Skip to content

Référence pour ultralytics/engine/tuner.py

Note

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



ultralytics.engine.tuner.Tuner

Classe responsable de l'ajustement des hyperparamètres des modèles YOLO .

La classe fait évoluer les hyperparamètres du modèle YOLO sur un nombre donné d'itérations en les mutant en fonction de l'espace de recherche et en réentraînant le modèle pour évaluer leurs performances.

Attributs :

Nom Type Description
space dict

Espace de recherche hyperparamétrique contenant des limites et des facteurs d'échelle pour la mutation.

tune_dir Path

Répertoire où les journaux d'évolution et les résultats seront sauvegardés.

tune_csv Path

Chemin d'accès au fichier CSV dans lequel les journaux d'évolution sont enregistrés.

MĂ©thodes :

Nom Description
_mutate

dict) -> dict : Modifie les hyperparamètres donnés dans les limites spécifiées dans self.space.

__call__

Exécute l'évolution des hyperparamètres sur plusieurs itérations.

Exemple

Ajuste les hyperparamètres pour YOLOv8n sur COCO8 à imgsz=640 et epochs=30 pour 300 itérations de réglage.

from ultralytics import YOLO

model = YOLO('yolov8n.pt')
model.tune(data='coco8.yaml', epochs=10, iterations=300, optimizer='AdamW', plots=False, save=False, val=False)

Accorde-toi avec un espace de recherche personnalisé.

from ultralytics import YOLO

model = YOLO('yolov8n.pt')
model.tune(space={key1: val1, key2: val2})  # custom search space dictionary

Code source dans ultralytics/engine/tuner.py
class Tuner:
    """
    Class responsible for hyperparameter tuning of YOLO models.

    The class evolves YOLO model hyperparameters over a given number of iterations
    by mutating them according to the search space and retraining the model to evaluate their performance.

    Attributes:
        space (dict): Hyperparameter search space containing bounds and scaling factors for mutation.
        tune_dir (Path): Directory where evolution logs and results will be saved.
        tune_csv (Path): Path to the CSV file where evolution logs are saved.

    Methods:
        _mutate(hyp: dict) -> dict:
            Mutates the given hyperparameters within the bounds specified in `self.space`.

        __call__():
            Executes the hyperparameter evolution across multiple iterations.

    Example:
        Tune hyperparameters for YOLOv8n on COCO8 at imgsz=640 and epochs=30 for 300 tuning iterations.
        ```python
        from ultralytics import YOLO

        model = YOLO('yolov8n.pt')
        model.tune(data='coco8.yaml', epochs=10, iterations=300, optimizer='AdamW', plots=False, save=False, val=False)
        ```

        Tune with custom search space.
        ```python
        from ultralytics import YOLO

        model = YOLO('yolov8n.pt')
        model.tune(space={key1: val1, key2: val2})  # custom search space dictionary
        ```
    """

    def __init__(self, args=DEFAULT_CFG, _callbacks=None):
        """
        Initialize the Tuner with configurations.

        Args:
            args (dict, optional): Configuration for hyperparameter evolution.
        """
        self.space = args.pop("space", None) or {  # key: (min, max, gain(optional))
            # 'optimizer': tune.choice(['SGD', 'Adam', 'AdamW', 'NAdam', 'RAdam', 'RMSProp']),
            "lr0": (1e-5, 1e-1),  # initial learning rate (i.e. SGD=1E-2, Adam=1E-3)
            "lrf": (0.0001, 0.1),  # final OneCycleLR learning rate (lr0 * lrf)
            "momentum": (0.7, 0.98, 0.3),  # SGD momentum/Adam beta1
            "weight_decay": (0.0, 0.001),  # optimizer weight decay 5e-4
            "warmup_epochs": (0.0, 5.0),  # warmup epochs (fractions ok)
            "warmup_momentum": (0.0, 0.95),  # warmup initial momentum
            "box": (1.0, 20.0),  # box loss gain
            "cls": (0.2, 4.0),  # cls loss gain (scale with pixels)
            "dfl": (0.4, 6.0),  # dfl loss gain
            "hsv_h": (0.0, 0.1),  # image HSV-Hue augmentation (fraction)
            "hsv_s": (0.0, 0.9),  # image HSV-Saturation augmentation (fraction)
            "hsv_v": (0.0, 0.9),  # image HSV-Value augmentation (fraction)
            "degrees": (0.0, 45.0),  # image rotation (+/- deg)
            "translate": (0.0, 0.9),  # image translation (+/- fraction)
            "scale": (0.0, 0.95),  # image scale (+/- gain)
            "shear": (0.0, 10.0),  # image shear (+/- deg)
            "perspective": (0.0, 0.001),  # image perspective (+/- fraction), range 0-0.001
            "flipud": (0.0, 1.0),  # image flip up-down (probability)
            "fliplr": (0.0, 1.0),  # image flip left-right (probability)
            "mosaic": (0.0, 1.0),  # image mixup (probability)
            "mixup": (0.0, 1.0),  # image mixup (probability)
            "copy_paste": (0.0, 1.0),  # segment copy-paste (probability)
        }
        self.args = get_cfg(overrides=args)
        self.tune_dir = get_save_dir(self.args, name="tune")
        self.tune_csv = self.tune_dir / "tune_results.csv"
        self.callbacks = _callbacks or callbacks.get_default_callbacks()
        self.prefix = colorstr("Tuner: ")
        callbacks.add_integration_callbacks(self)
        LOGGER.info(
            f"{self.prefix}Initialized Tuner instance with 'tune_dir={self.tune_dir}'\n"
            f"{self.prefix}đź’ˇ Learn about tuning at https://docs.ultralytics.com/guides/hyperparameter-tuning"
        )

    def _mutate(self, parent="single", n=5, mutation=0.8, sigma=0.2):
        """
        Mutates the hyperparameters based on bounds and scaling factors specified in `self.space`.

        Args:
            parent (str): Parent selection method: 'single' or 'weighted'.
            n (int): Number of parents to consider.
            mutation (float): Probability of a parameter mutation in any given iteration.
            sigma (float): Standard deviation for Gaussian random number generator.

        Returns:
            (dict): A dictionary containing mutated hyperparameters.
        """
        if self.tune_csv.exists():  # if CSV file exists: select best hyps and mutate
            # Select parent(s)
            x = np.loadtxt(self.tune_csv, ndmin=2, delimiter=",", skiprows=1)
            fitness = x[:, 0]  # first column
            n = min(n, len(x))  # number of previous results to consider
            x = x[np.argsort(-fitness)][:n]  # top n mutations
            w = x[:, 0] - x[:, 0].min() + 1e-6  # weights (sum > 0)
            if parent == "single" or len(x) == 1:
                # x = x[random.randint(0, n - 1)]  # random selection
                x = x[random.choices(range(n), weights=w)[0]]  # weighted selection
            elif parent == "weighted":
                x = (x * w.reshape(n, 1)).sum(0) / w.sum()  # weighted combination

            # Mutate
            r = np.random  # method
            r.seed(int(time.time()))
            g = np.array([v[2] if len(v) == 3 else 1.0 for k, v in self.space.items()])  # gains 0-1
            ng = len(self.space)
            v = np.ones(ng)
            while all(v == 1):  # mutate until a change occurs (prevent duplicates)
                v = (g * (r.random(ng) < mutation) * r.randn(ng) * r.random() * sigma + 1).clip(0.3, 3.0)
            hyp = {k: float(x[i + 1] * v[i]) for i, k in enumerate(self.space.keys())}
        else:
            hyp = {k: getattr(self.args, k) for k in self.space.keys()}

        # Constrain to limits
        for k, v in self.space.items():
            hyp[k] = max(hyp[k], v[0])  # lower limit
            hyp[k] = min(hyp[k], v[1])  # upper limit
            hyp[k] = round(hyp[k], 5)  # significant digits

        return hyp

    def __call__(self, model=None, iterations=10, cleanup=True):
        """
        Executes the hyperparameter evolution process when the Tuner instance is called.

        This method iterates through the number of iterations, performing the following steps in each iteration:
        1. Load the existing hyperparameters or initialize new ones.
        2. Mutate the hyperparameters using the `mutate` method.
        3. Train a YOLO model with the mutated hyperparameters.
        4. Log the fitness score and mutated hyperparameters to a CSV file.

        Args:
           model (Model): A pre-initialized YOLO model to be used for training.
           iterations (int): The number of generations to run the evolution for.
           cleanup (bool): Whether to delete iteration weights to reduce storage space used during tuning.

        Note:
           The method utilizes the `self.tune_csv` Path object to read and log hyperparameters and fitness scores.
           Ensure this path is set correctly in the Tuner instance.
        """

        t0 = time.time()
        best_save_dir, best_metrics = None, None
        (self.tune_dir / "weights").mkdir(parents=True, exist_ok=True)
        for i in range(iterations):
            # Mutate hyperparameters
            mutated_hyp = self._mutate()
            LOGGER.info(f"{self.prefix}Starting iteration {i + 1}/{iterations} with hyperparameters: {mutated_hyp}")

            metrics = {}
            train_args = {**vars(self.args), **mutated_hyp}
            save_dir = get_save_dir(get_cfg(train_args))
            weights_dir = save_dir / "weights"
            ckpt_file = weights_dir / ("best.pt" if (weights_dir / "best.pt").exists() else "last.pt")
            try:
                # Train YOLO model with mutated hyperparameters (run in subprocess to avoid dataloader hang)
                cmd = ["yolo", "train", *(f"{k}={v}" for k, v in train_args.items())]
                return_code = subprocess.run(cmd, check=True).returncode
                metrics = torch.load(ckpt_file)["train_metrics"]
                assert return_code == 0, "training failed"

            except Exception as e:
                LOGGER.warning(f"WARNING ❌️ training failure for hyperparameter tuning iteration {i + 1}\n{e}")

            # Save results and mutated_hyp to CSV
            fitness = metrics.get("fitness", 0.0)
            log_row = [round(fitness, 5)] + [mutated_hyp[k] for k in self.space.keys()]
            headers = "" if self.tune_csv.exists() else (",".join(["fitness"] + list(self.space.keys())) + "\n")
            with open(self.tune_csv, "a") as f:
                f.write(headers + ",".join(map(str, log_row)) + "\n")

            # Get best results
            x = np.loadtxt(self.tune_csv, ndmin=2, delimiter=",", skiprows=1)
            fitness = x[:, 0]  # first column
            best_idx = fitness.argmax()
            best_is_current = best_idx == i
            if best_is_current:
                best_save_dir = save_dir
                best_metrics = {k: round(v, 5) for k, v in metrics.items()}
                for ckpt in weights_dir.glob("*.pt"):
                    shutil.copy2(ckpt, self.tune_dir / "weights")
            elif cleanup:
                shutil.rmtree(ckpt_file.parent)  # remove iteration weights/ dir to reduce storage space

            # Plot tune results
            plot_tune_results(self.tune_csv)

            # Save and print tune results
            header = (
                f'{self.prefix}{i + 1}/{iterations} iterations complete âś… ({time.time() - t0:.2f}s)\n'
                f'{self.prefix}Results saved to {colorstr("bold", self.tune_dir)}\n'
                f'{self.prefix}Best fitness={fitness[best_idx]} observed at iteration {best_idx + 1}\n'
                f'{self.prefix}Best fitness metrics are {best_metrics}\n'
                f'{self.prefix}Best fitness model is {best_save_dir}\n'
                f'{self.prefix}Best fitness hyperparameters are printed below.\n'
            )
            LOGGER.info("\n" + header)
            data = {k: float(x[best_idx, i + 1]) for i, k in enumerate(self.space.keys())}
            yaml_save(
                self.tune_dir / "best_hyperparameters.yaml",
                data=data,
                header=remove_colorstr(header.replace(self.prefix, "# ")) + "\n",
            )
            yaml_print(self.tune_dir / "best_hyperparameters.yaml")

__call__(model=None, iterations=10, cleanup=True)

Exécute le processus d'évolution des hyperparamètres lorsque l'instance Tuner est appelée.

Cette méthode itère sur le nombre d'itérations, en effectuant les étapes suivantes à chaque itération : 1. Charge les hyperparamètres existants ou initialise de nouveaux hyperparamètres. 2. Modifie les hyperparamètres à l'aide de la fonction mutate méthode. 3. Entraîne un modèle YOLO avec les hyperparamètres modifiés. 4. Enregistre le score de fitness et les hyperparamètres mutés dans un fichier CSV.

Paramètres :

Nom Type Description DĂ©faut
model Model

Un modèle pré-initialisé YOLO à utiliser pour la formation.

None
iterations int

Le nombre de générations pour lesquelles l'évolution doit être exécutée.

10
cleanup bool

S'il faut supprimer les poids d'itération pour réduire l'espace de stockage utilisé pendant l'accord.

True
Note

La méthode utilise le self.tune_csv Objet de chemin pour lire et enregistrer les hyperparamètres et les scores de fitness. Assure-toi que ce chemin est correctement défini dans l'instance de l'accordeur.

Code source dans ultralytics/engine/tuner.py
def __call__(self, model=None, iterations=10, cleanup=True):
    """
    Executes the hyperparameter evolution process when the Tuner instance is called.

    This method iterates through the number of iterations, performing the following steps in each iteration:
    1. Load the existing hyperparameters or initialize new ones.
    2. Mutate the hyperparameters using the `mutate` method.
    3. Train a YOLO model with the mutated hyperparameters.
    4. Log the fitness score and mutated hyperparameters to a CSV file.

    Args:
       model (Model): A pre-initialized YOLO model to be used for training.
       iterations (int): The number of generations to run the evolution for.
       cleanup (bool): Whether to delete iteration weights to reduce storage space used during tuning.

    Note:
       The method utilizes the `self.tune_csv` Path object to read and log hyperparameters and fitness scores.
       Ensure this path is set correctly in the Tuner instance.
    """

    t0 = time.time()
    best_save_dir, best_metrics = None, None
    (self.tune_dir / "weights").mkdir(parents=True, exist_ok=True)
    for i in range(iterations):
        # Mutate hyperparameters
        mutated_hyp = self._mutate()
        LOGGER.info(f"{self.prefix}Starting iteration {i + 1}/{iterations} with hyperparameters: {mutated_hyp}")

        metrics = {}
        train_args = {**vars(self.args), **mutated_hyp}
        save_dir = get_save_dir(get_cfg(train_args))
        weights_dir = save_dir / "weights"
        ckpt_file = weights_dir / ("best.pt" if (weights_dir / "best.pt").exists() else "last.pt")
        try:
            # Train YOLO model with mutated hyperparameters (run in subprocess to avoid dataloader hang)
            cmd = ["yolo", "train", *(f"{k}={v}" for k, v in train_args.items())]
            return_code = subprocess.run(cmd, check=True).returncode
            metrics = torch.load(ckpt_file)["train_metrics"]
            assert return_code == 0, "training failed"

        except Exception as e:
            LOGGER.warning(f"WARNING ❌️ training failure for hyperparameter tuning iteration {i + 1}\n{e}")

        # Save results and mutated_hyp to CSV
        fitness = metrics.get("fitness", 0.0)
        log_row = [round(fitness, 5)] + [mutated_hyp[k] for k in self.space.keys()]
        headers = "" if self.tune_csv.exists() else (",".join(["fitness"] + list(self.space.keys())) + "\n")
        with open(self.tune_csv, "a") as f:
            f.write(headers + ",".join(map(str, log_row)) + "\n")

        # Get best results
        x = np.loadtxt(self.tune_csv, ndmin=2, delimiter=",", skiprows=1)
        fitness = x[:, 0]  # first column
        best_idx = fitness.argmax()
        best_is_current = best_idx == i
        if best_is_current:
            best_save_dir = save_dir
            best_metrics = {k: round(v, 5) for k, v in metrics.items()}
            for ckpt in weights_dir.glob("*.pt"):
                shutil.copy2(ckpt, self.tune_dir / "weights")
        elif cleanup:
            shutil.rmtree(ckpt_file.parent)  # remove iteration weights/ dir to reduce storage space

        # Plot tune results
        plot_tune_results(self.tune_csv)

        # Save and print tune results
        header = (
            f'{self.prefix}{i + 1}/{iterations} iterations complete âś… ({time.time() - t0:.2f}s)\n'
            f'{self.prefix}Results saved to {colorstr("bold", self.tune_dir)}\n'
            f'{self.prefix}Best fitness={fitness[best_idx]} observed at iteration {best_idx + 1}\n'
            f'{self.prefix}Best fitness metrics are {best_metrics}\n'
            f'{self.prefix}Best fitness model is {best_save_dir}\n'
            f'{self.prefix}Best fitness hyperparameters are printed below.\n'
        )
        LOGGER.info("\n" + header)
        data = {k: float(x[best_idx, i + 1]) for i, k in enumerate(self.space.keys())}
        yaml_save(
            self.tune_dir / "best_hyperparameters.yaml",
            data=data,
            header=remove_colorstr(header.replace(self.prefix, "# ")) + "\n",
        )
        yaml_print(self.tune_dir / "best_hyperparameters.yaml")

__init__(args=DEFAULT_CFG, _callbacks=None)

Initialise l'accordeur avec les configurations.

Paramètres :

Nom Type Description DĂ©faut
args dict

Configuration pour l'évolution des hyperparamètres.

DEFAULT_CFG
Code source dans ultralytics/engine/tuner.py
def __init__(self, args=DEFAULT_CFG, _callbacks=None):
    """
    Initialize the Tuner with configurations.

    Args:
        args (dict, optional): Configuration for hyperparameter evolution.
    """
    self.space = args.pop("space", None) or {  # key: (min, max, gain(optional))
        # 'optimizer': tune.choice(['SGD', 'Adam', 'AdamW', 'NAdam', 'RAdam', 'RMSProp']),
        "lr0": (1e-5, 1e-1),  # initial learning rate (i.e. SGD=1E-2, Adam=1E-3)
        "lrf": (0.0001, 0.1),  # final OneCycleLR learning rate (lr0 * lrf)
        "momentum": (0.7, 0.98, 0.3),  # SGD momentum/Adam beta1
        "weight_decay": (0.0, 0.001),  # optimizer weight decay 5e-4
        "warmup_epochs": (0.0, 5.0),  # warmup epochs (fractions ok)
        "warmup_momentum": (0.0, 0.95),  # warmup initial momentum
        "box": (1.0, 20.0),  # box loss gain
        "cls": (0.2, 4.0),  # cls loss gain (scale with pixels)
        "dfl": (0.4, 6.0),  # dfl loss gain
        "hsv_h": (0.0, 0.1),  # image HSV-Hue augmentation (fraction)
        "hsv_s": (0.0, 0.9),  # image HSV-Saturation augmentation (fraction)
        "hsv_v": (0.0, 0.9),  # image HSV-Value augmentation (fraction)
        "degrees": (0.0, 45.0),  # image rotation (+/- deg)
        "translate": (0.0, 0.9),  # image translation (+/- fraction)
        "scale": (0.0, 0.95),  # image scale (+/- gain)
        "shear": (0.0, 10.0),  # image shear (+/- deg)
        "perspective": (0.0, 0.001),  # image perspective (+/- fraction), range 0-0.001
        "flipud": (0.0, 1.0),  # image flip up-down (probability)
        "fliplr": (0.0, 1.0),  # image flip left-right (probability)
        "mosaic": (0.0, 1.0),  # image mixup (probability)
        "mixup": (0.0, 1.0),  # image mixup (probability)
        "copy_paste": (0.0, 1.0),  # segment copy-paste (probability)
    }
    self.args = get_cfg(overrides=args)
    self.tune_dir = get_save_dir(self.args, name="tune")
    self.tune_csv = self.tune_dir / "tune_results.csv"
    self.callbacks = _callbacks or callbacks.get_default_callbacks()
    self.prefix = colorstr("Tuner: ")
    callbacks.add_integration_callbacks(self)
    LOGGER.info(
        f"{self.prefix}Initialized Tuner instance with 'tune_dir={self.tune_dir}'\n"
        f"{self.prefix}đź’ˇ Learn about tuning at https://docs.ultralytics.com/guides/hyperparameter-tuning"
    )





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