dgenerate-ultralytics-headless 8.3.134__py3-none-any.whl

ultralytics/models/utils/ops.py

@@ -0,0 +1,268 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from scipy.optimize import linear_sum_assignment
+
+from ultralytics.utils.metrics import bbox_iou
+from ultralytics.utils.ops import xywh2xyxy, xyxy2xywh
+
+
+class HungarianMatcher(nn.Module):
+    """
+    A module implementing the HungarianMatcher, which is a differentiable module to solve the assignment problem in an
+    end-to-end fashion.
+
+    HungarianMatcher performs optimal assignment over the predicted and ground truth bounding boxes using a cost
+    function that considers classification scores, bounding box coordinates, and optionally, mask predictions.
+
+    Attributes:
+        cost_gain (dict): Dictionary of cost coefficients: 'class', 'bbox', 'giou', 'mask', and 'dice'.
+        use_fl (bool): Indicates whether to use Focal Loss for the classification cost calculation.
+        with_mask (bool): Indicates whether the model makes mask predictions.
+        num_sample_points (int): The number of sample points used in mask cost calculation.
+        alpha (float): The alpha factor in Focal Loss calculation.
+        gamma (float): The gamma factor in Focal Loss calculation.
+
+    Methods:
+        forward: Computes the assignment between predictions and ground truths for a batch.
+        _cost_mask: Computes the mask cost and dice cost if masks are predicted.
+    """
+
+    def __init__(self, cost_gain=None, use_fl=True, with_mask=False, num_sample_points=12544, alpha=0.25, gamma=2.0):
+        """
+        Initialize a HungarianMatcher module for optimal assignment of predicted and ground truth bounding boxes.
+
+        The HungarianMatcher uses a cost function that considers classification scores, bounding box coordinates,
+        and optionally mask predictions to perform optimal bipartite matching between predictions and ground truths.
+
+        Args:
+            cost_gain (dict, optional): Dictionary of cost coefficients for different components of the matching cost.
+                Should contain keys 'class', 'bbox', 'giou', 'mask', and 'dice'.
+            use_fl (bool, optional): Whether to use Focal Loss for the classification cost calculation.
+            with_mask (bool, optional): Whether the model makes mask predictions.
+            num_sample_points (int, optional): Number of sample points used in mask cost calculation.
+            alpha (float, optional): Alpha factor in Focal Loss calculation.
+            gamma (float, optional): Gamma factor in Focal Loss calculation.
+        """
+        super().__init__()
+        if cost_gain is None:
+            cost_gain = {"class": 1, "bbox": 5, "giou": 2, "mask": 1, "dice": 1}
+        self.cost_gain = cost_gain
+        self.use_fl = use_fl
+        self.with_mask = with_mask
+        self.num_sample_points = num_sample_points
+        self.alpha = alpha
+        self.gamma = gamma
+
+    def forward(self, pred_bboxes, pred_scores, gt_bboxes, gt_cls, gt_groups, masks=None, gt_mask=None):
+        """
+        Forward pass for HungarianMatcher. Computes costs based on prediction and ground truth and finds the optimal
+        matching between predictions and ground truth based on these costs.
+
+        Args:
+            pred_bboxes (torch.Tensor): Predicted bounding boxes with shape (batch_size, num_queries, 4).
+            pred_scores (torch.Tensor): Predicted scores with shape (batch_size, num_queries, num_classes).
+            gt_cls (torch.Tensor): Ground truth classes with shape (num_gts, ).
+            gt_bboxes (torch.Tensor): Ground truth bounding boxes with shape (num_gts, 4).
+            gt_groups (List[int]): List of length equal to batch size, containing the number of ground truths for
+                each image.
+            masks (torch.Tensor, optional): Predicted masks with shape (batch_size, num_queries, height, width).
+            gt_mask (List[torch.Tensor], optional): List of ground truth masks, each with shape (num_masks, Height, Width).
+
+        Returns:
+            (List[Tuple[torch.Tensor, torch.Tensor]]): A list of size batch_size, each element is a tuple (index_i, index_j), where:
+                - index_i is the tensor of indices of the selected predictions (in order)
+                - index_j is the tensor of indices of the corresponding selected ground truth targets (in order)
+                For each batch element, it holds:
+                    len(index_i) = len(index_j) = min(num_queries, num_target_boxes)
+        """
+        bs, nq, nc = pred_scores.shape
+
+        if sum(gt_groups) == 0:
+            return [(torch.tensor([], dtype=torch.long), torch.tensor([], dtype=torch.long)) for _ in range(bs)]
+
+        # We flatten to compute the cost matrices in a batch
+        # (batch_size * num_queries, num_classes)
+        pred_scores = pred_scores.detach().view(-1, nc)
+        pred_scores = F.sigmoid(pred_scores) if self.use_fl else F.softmax(pred_scores, dim=-1)
+        # (batch_size * num_queries, 4)
+        pred_bboxes = pred_bboxes.detach().view(-1, 4)
+
+        # Compute the classification cost
+        pred_scores = pred_scores[:, gt_cls]
+        if self.use_fl:
+            neg_cost_class = (1 - self.alpha) * (pred_scores**self.gamma) * (-(1 - pred_scores + 1e-8).log())
+            pos_cost_class = self.alpha * ((1 - pred_scores) ** self.gamma) * (-(pred_scores + 1e-8).log())
+            cost_class = pos_cost_class - neg_cost_class
+        else:
+            cost_class = -pred_scores
+
+        # Compute the L1 cost between boxes
+        cost_bbox = (pred_bboxes.unsqueeze(1) - gt_bboxes.unsqueeze(0)).abs().sum(-1)  # (bs*num_queries, num_gt)
+
+        # Compute the GIoU cost between boxes, (bs*num_queries, num_gt)
+        cost_giou = 1.0 - bbox_iou(pred_bboxes.unsqueeze(1), gt_bboxes.unsqueeze(0), xywh=True, GIoU=True).squeeze(-1)
+
+        # Final cost matrix
+        C = (
+            self.cost_gain["class"] * cost_class
+            + self.cost_gain["bbox"] * cost_bbox
+            + self.cost_gain["giou"] * cost_giou
+        )
+        # Compute the mask cost and dice cost
+        if self.with_mask:
+            C += self._cost_mask(bs, gt_groups, masks, gt_mask)
+
+        # Set invalid values (NaNs and infinities) to 0 (fixes ValueError: matrix contains invalid numeric entries)
+        C[C.isnan() | C.isinf()] = 0.0
+
+        C = C.view(bs, nq, -1).cpu()
+        indices = [linear_sum_assignment(c[i]) for i, c in enumerate(C.split(gt_groups, -1))]
+        gt_groups = torch.as_tensor([0, *gt_groups[:-1]]).cumsum_(0)  # (idx for queries, idx for gt)
+        return [
+            (torch.tensor(i, dtype=torch.long), torch.tensor(j, dtype=torch.long) + gt_groups[k])
+            for k, (i, j) in enumerate(indices)
+        ]
+
+    # This function is for future RT-DETR Segment models
+    # def _cost_mask(self, bs, num_gts, masks=None, gt_mask=None):
+    #     assert masks is not None and gt_mask is not None, 'Make sure the input has `mask` and `gt_mask`'
+    #     # all masks share the same set of points for efficient matching
+    #     sample_points = torch.rand([bs, 1, self.num_sample_points, 2])
+    #     sample_points = 2.0 * sample_points - 1.0
+    #
+    #     out_mask = F.grid_sample(masks.detach(), sample_points, align_corners=False).squeeze(-2)
+    #     out_mask = out_mask.flatten(0, 1)
+    #
+    #     tgt_mask = torch.cat(gt_mask).unsqueeze(1)
+    #     sample_points = torch.cat([a.repeat(b, 1, 1, 1) for a, b in zip(sample_points, num_gts) if b > 0])
+    #     tgt_mask = F.grid_sample(tgt_mask, sample_points, align_corners=False).squeeze([1, 2])
+    #
+    #     with torch.amp.autocast("cuda", enabled=False):
+    #         # binary cross entropy cost
+    #         pos_cost_mask = F.binary_cross_entropy_with_logits(out_mask, torch.ones_like(out_mask), reduction='none')
+    #         neg_cost_mask = F.binary_cross_entropy_with_logits(out_mask, torch.zeros_like(out_mask), reduction='none')
+    #         cost_mask = torch.matmul(pos_cost_mask, tgt_mask.T) + torch.matmul(neg_cost_mask, 1 - tgt_mask.T)
+    #         cost_mask /= self.num_sample_points
+    #
+    #         # dice cost
+    #         out_mask = F.sigmoid(out_mask)
+    #         numerator = 2 * torch.matmul(out_mask, tgt_mask.T)
+    #         denominator = out_mask.sum(-1, keepdim=True) + tgt_mask.sum(-1).unsqueeze(0)
+    #         cost_dice = 1 - (numerator + 1) / (denominator + 1)
+    #
+    #         C = self.cost_gain['mask'] * cost_mask + self.cost_gain['dice'] * cost_dice
+    #     return C
+
+
+def get_cdn_group(
+    batch, num_classes, num_queries, class_embed, num_dn=100, cls_noise_ratio=0.5, box_noise_scale=1.0, training=False
+):
+    """
+    Get contrastive denoising training group with positive and negative samples from ground truths.
+
+    Args:
+        batch (dict): A dict that includes 'gt_cls' (torch.Tensor with shape (num_gts, )), 'gt_bboxes'
+            (torch.Tensor with shape (num_gts, 4)), 'gt_groups' (List[int]) which is a list of batch size length
+            indicating the number of gts of each image.
+        num_classes (int): Number of classes.
+        num_queries (int): Number of queries.
+        class_embed (torch.Tensor): Embedding weights to map class labels to embedding space.
+        num_dn (int, optional): Number of denoising queries.
+        cls_noise_ratio (float, optional): Noise ratio for class labels.
+        box_noise_scale (float, optional): Noise scale for bounding box coordinates.
+        training (bool, optional): If it's in training mode.
+
+    Returns:
+        padding_cls (Optional[torch.Tensor]): The modified class embeddings for denoising.
+        padding_bbox (Optional[torch.Tensor]): The modified bounding boxes for denoising.
+        attn_mask (Optional[torch.Tensor]): The attention mask for denoising.
+        dn_meta (Optional[Dict]): Meta information for denoising.
+    """
+    if (not training) or num_dn <= 0 or batch is None:
+        return None, None, None, None
+    gt_groups = batch["gt_groups"]
+    total_num = sum(gt_groups)
+    max_nums = max(gt_groups)
+    if max_nums == 0:
+        return None, None, None, None
+
+    num_group = num_dn // max_nums
+    num_group = 1 if num_group == 0 else num_group
+    # Pad gt to max_num of a batch
+    bs = len(gt_groups)
+    gt_cls = batch["cls"]  # (bs*num, )
+    gt_bbox = batch["bboxes"]  # bs*num, 4
+    b_idx = batch["batch_idx"]
+
+    # Each group has positive and negative queries.
+    dn_cls = gt_cls.repeat(2 * num_group)  # (2*num_group*bs*num, )
+    dn_bbox = gt_bbox.repeat(2 * num_group, 1)  # 2*num_group*bs*num, 4
+    dn_b_idx = b_idx.repeat(2 * num_group).view(-1)  # (2*num_group*bs*num, )
+
+    # Positive and negative mask
+    # (bs*num*num_group, ), the second total_num*num_group part as negative samples
+    neg_idx = torch.arange(total_num * num_group, dtype=torch.long, device=gt_bbox.device) + num_group * total_num
+
+    if cls_noise_ratio > 0:
+        # Half of bbox prob
+        mask = torch.rand(dn_cls.shape) < (cls_noise_ratio * 0.5)
+        idx = torch.nonzero(mask).squeeze(-1)
+        # Randomly put a new one here
+        new_label = torch.randint_like(idx, 0, num_classes, dtype=dn_cls.dtype, device=dn_cls.device)
+        dn_cls[idx] = new_label
+
+    if box_noise_scale > 0:
+        known_bbox = xywh2xyxy(dn_bbox)
+
+        diff = (dn_bbox[..., 2:] * 0.5).repeat(1, 2) * box_noise_scale  # 2*num_group*bs*num, 4
+
+        rand_sign = torch.randint_like(dn_bbox, 0, 2) * 2.0 - 1.0
+        rand_part = torch.rand_like(dn_bbox)
+        rand_part[neg_idx] += 1.0
+        rand_part *= rand_sign
+        known_bbox += rand_part * diff
+        known_bbox.clip_(min=0.0, max=1.0)
+        dn_bbox = xyxy2xywh(known_bbox)
+        dn_bbox = torch.logit(dn_bbox, eps=1e-6)  # inverse sigmoid
+
+    num_dn = int(max_nums * 2 * num_group)  # total denoising queries
+    # class_embed = torch.cat([class_embed, torch.zeros([1, class_embed.shape[-1]], device=class_embed.device)])
+    dn_cls_embed = class_embed[dn_cls]  # bs*num * 2 * num_group, 256
+    padding_cls = torch.zeros(bs, num_dn, dn_cls_embed.shape[-1], device=gt_cls.device)
+    padding_bbox = torch.zeros(bs, num_dn, 4, device=gt_bbox.device)
+
+    map_indices = torch.cat([torch.tensor(range(num), dtype=torch.long) for num in gt_groups])
+    pos_idx = torch.stack([map_indices + max_nums * i for i in range(num_group)], dim=0)
+
+    map_indices = torch.cat([map_indices + max_nums * i for i in range(2 * num_group)])
+    padding_cls[(dn_b_idx, map_indices)] = dn_cls_embed
+    padding_bbox[(dn_b_idx, map_indices)] = dn_bbox
+
+    tgt_size = num_dn + num_queries
+    attn_mask = torch.zeros([tgt_size, tgt_size], dtype=torch.bool)
+    # Match query cannot see the reconstruct
+    attn_mask[num_dn:, :num_dn] = True
+    # Reconstruct cannot see each other
+    for i in range(num_group):
+        if i == 0:
+            attn_mask[max_nums * 2 * i : max_nums * 2 * (i + 1), max_nums * 2 * (i + 1) : num_dn] = True
+        if i == num_group - 1:
+            attn_mask[max_nums * 2 * i : max_nums * 2 * (i + 1), : max_nums * i * 2] = True
+        else:
+            attn_mask[max_nums * 2 * i : max_nums * 2 * (i + 1), max_nums * 2 * (i + 1) : num_dn] = True
+            attn_mask[max_nums * 2 * i : max_nums * 2 * (i + 1), : max_nums * 2 * i] = True
+    dn_meta = {
+        "dn_pos_idx": [p.reshape(-1) for p in pos_idx.cpu().split(list(gt_groups), dim=1)],
+        "dn_num_group": num_group,
+        "dn_num_split": [num_dn, num_queries],
+    }
+
+    return (
+        padding_cls.to(class_embed.device),
+        padding_bbox.to(class_embed.device),
+        attn_mask.to(class_embed.device),
+        dn_meta,
+    )

ultralytics/models/yolo/__init__.py

@@ -0,0 +1,7 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+from ultralytics.models.yolo import classify, detect, obb, pose, segment, world, yoloe
+
+from .model import YOLO, YOLOE, YOLOWorld
+
+__all__ = "classify", "segment", "detect", "pose", "obb", "world", "yoloe", "YOLO", "YOLOWorld", "YOLOE"

ultralytics/models/yolo/classify/__init__.py

@@ -0,0 +1,7 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+from ultralytics.models.yolo.classify.predict import ClassificationPredictor
+from ultralytics.models.yolo.classify.train import ClassificationTrainer
+from ultralytics.models.yolo.classify.val import ClassificationValidator
+
+__all__ = "ClassificationPredictor", "ClassificationTrainer", "ClassificationValidator"

ultralytics/models/yolo/classify/predict.py

@@ -0,0 +1,88 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+import cv2
+import torch
+from PIL import Image
+
+from ultralytics.engine.predictor import BasePredictor
+from ultralytics.engine.results import Results
+from ultralytics.utils import DEFAULT_CFG, ops
+
+
+class ClassificationPredictor(BasePredictor):
+    """
+    A class extending the BasePredictor class for prediction based on a classification model.
+
+    This predictor handles the specific requirements of classification models, including preprocessing images
+    and postprocessing predictions to generate classification results.
+
+    Attributes:
+        args (dict): Configuration arguments for the predictor.
+        _legacy_transform_name (str): Name of the legacy transform class for backward compatibility.
+
+    Methods:
+        preprocess: Convert input images to model-compatible format.
+        postprocess: Process model predictions into Results objects.
+
+    Notes:
+        - Torchvision classification models can also be passed to the 'model' argument, i.e. model='resnet18'.
+
+    Examples:
+        >>> from ultralytics.utils import ASSETS
+        >>> from ultralytics.models.yolo.classify import ClassificationPredictor
+        >>> args = dict(model="yolo11n-cls.pt", source=ASSETS)
+        >>> predictor = ClassificationPredictor(overrides=args)
+        >>> predictor.predict_cli()
+    """
+
+    def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
+        """
+        Initialize the ClassificationPredictor with the specified configuration and set task to 'classify'.
+
+        This constructor initializes a ClassificationPredictor instance, which extends BasePredictor for classification
+        tasks. It ensures the task is set to 'classify' regardless of input configuration.
+
+        Args:
+            cfg (dict): Default configuration dictionary containing prediction settings. Defaults to DEFAULT_CFG.
+            overrides (dict, optional): Configuration overrides that take precedence over cfg.
+            _callbacks (list, optional): List of callback functions to be executed during prediction.
+        """
+        super().__init__(cfg, overrides, _callbacks)
+        self.args.task = "classify"
+        self._legacy_transform_name = "ultralytics.yolo.data.augment.ToTensor"
+
+    def preprocess(self, img):
+        """Convert input images to model-compatible tensor format with appropriate normalization."""
+        if not isinstance(img, torch.Tensor):
+            is_legacy_transform = any(
+                self._legacy_transform_name in str(transform) for transform in self.transforms.transforms
+            )
+            if is_legacy_transform:  # to handle legacy transforms
+                img = torch.stack([self.transforms(im) for im in img], dim=0)
+            else:
+                img = torch.stack(
+                    [self.transforms(Image.fromarray(cv2.cvtColor(im, cv2.COLOR_BGR2RGB))) for im in img], dim=0
+                )
+        img = (img if isinstance(img, torch.Tensor) else torch.from_numpy(img)).to(self.model.device)
+        return img.half() if self.model.fp16 else img.float()  # uint8 to fp16/32
+
+    def postprocess(self, preds, img, orig_imgs):
+        """
+        Process predictions to return Results objects with classification probabilities.
+
+        Args:
+            preds (torch.Tensor): Raw predictions from the model.
+            img (torch.Tensor): Input images after preprocessing.
+            orig_imgs (List[np.ndarray] | torch.Tensor): Original images before preprocessing.
+
+        Returns:
+            (List[Results]): List of Results objects containing classification results for each image.
+        """
+        if not isinstance(orig_imgs, list):  # input images are a torch.Tensor, not a list
+            orig_imgs = ops.convert_torch2numpy_batch(orig_imgs)
+
+        preds = preds[0] if isinstance(preds, (list, tuple)) else preds
+        return [
+            Results(orig_img, path=img_path, names=self.model.names, probs=pred)
+            for pred, orig_img, img_path in zip(preds, orig_imgs, self.batch[0])
+        ]

ultralytics/models/yolo/classify/train.py

@@ -0,0 +1,233 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+from copy import copy
+
+import torch
+
+from ultralytics.data import ClassificationDataset, build_dataloader
+from ultralytics.engine.trainer import BaseTrainer
+from ultralytics.models import yolo
+from ultralytics.nn.tasks import ClassificationModel
+from ultralytics.utils import DEFAULT_CFG, LOGGER, RANK
+from ultralytics.utils.plotting import plot_images, plot_results
+from ultralytics.utils.torch_utils import is_parallel, strip_optimizer, torch_distributed_zero_first
+
+
+class ClassificationTrainer(BaseTrainer):
+    """
+    A class extending the BaseTrainer class for training based on a classification model.
+
+    This trainer handles the training process for image classification tasks, supporting both YOLO classification models
+    and torchvision models.
+
+    Attributes:
+        model (ClassificationModel): The classification model to be trained.
+        data (dict): Dictionary containing dataset information including class names and number of classes.
+        loss_names (List[str]): Names of the loss functions used during training.
+        validator (ClassificationValidator): Validator instance for model evaluation.
+
+    Methods:
+        set_model_attributes: Set the model's class names from the loaded dataset.
+        get_model: Return a modified PyTorch model configured for training.
+        setup_model: Load, create or download model for classification.
+        build_dataset: Create a ClassificationDataset instance.
+        get_dataloader: Return PyTorch DataLoader with transforms for image preprocessing.
+        preprocess_batch: Preprocess a batch of images and classes.
+        progress_string: Return a formatted string showing training progress.
+        get_validator: Return an instance of ClassificationValidator.
+        label_loss_items: Return a loss dict with labelled training loss items.
+        plot_metrics: Plot metrics from a CSV file.
+        final_eval: Evaluate trained model and save validation results.
+        plot_training_samples: Plot training samples with their annotations.
+
+    Examples:
+        >>> from ultralytics.models.yolo.classify import ClassificationTrainer
+        >>> args = dict(model="yolo11n-cls.pt", data="imagenet10", epochs=3)
+        >>> trainer = ClassificationTrainer(overrides=args)
+        >>> trainer.train()
+    """
+
+    def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
+        """
+        Initialize a ClassificationTrainer object.
+
+        This constructor sets up a trainer for image classification tasks, configuring the task type and default
+        image size if not specified.
+
+        Args:
+            cfg (dict, optional): Default configuration dictionary containing training parameters.
+            overrides (dict, optional): Dictionary of parameter overrides for the default configuration.
+            _callbacks (list, optional): List of callback functions to be executed during training.
+
+        Examples:
+            >>> from ultralytics.models.yolo.classify import ClassificationTrainer
+            >>> args = dict(model="yolo11n-cls.pt", data="imagenet10", epochs=3)
+            >>> trainer = ClassificationTrainer(overrides=args)
+            >>> trainer.train()
+        """
+        if overrides is None:
+            overrides = {}
+        overrides["task"] = "classify"
+        if overrides.get("imgsz") is None:
+            overrides["imgsz"] = 224
+        super().__init__(cfg, overrides, _callbacks)
+
+    def set_model_attributes(self):
+        """Set the YOLO model's class names from the loaded dataset."""
+        self.model.names = self.data["names"]
+
+    def get_model(self, cfg=None, weights=None, verbose=True):
+        """
+        Return a modified PyTorch model configured for training YOLO.
+
+        Args:
+            cfg (Any): Model configuration.
+            weights (Any): Pre-trained model weights.
+            verbose (bool): Whether to display model information.
+
+        Returns:
+            (ClassificationModel): Configured PyTorch model for classification.
+        """
+        model = ClassificationModel(cfg, nc=self.data["nc"], ch=self.data["channels"], 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
+
+    def setup_model(self):
+        """
+        Load, create or download model for classification tasks.
+
+        Returns:
+            (Any): Model checkpoint if applicable, otherwise None.
+        """
+        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
+
+    def build_dataset(self, img_path, mode="train", batch=None):
+        """
+        Create a ClassificationDataset instance given an image path and mode.
+
+        Args:
+            img_path (str): Path to the dataset images.
+            mode (str): Dataset mode ('train', 'val', or 'test').
+            batch (Any): Batch information (unused in this implementation).
+
+        Returns:
+            (ClassificationDataset): Dataset for the specified mode.
+        """
+        return ClassificationDataset(root=img_path, args=self.args, augment=mode == "train", prefix=mode)
+
+    def get_dataloader(self, dataset_path, batch_size=16, rank=0, mode="train"):
+        """
+        Return PyTorch DataLoader with transforms to preprocess images.
+
+        Args:
+            dataset_path (str): Path to the dataset.
+            batch_size (int): Number of images per batch.
+            rank (int): Process rank for distributed training.
+            mode (str): 'train', 'val', or 'test' mode.
+
+        Returns:
+            (torch.utils.data.DataLoader): DataLoader for the specified dataset and mode.
+        """
+        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
+
+    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
+
+    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",
+        )
+
+    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
+        )
+
+    def label_loss_items(self, loss_items=None, prefix="train"):
+        """
+        Return a loss dict with labelled training loss items tensor.
+
+        Args:
+            loss_items (torch.Tensor, optional): Loss tensor items.
+            prefix (str): Prefix to prepend to loss names.
+
+        Returns:
+            (Dict[str, float] | List[str]): Dictionary of loss items or list of loss keys if loss_items is None.
+        """
+        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))
+
+    def plot_metrics(self):
+        """Plot metrics from a CSV file."""
+        plot_results(file=self.csv, classify=True, on_plot=self.on_plot)  # save results.png
+
+    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")
+
+    def plot_training_samples(self, batch, ni):
+        """
+        Plot training samples with their annotations.
+
+        Args:
+            batch (Dict[str, torch.Tensor]): Batch containing images and class labels.
+            ni (int): Number of iterations.
+        """
+        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,
+        )