ultralytics 8.3.92__py3-none-any.whl → 8.3.94__py3-none-any.whl

ultralytics/hub/session.py

@@ -26,13 +26,13 @@ class HUBTrainingSession:
     Attributes:
         model_id (str): Identifier for the YOLO model being trained.
         model_url (str): URL for the model in Ultralytics HUB.
-        rate_limits (Dict): Rate limits for different API calls (in seconds).
-        timers (Dict): Timers for rate limiting.
-        metrics_queue (Dict): Queue for the model's metrics.
-        metrics_upload_failed_queue (Dict): Queue for metrics that failed to upload.
-        model (Dict): Model data fetched from Ultralytics HUB.
+        rate_limits (dict): Rate limits for different API calls (in seconds).
+        timers (dict): Timers for rate limiting.
+        metrics_queue (dict): Queue for the model's metrics.
+        metrics_upload_failed_queue (dict): Queue for metrics that failed to upload.
+        model (dict): Model data fetched from Ultralytics HUB.
         model_file (str): Path to the model file.
-        train_args (Dict): Arguments for training the model.
+        train_args (dict): Arguments for training the model.
         client (HUBClient): Client for interacting with Ultralytics HUB.
         filename (str): Filename of the model.
 
@@ -95,7 +95,7 @@ class HUBTrainingSession:
 
         Args:
             identifier (str): Model identifier used to initialize the HUB training session.
-            args (Dict, optional): Arguments for creating a new model if identifier is not a HUB model URL.
+            args (dict, optional): Arguments for creating a new model if identifier is not a HUB model URL.
 
         Returns:
             (HUBTrainingSession | None): An authenticated session or None if creation fails.
@@ -141,7 +141,7 @@ class HUBTrainingSession:
         Initialize a HUB training session with the specified model arguments.
 
         Args:
-            model_args (Dict): Arguments for creating the model, including batch size, epochs, image size, etc.
+            model_args (dict): Arguments for creating the model, including batch size, epochs, image size, etc.
 
         Returns:
             (None): If the model could not be created.

ultralytics/hub/utils.py

@@ -177,7 +177,7 @@ class Events:
     Attributes:
         url (str): The URL to send anonymous events.
         rate_limit (float): The rate limit in seconds for sending events.
-        metadata (Dict): A dictionary containing metadata about the environment.
+        metadata (dict): A dictionary containing metadata about the environment.
         enabled (bool): A flag to enable or disable Events based on certain conditions.
     """
 

ultralytics/models/fastsam/model.py

@@ -43,14 +43,14 @@ class FastSAM(Model):
             source (str | PIL.Image | numpy.ndarray): Input source for prediction, can be a file path, URL, PIL image,
                 or numpy array.
             stream (bool): Whether to enable real-time streaming mode for video inputs.
-            bboxes (List): Bounding box coordinates for prompted segmentation in format [[x1, y1, x2, y2], ...].
-            points (List): Point coordinates for prompted segmentation in format [[x, y], ...].
-            labels (List): Class labels for prompted segmentation.
-            texts (List): Text prompts for segmentation guidance.
+            bboxes (list): Bounding box coordinates for prompted segmentation in format [[x1, y1, x2, y2], ...].
+            points (list): Point coordinates for prompted segmentation in format [[x, y], ...].
+            labels (list): Class labels for prompted segmentation.
+            texts (list): Text prompts for segmentation guidance.
             **kwargs (Any): Additional keyword arguments passed to the predictor.
 
         Returns:
-            (List): List of Results objects containing the prediction results.
+            (list): List of Results objects containing the prediction results.
         """
         prompts = dict(bboxes=bboxes, points=points, labels=labels, texts=texts)
         return super().predict(source, stream, prompts=prompts, **kwargs)

ultralytics/models/fastsam/predict.py

@@ -20,7 +20,7 @@ class FastSAMPredictor(SegmentationPredictor):
     single-class segmentation.
 
     Attributes:
-        prompts (Dict): Dictionary containing prompt information for segmentation (bboxes, points, labels, texts).
+        prompts (dict): Dictionary containing prompt information for segmentation (bboxes, points, labels, texts).
         device (torch.device): Device on which model and tensors are processed.
         clip_model (Any, optional): CLIP model for text-based prompting, loaded on demand.
         clip_preprocess (Any, optional): CLIP preprocessing function for images, loaded on demand.

ultralytics/models/fastsam/val.py

@@ -17,7 +17,7 @@ class FastSAMValidator(SegmentationValidator):
         save_dir (Path): The directory where validation results will be saved.
         pbar (tqdm.tqdm): A progress bar object for displaying validation progress.
         args (SimpleNamespace): Additional arguments for customization of the validation process.
-        _callbacks (List): List of callback functions to be invoked during validation.
+        _callbacks (list): List of callback functions to be invoked during validation.
     """
 
     def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None):
@@ -29,7 +29,7 @@ class FastSAMValidator(SegmentationValidator):
             save_dir (Path, optional): Directory to save results.
             pbar (tqdm.tqdm): Progress bar for displaying progress.
             args (SimpleNamespace): Configuration for the validator.
-            _callbacks (List): List of callback functions to be invoked during validation.
+            _callbacks (list): List of callback functions to be invoked during validation.
 
         Notes:
             Plots for ConfusionMatrix and other related metrics are disabled in this class to avoid errors.

ultralytics/models/nas/predict.py

@@ -19,7 +19,7 @@ class NASPredictor(BasePredictor):
         args (Namespace): Namespace containing various configurations for post-processing including confidence threshold,
             IoU threshold, agnostic NMS flag, maximum detections, and class filtering options.
         model (torch.nn.Module): The YOLO NAS model used for inference.
-        batch (List): Batch of inputs for processing.
+        batch (list): Batch of inputs for processing.
 
     Examples:
         >>> from ultralytics import NAS

ultralytics/models/rtdetr/model.py

@@ -51,7 +51,7 @@ class RTDETR(Model):
         Returns a task map for RT-DETR, associating tasks with corresponding Ultralytics classes.
 
         Returns:
-            (Dict): A dictionary mapping task names to Ultralytics task classes for the RT-DETR model.
+            (dict): A dictionary mapping task names to Ultralytics task classes for the RT-DETR model.
         """
         return {
             "detect": {

ultralytics/models/rtdetr/predict.py

@@ -19,7 +19,7 @@ class RTDETRPredictor(BasePredictor):
         imgsz (int): Image size for inference (must be square and scale-filled).
         args (dict): Argument overrides for the predictor.
         model (torch.nn.Module): The loaded RT-DETR model.
-        batch (List): Current batch of processed inputs.
+        batch (list): Current batch of processed inputs.
 
     Examples:
         >>> from ultralytics.utils import ASSETS

ultralytics/models/rtdetr/train.py

@@ -21,8 +21,8 @@ class RTDETRTrainer(DetectionTrainer):
 
     Attributes:
         loss_names (Tuple[str]): Names of the loss components used for training.
-        data (Dict): Dataset configuration containing class count and other parameters.
-        args (Dict): Training arguments and hyperparameters.
+        data (dict): Dataset configuration containing class count and other parameters.
+        args (dict): Training arguments and hyperparameters.
         save_dir (Path): Directory to save training results.
         test_loader (DataLoader): DataLoader for validation/testing data.
 
@@ -42,7 +42,7 @@ class RTDETRTrainer(DetectionTrainer):
         Initialize and return an RT-DETR model for object detection tasks.
 
         Args:
-            cfg (Dict, optional): Model configuration.
+            cfg (dict, optional): Model configuration.
             weights (str, optional): Path to pre-trained model weights.
             verbose (bool): Verbose logging if True.
 
@@ -91,10 +91,10 @@ class RTDETRTrainer(DetectionTrainer):
         Preprocess a batch of images by scaling and converting to float format.
 
         Args:
-            batch (Dict): Dictionary containing a batch of images, bboxes, and labels.
+            batch (dict): Dictionary containing a batch of images, bboxes, and labels.
 
         Returns:
-            (Dict): Preprocessed batch with ground truth bounding boxes and classes separated by batch index.
+            (dict): Preprocessed batch with ground truth bounding boxes and classes separated by batch index.
         """
         batch = super().preprocess_batch(batch)
         bs = len(batch["img"])

ultralytics/models/rtdetr/val.py

@@ -31,7 +31,7 @@ class RTDETRDataset(YOLODataset):
         Build transformation pipeline for the dataset.
 
         Args:
-            hyp (Dict, optional): Hyperparameters for transformations.
+            hyp (dict, optional): Hyperparameters for transformations.
 
         Returns:
             (Compose): Composition of transformation functions.
@@ -134,10 +134,10 @@ class RTDETRValidator(DetectionValidator):
 
         Args:
             si (int): Batch index.
-            batch (Dict): Batch data containing images and annotations.
+            batch (dict): Batch data containing images and annotations.
 
         Returns:
-            (Dict): Prepared batch with transformed annotations.
+            (dict): Prepared batch with transformed annotations.
         """
         idx = batch["batch_idx"] == si
         cls = batch["cls"][idx].squeeze(-1)
@@ -157,7 +157,7 @@ class RTDETRValidator(DetectionValidator):
 
         Args:
             pred (torch.Tensor): Raw predictions.
-            pbatch (Dict): Prepared batch information.
+            pbatch (dict): Prepared batch information.
 
         Returns:
             (torch.Tensor): Predictions scaled to original image dimensions.

ultralytics/models/sam/model.py

@@ -94,7 +94,7 @@ class SAM(Model):
             **kwargs (Any): Additional keyword arguments for prediction.
 
         Returns:
-            (List): The model predictions.
+            (list): The model predictions.
 
         Examples:
             >>> sam = SAM("sam_b.pt")
@@ -124,7 +124,7 @@ class SAM(Model):
             **kwargs (Any): Additional keyword arguments to be passed to the predict method.
 
         Returns:
-            (List): The model predictions, typically containing segmentation masks and other relevant information.
+            (list): The model predictions, typically containing segmentation masks and other relevant information.
 
         Examples:
             >>> sam = SAM("sam_b.pt")

ultralytics/models/sam/modules/blocks.py

@@ -707,7 +707,7 @@ class PositionEmbeddingSine(nn.Module):
         temperature (int): Temperature parameter for the sinusoidal functions.
         normalize (bool): Whether to normalize the positional embeddings.
         scale (float): Scaling factor for the embeddings when normalize is True.
-        cache (Dict): Cache for storing precomputed embeddings.
+        cache (dict): Cache for storing precomputed embeddings.
 
     Methods:
         _encode_xy: Encodes 2D positions using sine and cosine functions.

ultralytics/models/sam/predict.py

@@ -48,7 +48,7 @@ class Predictor(BasePredictor):
         device (torch.device): The device (CPU or GPU) on which the model is loaded.
         im (torch.Tensor): The preprocessed input image.
         features (torch.Tensor): Extracted image features.
-        prompts (Dict): Dictionary to store various types of prompts (e.g., bboxes, points, masks).
+        prompts (dict): Dictionary to store various types of prompts (e.g., bboxes, points, masks).
         segment_all (bool): Flag to indicate if full image segmentation should be performed.
         mean (torch.Tensor): Mean values for image normalization.
         std (torch.Tensor): Standard deviation values for image normalization.
@@ -86,7 +86,7 @@ class Predictor(BasePredictor):
         for optimal results.
 
         Args:
-            cfg (Dict): Configuration dictionary containing default settings.
+            cfg (dict): Configuration dictionary containing default settings.
             overrides (Dict | None): Dictionary of values to override default configuration.
             _callbacks (Dict | None): Dictionary of callback functions to customize behavior.
 
@@ -634,7 +634,7 @@ class SAM2Predictor(Predictor):
         device (torch.device): The device (CPU or GPU) on which the model is loaded.
         features (Dict[str, torch.Tensor]): Cached image features for efficient inference.
         segment_all (bool): Flag to indicate if all segments should be predicted.
-        prompts (Dict): Dictionary to store various types of prompts for inference.
+        prompts (dict): Dictionary to store various types of prompts for inference.
 
     Methods:
         get_model: Retrieves and initializes the SAM2 model.
@@ -818,16 +818,16 @@ class SAM2VideoPredictor(SAM2Predictor):
     clearing memory for non-conditional inputs, and setting up callbacks for prediction events.
 
     Attributes:
-        inference_state (Dict): A dictionary to store the current state of inference operations.
+        inference_state (dict): A dictionary to store the current state of inference operations.
         non_overlap_masks (bool): A flag indicating whether masks should be non-overlapping.
         clear_non_cond_mem_around_input (bool): A flag to control clearing non-conditional memory around inputs.
         clear_non_cond_mem_for_multi_obj (bool): A flag to control clearing non-conditional memory for multi-object scenarios.
-        callbacks (Dict): A dictionary of callbacks for various prediction lifecycle events.
+        callbacks (dict): A dictionary of callbacks for various prediction lifecycle events.
 
     Args:
-        cfg (Dict, Optional): Configuration settings for the predictor. Defaults to DEFAULT_CFG.
-        overrides (Dict, Optional): Additional configuration overrides. Defaults to None.
-        _callbacks (List, Optional): Custom callbacks to be added. Defaults to None.
+        cfg (dict, Optional): Configuration settings for the predictor. Defaults to DEFAULT_CFG.
+        overrides (dict, Optional): Additional configuration overrides. Defaults to None.
+        _callbacks (list, Optional): Custom callbacks to be added. Defaults to None.
 
     Note:
         The `fill_hole_area` attribute is defined but not used in the current implementation.
@@ -844,7 +844,7 @@ class SAM2VideoPredictor(SAM2Predictor):
         that control the behavior of the predictor.
 
         Args:
-            cfg (Dict): Configuration dictionary containing default settings.
+            cfg (dict): Configuration dictionary containing default settings.
             overrides (Dict | None): Dictionary of values to override default configuration.
             _callbacks (Dict | None): Dictionary of callback functions to customize behavior.
 
@@ -1284,11 +1284,11 @@ class SAM2VideoPredictor(SAM2Predictor):
         Run tracking on a single frame based on current inputs and previous memory.
 
         Args:
-            output_dict (Dict): The dictionary containing the output states of the tracking process.
+            output_dict (dict): The dictionary containing the output states of the tracking process.
             frame_idx (int): The index of the current frame.
             batch_size (int): The batch size for processing the frame.
             is_init_cond_frame (bool): Indicates if the current frame is an initial conditioning frame.
-            point_inputs (Dict, Optional): Input points and their labels. Defaults to None.
+            point_inputs (dict, Optional): Input points and their labels. Defaults to None.
             mask_inputs (torch.Tensor, Optional): Input binary masks. Defaults to None.
             reverse (bool): Indicates if the tracking should be performed in reverse order.
             run_mem_encoder (bool): Indicates if the memory encoder should be executed.
@@ -1559,7 +1559,7 @@ class SAM2VideoPredictor(SAM2Predictor):
 
         Args:
             frame_idx (int): The index of the current frame.
-            current_out (Dict): The current output dictionary containing multi-object outputs.
+            current_out (dict): The current output dictionary containing multi-object outputs.
             storage_key (str): The key used to store the output in the per-object output dictionary.
         """
         maskmem_features = current_out["maskmem_features"]

ultralytics/models/utils/loss.py

@@ -19,7 +19,7 @@ class DETRLoss(nn.Module):
 
     Attributes:
         nc (int): Number of classes.
-        loss_gain (Dict): Coefficients for different loss components.
+        loss_gain (dict): Coefficients for different loss components.
         aux_loss (bool): Whether to compute auxiliary losses.
         use_fl (bool): Whether to use FocalLoss.
         use_vfl (bool): Whether to use VarifocalLoss.
@@ -42,7 +42,7 @@ class DETRLoss(nn.Module):
 
         Args:
             nc (int): Number of classes.
-            loss_gain (Dict): Coefficients for different loss components.
+            loss_gain (dict): Coefficients for different loss components.
             aux_loss (bool): Whether to use auxiliary losses from each decoder layer.
             use_fl (bool): Whether to use FocalLoss.
             use_vfl (bool): Whether to use VarifocalLoss.
@@ -162,7 +162,7 @@ class DETRLoss(nn.Module):
             gt_mask (torch.Tensor, optional): Ground truth masks if using segmentation.
 
         Returns:
-            (Dict): Dictionary of auxiliary losses.
+            (dict): Dictionary of auxiliary losses.
         """
         # NOTE: loss class, bbox, giou, mask, dice
         loss = torch.zeros(5 if masks is not None else 3, device=pred_bboxes.device)
@@ -276,7 +276,7 @@ class DETRLoss(nn.Module):
             match_indices (List[tuple], optional): Pre-computed matching indices.
 
         Returns:
-            (Dict): Dictionary of losses.
+            (dict): Dictionary of losses.
         """
         if match_indices is None:
             match_indices = self.matcher(
@@ -307,7 +307,7 @@ class DETRLoss(nn.Module):
         Args:
             pred_bboxes (torch.Tensor): Predicted bounding boxes, shape [l, b, query, 4].
             pred_scores (torch.Tensor): Predicted class scores, shape [l, b, query, num_classes].
-            batch (Dict): Batch information containing:
+            batch (dict): Batch information containing:
                 cls (torch.Tensor): Ground truth classes, shape [num_gts].
                 bboxes (torch.Tensor): Ground truth bounding boxes, shape [num_gts, 4].
                 gt_groups (List[int]): Number of ground truths for each image in the batch.
@@ -315,7 +315,7 @@ class DETRLoss(nn.Module):
             **kwargs (Any): Additional arguments, may include 'match_indices'.
 
         Returns:
-            (Dict): Computed losses, including main and auxiliary (if enabled).
+            (dict): Computed losses, including main and auxiliary (if enabled).
 
         Notes:
             Uses last elements of pred_bboxes and pred_scores for main loss, and the rest for auxiliary losses if
@@ -353,13 +353,13 @@ class RTDETRDetectionLoss(DETRLoss):
 
         Args:
             preds (tuple): Tuple containing predicted bounding boxes and scores.
-            batch (Dict): Batch data containing ground truth information.
+            batch (dict): Batch data containing ground truth information.
             dn_bboxes (torch.Tensor, optional): Denoising bounding boxes.
             dn_scores (torch.Tensor, optional): Denoising scores.
-            dn_meta (Dict, optional): Metadata for denoising.
+            dn_meta (dict, optional): Metadata for denoising.
 
         Returns:
-            (Dict): Dictionary containing total loss and denoising loss if applicable.
+            (dict): Dictionary containing total loss and denoising loss if applicable.
         """
         pred_bboxes, pred_scores = preds
         total_loss = super().forward(pred_bboxes, pred_scores, batch)

ultralytics/models/utils/ops.py

@@ -18,7 +18,7 @@ class HungarianMatcher(nn.Module):
     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'.
+        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.
@@ -150,7 +150,7 @@ def get_cdn_group(
     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'
+        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.

ultralytics/models/yolo/classify/predict.py

@@ -17,7 +17,7 @@ class ClassificationPredictor(BasePredictor):
     and postprocessing predictions to generate classification results.
 
     Attributes:
-        args (Dict): Configuration arguments for the predictor.
+        args (dict): Configuration arguments for the predictor.
         _legacy_transform_name (str): Name of the legacy transform class for backward compatibility.
 
     Methods:

ultralytics/models/yolo/classify/train.py

@@ -22,7 +22,7 @@ class ClassificationTrainer(BaseTrainer):
 
     Attributes:
         model (ClassificationModel): The classification model to be trained.
-        data (Dict): Dictionary containing dataset information including class names and number of classes.
+        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.
 

ultralytics/models/yolo/classify/val.py

@@ -20,7 +20,7 @@ class ClassificationValidator(BaseValidator):
         targets (List[torch.Tensor]): Ground truth class labels.
         pred (List[torch.Tensor]): Model predictions.
         metrics (ClassifyMetrics): Object to calculate and store classification metrics.
-        names (Dict): Mapping of class indices to class names.
+        names (dict): Mapping of class indices to class names.
         nc (int): Number of classes.
         confusion_matrix (ConfusionMatrix): Matrix to evaluate model performance across classes.
 

ultralytics/models/yolo/detect/predict.py

@@ -15,7 +15,7 @@ class DetectionPredictor(BasePredictor):
     Attributes:
         args (namespace): Configuration arguments for the predictor.
         model (nn.Module): The detection model used for inference.
-        batch (List): Batch of images and metadata for processing.
+        batch (list): Batch of images and metadata for processing.
 
     Methods:
         postprocess: Process raw model predictions into detection results.

ultralytics/models/yolo/detect/train.py

@@ -25,7 +25,7 @@ class DetectionTrainer(BaseTrainer):
 
     Attributes:
         model (DetectionModel): The YOLO detection model being trained.
-        data (Dict): Dictionary containing dataset information including class names and number of classes.
+        data (dict): Dictionary containing dataset information including class names and number of classes.
         loss_names (Tuple[str]): Names of the loss components used in training (box_loss, cls_loss, dfl_loss).
 
     Methods:
@@ -92,10 +92,10 @@ class DetectionTrainer(BaseTrainer):
         Preprocess a batch of images by scaling and converting to float.
 
         Args:
-            batch (Dict): Dictionary containing batch data with 'img' tensor.
+            batch (dict): Dictionary containing batch data with 'img' tensor.
 
         Returns:
-            (Dict): Preprocessed batch with normalized images.
+            (dict): Preprocessed batch with normalized images.
         """
         batch["img"] = batch["img"].to(self.device, non_blocking=True).float() / 255
         if self.args.multi_scale:
@@ -182,7 +182,7 @@ class DetectionTrainer(BaseTrainer):
         Plot training samples with their annotations.
 
         Args:
-            batch (Dict): Dictionary containing batch data.
+            batch (dict): Dictionary containing batch data.
             ni (int): Number of iterations.
         """
         plot_images(

ultralytics/models/yolo/detect/val.py

@@ -26,13 +26,13 @@ class DetectionValidator(BaseValidator):
         nt_per_image (np.ndarray): Number of targets per image.
         is_coco (bool): Whether the dataset is COCO.
         is_lvis (bool): Whether the dataset is LVIS.
-        class_map (List): Mapping from model class indices to dataset class indices.
+        class_map (list): Mapping from model class indices to dataset class indices.
         metrics (DetMetrics): Object detection metrics calculator.
         iouv (torch.Tensor): IoU thresholds for mAP calculation.
         niou (int): Number of IoU thresholds.
-        lb (List): List for storing ground truth labels for hybrid saving.
-        jdict (List): List for storing JSON detection results.
-        stats (Dict): Dictionary for storing statistics during validation.
+        lb (list): List for storing ground truth labels for hybrid saving.
+        jdict (list): List for storing JSON detection results.
+        stats (dict): Dictionary for storing statistics during validation.
 
     Examples:
         >>> from ultralytics.models.yolo.detect import DetectionValidator
@@ -49,8 +49,8 @@ class DetectionValidator(BaseValidator):
             dataloader (torch.utils.data.DataLoader, optional): Dataloader to use for validation.
             save_dir (Path, optional): Directory to save results.
             pbar (Any, optional): Progress bar for displaying progress.
-            args (Dict, optional): Arguments for the validator.
-            _callbacks (List, optional): List of callback functions.
+            args (dict, optional): Arguments for the validator.
+            _callbacks (list, optional): List of callback functions.
         """
         super().__init__(dataloader, save_dir, pbar, args, _callbacks)
         self.nt_per_class = None
@@ -74,10 +74,10 @@ class DetectionValidator(BaseValidator):
         Preprocess batch of images for YOLO validation.
 
         Args:
-            batch (Dict): Batch containing images and annotations.
+            batch (dict): Batch containing images and annotations.
 
         Returns:
-            (Dict): Preprocessed batch.
+            (dict): Preprocessed batch.
         """
         batch["img"] = batch["img"].to(self.device, non_blocking=True)
         batch["img"] = (batch["img"].half() if self.args.half else batch["img"].float()) / 255
@@ -154,10 +154,10 @@ class DetectionValidator(BaseValidator):
 
         Args:
             si (int): Batch index.
-            batch (Dict): Batch data containing images and annotations.
+            batch (dict): Batch data containing images and annotations.
 
         Returns:
-            (Dict): Prepared batch with processed annotations.
+            (dict): Prepared batch with processed annotations.
         """
         idx = batch["batch_idx"] == si
         cls = batch["cls"][idx].squeeze(-1)
@@ -176,7 +176,7 @@ class DetectionValidator(BaseValidator):
 
         Args:
             pred (torch.Tensor): Model predictions.
-            pbatch (Dict): Prepared batch information.
+            pbatch (dict): Prepared batch information.
 
         Returns:
             (torch.Tensor): Prepared predictions in native space.
@@ -193,7 +193,7 @@ class DetectionValidator(BaseValidator):
 
         Args:
             preds (List[torch.Tensor]): List of predictions from the model.
-            batch (Dict): Batch data containing ground truth.
+            batch (dict): Batch data containing ground truth.
         """
         for si, pred in enumerate(preds):
             self.seen += 1
@@ -258,7 +258,7 @@ class DetectionValidator(BaseValidator):
         Calculate and return metrics statistics.
 
         Returns:
-            (Dict): Dictionary containing metrics results.
+            (dict): Dictionary containing metrics results.
         """
         stats = {k: torch.cat(v, 0).cpu().numpy() for k, v in self.stats.items()}  # to numpy
         self.nt_per_class = np.bincount(stats["target_cls"].astype(int), minlength=self.nc)
@@ -338,7 +338,7 @@ class DetectionValidator(BaseValidator):
         Plot validation image samples.
 
         Args:
-            batch (Dict): Batch containing images and annotations.
+            batch (dict): Batch containing images and annotations.
             ni (int): Batch index.
         """
         plot_images(
@@ -357,7 +357,7 @@ class DetectionValidator(BaseValidator):
         Plot predicted bounding boxes on input images and save the result.
 
         Args:
-            batch (Dict): Batch containing images and annotations.
+            batch (dict): Batch containing images and annotations.
             preds (List[torch.Tensor]): List of predictions from the model.
             ni (int): Batch index.
         """
@@ -416,10 +416,10 @@ class DetectionValidator(BaseValidator):
         Evaluate YOLO output in JSON format and return performance statistics.
 
         Args:
-            stats (Dict): Current statistics dictionary.
+            stats (dict): Current statistics dictionary.
 
         Returns:
-            (Dict): Updated statistics dictionary with COCO/LVIS evaluation results.
+            (dict): Updated statistics dictionary with COCO/LVIS evaluation results.
         """
         if self.args.save_json and (self.is_coco or self.is_lvis) and len(self.jdict):
             pred_json = self.save_dir / "predictions.json"  # predictions

ultralytics/models/yolo/obb/val.py

@@ -18,7 +18,7 @@ class OBBValidator(DetectionValidator):
     satellite imagery where objects can appear at various orientations.
 
     Attributes:
-        args (Dict): Configuration arguments for the validator.
+        args (dict): Configuration arguments for the validator.
         metrics (OBBMetrics): Metrics object for evaluating OBB model performance.
         is_dota (bool): Flag indicating whether the validation dataset is in DOTA format.
 

ultralytics/models/yolo/pose/train.py

@@ -16,9 +16,9 @@ class PoseTrainer(yolo.detect.DetectionTrainer):
     of pose keypoints alongside bounding boxes.
 
     Attributes:
-        args (Dict): Configuration arguments for training.
+        args (dict): Configuration arguments for training.
         model (PoseModel): The pose estimation model being trained.
-        data (Dict): Dataset configuration including keypoint shape information.
+        data (dict): Dataset configuration including keypoint shape information.
         loss_names (Tuple[str]): Names of the loss components used in training.
 
     Methods:

ultralytics/models/yolo/pose/val.py

@@ -22,7 +22,7 @@ class PoseValidator(DetectionValidator):
     Attributes:
         sigma (np.ndarray): Sigma values for OKS calculation, either from OKS_SIGMA or ones divided by number of keypoints.
         kpt_shape (List[int]): Shape of the keypoints, typically [17, 3] for COCO format.
-        args (Dict): Arguments for the validator including task set to "pose".
+        args (dict): Arguments for the validator including task set to "pose".
         metrics (PoseMetrics): Metrics object for pose evaluation.
 
     Methods:
@@ -119,7 +119,7 @@ class PoseValidator(DetectionValidator):
 
         Args:
             preds (List[torch.Tensor]): List of prediction tensors from the model.
-            batch (Dict): Batch data containing images and ground truth annotations.
+            batch (dict): Batch data containing images and ground truth annotations.
         """
         for si, pred in enumerate(preds):
             self.seen += 1

ultralytics/models/yolo/segment/predict.py

@@ -13,9 +13,9 @@ class SegmentationPredictor(DetectionPredictor):
     prediction results.
 
     Attributes:
-        args (Dict): Configuration arguments for the predictor.
+        args (dict): Configuration arguments for the predictor.
         model (torch.nn.Module): The loaded YOLO segmentation model.
-        batch (List): Current batch of images being processed.
+        batch (list): Current batch of images being processed.
 
     Methods:
         postprocess: Applies non-max suppression and processes detections.