Skip to content

Reference for ultralytics/models/yolo/classify/train.py

Note

This file is available at https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/classify/train.py. If you spot a problem please help fix it by contributing a Pull Request 🛠️. Thank you 🙏!


ultralytics.models.yolo.classify.train.ClassificationTrainer

ClassificationTrainer(cfg=DEFAULT_CFG, overrides=None, _callbacks=None)

Bases: BaseTrainer

A class extending the BaseTrainer class for training based on a classification model.

Notes
  • Torchvision classification models can also be passed to the 'model' argument, i.e. model='resnet18'.
Example
from ultralytics.models.yolo.classify import ClassificationTrainer

args = dict(model="yolov8n-cls.pt", data="imagenet10", epochs=3)
trainer = ClassificationTrainer(overrides=args)
trainer.train()
Source code in ultralytics/models/yolo/classify/train.py
def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
    """Initialize a ClassificationTrainer object with optional configuration overrides and callbacks."""
    if overrides is None:
        overrides = {}
    overrides["task"] = "classify"
    if overrides.get("imgsz") is None:
        overrides["imgsz"] = 224
    super().__init__(cfg, overrides, _callbacks)

build_dataset

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

Creates a ClassificationDataset instance given an image path, and mode (train/test etc.).

Source code in ultralytics/models/yolo/classify/train.py
def build_dataset(self, img_path, mode="train", batch=None):
    """Creates a ClassificationDataset instance given an image path, and mode (train/test etc.)."""
    return ClassificationDataset(root=img_path, args=self.args, augment=mode == "train", prefix=mode)

final_eval

final_eval()

Evaluate trained model and save validation results.

Source code in ultralytics/models/yolo/classify/train.py
def final_eval(self):
    """Evaluate trained model and save validation results."""
    for f in self.last, self.best:
        if f.exists():
            strip_optimizer(f)  # strip optimizers
            if f is self.best:
                LOGGER.info(f"\nValidating {f}...")
                self.validator.args.data = self.args.data
                self.validator.args.plots = self.args.plots
                self.metrics = self.validator(model=f)
                self.metrics.pop("fitness", None)
                self.run_callbacks("on_fit_epoch_end")

get_dataloader

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

Returns PyTorch DataLoader with transforms to preprocess images for inference.

Source code in ultralytics/models/yolo/classify/train.py
def get_dataloader(self, dataset_path, batch_size=16, rank=0, mode="train"):
    """Returns PyTorch DataLoader with transforms to preprocess images for inference."""
    with torch_distributed_zero_first(rank):  # init dataset *.cache only once if DDP
        dataset = self.build_dataset(dataset_path, mode)

    loader = build_dataloader(dataset, batch_size, self.args.workers, rank=rank)
    # Attach inference transforms
    if mode != "train":
        if is_parallel(self.model):
            self.model.module.transforms = loader.dataset.torch_transforms
        else:
            self.model.transforms = loader.dataset.torch_transforms
    return loader

get_model

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

Returns a modified PyTorch model configured for training YOLO.

Source code in ultralytics/models/yolo/classify/train.py
def get_model(self, cfg=None, weights=None, verbose=True):
    """Returns a modified PyTorch model configured for training YOLO."""
    model = ClassificationModel(cfg, nc=self.data["nc"], verbose=verbose and RANK == -1)
    if weights:
        model.load(weights)

    for m in model.modules():
        if not self.args.pretrained and hasattr(m, "reset_parameters"):
            m.reset_parameters()
        if isinstance(m, torch.nn.Dropout) and self.args.dropout:
            m.p = self.args.dropout  # set dropout
    for p in model.parameters():
        p.requires_grad = True  # for training
    return model

get_validator

get_validator()

Returns an instance of ClassificationValidator for validation.

Source code in ultralytics/models/yolo/classify/train.py
def get_validator(self):
    """Returns an instance of ClassificationValidator for validation."""
    self.loss_names = ["loss"]
    return yolo.classify.ClassificationValidator(
        self.test_loader, self.save_dir, args=copy(self.args), _callbacks=self.callbacks
    )

label_loss_items

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

Returns a loss dict with labelled training loss items tensor.

Not needed for classification but necessary for segmentation & detection

Source code in ultralytics/models/yolo/classify/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 None:
        return keys
    loss_items = [round(float(loss_items), 5)]
    return dict(zip(keys, loss_items))

plot_metrics

plot_metrics()

Plots metrics from a CSV file.

Source code in ultralytics/models/yolo/classify/train.py
def plot_metrics(self):
    """Plots metrics from a CSV file."""
    plot_results(file=self.csv, classify=True, on_plot=self.on_plot)  # save results.png

plot_training_samples

plot_training_samples(batch, ni)

Plots training samples with their annotations.

Source code in ultralytics/models/yolo/classify/train.py
def plot_training_samples(self, batch, ni):
    """Plots training samples with their annotations."""
    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"train_batch{ni}.jpg",
        on_plot=self.on_plot,
    )

preprocess_batch

preprocess_batch(batch)

Preprocesses a batch of images and classes.

Source code in ultralytics/models/yolo/classify/train.py
def preprocess_batch(self, batch):
    """Preprocesses a batch of images and classes."""
    batch["img"] = batch["img"].to(self.device)
    batch["cls"] = batch["cls"].to(self.device)
    return batch

progress_string

progress_string()

Returns a formatted string showing training progress.

Source code in ultralytics/models/yolo/classify/train.py
def progress_string(self):
    """Returns a formatted string showing training progress."""
    return ("\n" + "%11s" * (4 + len(self.loss_names))) % (
        "Epoch",
        "GPU_mem",
        *self.loss_names,
        "Instances",
        "Size",
    )

set_model_attributes

set_model_attributes()

Set the YOLO model's class names from the loaded dataset.

Source code in ultralytics/models/yolo/classify/train.py
def set_model_attributes(self):
    """Set the YOLO model's class names from the loaded dataset."""
    self.model.names = self.data["names"]

setup_model

setup_model()

Load, create or download model for any task.

Source code in ultralytics/models/yolo/classify/train.py
def setup_model(self):
    """Load, create or download model for any task."""
    import torchvision  # scope for faster 'import ultralytics'

    if str(self.model) in torchvision.models.__dict__:
        self.model = torchvision.models.__dict__[self.model](
            weights="IMAGENET1K_V1" if self.args.pretrained else None
        )
        ckpt = None
    else:
        ckpt = super().setup_model()
    ClassificationModel.reshape_outputs(self.model, self.data["nc"])
    return ckpt



📅 Created 11 months ago ✏️ Updated 1 month ago