_size):
    """Builds and returns a data loader for classification tasks with given parameters."""
    dataset = self.build_dataset(dataset_path)
    return build_dataloader(dataset, batch_size, self.args.workers, rank=-1)

get_desc()

Renvoie une chaîne formatée résumant les métriques de classification.

Code source dans ultralytics/models/yolo/classify/val.py
def get_desc(self):
    """Returns a formatted string summarizing classification metrics."""
    return ("%22s" + "%11s" * 2) % ("classes", "top1_acc", "top5_acc")

get_stats()

Renvoie un dictionnaire de métriques obtenues en traitant les cibles et les prédictions.

Code source dans ultralytics/models/yolo/classify/val.py
def get_stats(self):
    """Returns a dictionary of metrics obtained by processing targets and predictions."""
    self.metrics.process(self.targets, self.pred)
    return self.metrics.results_dict

init_metrics(model)

Initialise la matrice de confusion, les noms des classes, et la précision du top-1 et du top-5.

Code source dans ultralytics/models/yolo/classify/val.py
def init_metrics(self, model):
    """Initialize confusion matrix, class names, and top-1 and top-5 accuracy."""
    self.names = model.names
    self.nc = len(model.names)
    self.confusion_matrix = ConfusionMatrix(nc=self.nc, conf=self.args.conf, task="classify")
    self.pred = []
    self.targets = []

plot_predictions(batch, preds, ni)

Trace les boîtes de délimitation prédites sur les images d'entrée et enregistre le résultat.

Code source dans ultralytics/models/yolo/classify/val.py
def plot_predictions(self, batch, preds, ni):
    """Plots predicted bounding boxes on input images and saves the result."""
    plot_images(
        batch["img"],
        batch_idx=torch.arange(len(batch["img"])),
        cls=torch.argmax(preds, dim=1),
        fname=self.save_dir / f"val_batch{ni}_pred.jpg",
        names=self.names,
        on_plot=self.on_plot,
    )  # pred

plot_val_samples(batch, ni)

Trace des Ă©chantillons d'images de validation.

Code source dans ultralytics/models/yolo/classify/val.py
def plot_val_samples(self, batch, ni):
    """Plot validation image samples."""
    plot_images(
        images=batch["img"],
        batch_idx=torch.arange(len(batch["img"])),
        cls=batch["cls"].view(-1),  # warning: use .view(), not .squeeze() for Classify models
        fname=self.save_dir / f"val_batch{ni}_labels.jpg",
        names=self.names,
        on_plot=self.on_plot,
    )

preprocess(batch)

Prétraite le lot d'entrée et le renvoie.

Code source dans ultralytics/models/yolo/classify/val.py
def preprocess(self, batch):
    """Preprocesses input batch and returns it."""
    batch["img"] = batch["img"].to(self.device, non_blocking=True)
    batch["img"] = batch["img"].half() if self.args.half else batch["img"].float()
    batch["cls"] = batch["cls"].to(self.device)
    return batch

print_results()

Imprime des métriques d'évaluation pour le modèle de détection d'objets YOLO .

Code source dans ultralytics/models/yolo/classify/val.py
def print_results(self):
    """Prints evaluation metrics for YOLO object detection model."""
    pf = "%22s" + "%11.3g" * len(self.metrics.keys)  # print format
    LOGGER.info(pf % ("all", self.metrics.top1, self.metrics.top5))

update_metrics(preds, batch)

Met à jour les mesures en cours avec les prédictions du modèle et les objectifs des lots.

Code source dans ultralytics/models/yolo/classify/val.py
def update_metrics(self, preds, batch):
    """Updates running metrics with model predictions and batch targets."""
    n5 = min(len(self.names), 5)
    self.pred.append(preds.argsort(1, descending=True)[:, :n5])
    self.targets.append(batch["cls"])





Créé le 2023-11-12, Mis à jour le 2023-11-25
Auteurs : glenn-jocher (3)