dgenerate-ultralytics-headless 8.3.194__py3-none-any.whl → 8.3.195__py3-none-any.whl

ultralytics/models/sam/predict.py

@@ -51,7 +51,7 @@ 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[str, Any]): Dictionary to store various types of prompts (e.g., bboxes, points, masks).
+        prompts (dict[str, Any]): 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.
@@ -116,7 +116,7 @@ class Predictor(BasePredictor):
         torch.Tensor and list of np.ndarray as input formats.
 
         Args:
-            im (torch.Tensor | List[np.ndarray]): Input image(s) in BCHW tensor format or list of HWC numpy arrays.
+            im (torch.Tensor | list[np.ndarray]): Input image(s) in BCHW tensor format or list of HWC numpy arrays.
 
         Returns:
             (torch.Tensor): The preprocessed image tensor, normalized and converted to the appropriate dtype.
@@ -149,10 +149,10 @@ class Predictor(BasePredictor):
         Currently, batched inference is not supported; hence the list length should be 1.
 
         Args:
-            im (List[np.ndarray]): List containing a single image in HWC numpy array format.
+            im (list[np.ndarray]): List containing a single image in HWC numpy array format.
 
         Returns:
-            (List[np.ndarray]): List containing the transformed image.
+            (list[np.ndarray]): List containing the transformed image.
 
         Raises:
             AssertionError: If the input list contains more than one image.
@@ -177,9 +177,9 @@ class Predictor(BasePredictor):
 
         Args:
             im (torch.Tensor): The preprocessed input image in tensor format, with shape (N, C, H, W).
-            bboxes (np.ndarray | List | None): Bounding boxes with shape (N, 4), in XYXY format.
-            points (np.ndarray | List | None): Points indicating object locations with shape (N, 2), in pixels.
-            labels (np.ndarray | List | None): Labels for point prompts, shape (N,). 1 = foreground, 0 = background.
+            bboxes (np.ndarray | list | None): Bounding boxes with shape (N, 4), in XYXY format.
+            points (np.ndarray | list | None): Points indicating object locations with shape (N, 2), in pixels.
+            labels (np.ndarray | list | None): Labels for point prompts, shape (N,). 1 = foreground, 0 = background.
             masks (np.ndarray | None): Low-resolution masks from previous predictions, shape (N, H, W). For SAM H=W=256.
             multimask_output (bool): Flag to return multiple masks. Helpful for ambiguous prompts.
             *args (Any): Additional positional arguments.
@@ -215,9 +215,9 @@ class Predictor(BasePredictor):
 
         Args:
             im (torch.Tensor): Preprocessed input image tensor with shape (N, C, H, W).
-            bboxes (np.ndarray | List | None): Bounding boxes in XYXY format with shape (N, 4).
-            points (np.ndarray | List | None): Points indicating object locations with shape (N, 2) or (N, num_points, 2), in pixels.
-            labels (np.ndarray | List | None): Point prompt labels with shape (N) or (N, num_points). 1 for foreground, 0 for background.
+            bboxes (np.ndarray | list | None): Bounding boxes in XYXY format with shape (N, 4).
+            points (np.ndarray | list | None): Points indicating object locations with shape (N, 2) or (N, num_points, 2), in pixels.
+            labels (np.ndarray | list | None): Point prompt labels with shape (N) or (N, num_points). 1 for foreground, 0 for background.
             masks (np.ndarray | None): Low-res masks from previous predictions with shape (N, H, W). For SAM, H=W=256.
             multimask_output (bool): Flag to return multiple masks for ambiguous prompts.
 
@@ -250,10 +250,10 @@ class Predictor(BasePredictor):
 
         Args:
             features (torch.Tensor): Extracted image features with shape (B, C, H, W) from the SAM model image encoder.
-            bboxes (np.ndarray | List[List[float]] | None): Bounding boxes in XYXY format with shape (N, 4).
-            points (np.ndarray | List[List[float]] | None): Object location points with shape (N, 2), in pixels.
-            labels (np.ndarray | List[int] | None): Point prompt labels with shape (N,). 1 = foreground, 0 = background.
-            masks (List[np.ndarray] | np.ndarray | None): Masks for the objects, where each mask is a 2D array.
+            bboxes (np.ndarray | list[list[float]] | None): Bounding boxes in XYXY format with shape (N, 4).
+            points (np.ndarray | list[list[float]] | None): Object location points with shape (N, 2), in pixels.
+            labels (np.ndarray | list[int] | None): Point prompt labels with shape (N,). 1 = foreground, 0 = background.
+            masks (list[np.ndarray] | np.ndarray | None): Masks for the objects, where each mask is a 2D array.
             multimask_output (bool): Flag to return multiple masks for ambiguous prompts.
 
         Returns:
@@ -282,12 +282,12 @@ class Predictor(BasePredictor):
         Prepare and transform the input prompts for processing based on the destination shape.
 
         Args:
-            dst_shape (Tuple[int, int]): The target shape (height, width) for the prompts.
-            src_shape (Tuple[int, int]): The source shape (height, width) of the input image.
-            bboxes (np.ndarray | List | None): Bounding boxes in XYXY format with shape (N, 4).
-            points (np.ndarray | List | None): Points indicating object locations with shape (N, 2) or (N, num_points, 2), in pixels.
-            labels (np.ndarray | List | None): Point prompt labels with shape (N) or (N, num_points). 1 for foreground, 0 for background.
-            masks (List[np.ndarray] | np.ndarray | None): Masks for the objects, where each mask is a 2D array with shape (H, W).
+            dst_shape (tuple[int, int]): The target shape (height, width) for the prompts.
+            src_shape (tuple[int, int]): The source shape (height, width) of the input image.
+            bboxes (np.ndarray | list | None): Bounding boxes in XYXY format with shape (N, 4).
+            points (np.ndarray | list | None): Points indicating object locations with shape (N, 2) or (N, num_points, 2), in pixels.
+            labels (np.ndarray | list | None): Point prompt labels with shape (N) or (N, num_points). 1 for foreground, 0 for background.
+            masks (list[np.ndarray] | np.ndarray | None): Masks for the objects, where each mask is a 2D array with shape (H, W).
 
         Returns:
             bboxes (torch.Tensor | None): Transformed bounding boxes.
@@ -351,7 +351,7 @@ class Predictor(BasePredictor):
             crop_n_layers (int): Number of layers for additional mask predictions on image crops.
             crop_overlap_ratio (float): Overlap between crops, scaled down in subsequent layers.
             crop_downscale_factor (int): Scaling factor for sampled points-per-side in each layer.
-            point_grids (List[np.ndarray] | None): Custom grids for point sampling normalized to [0,1].
+            point_grids (list[np.ndarray] | None): Custom grids for point sampling normalized to [0,1].
             points_stride (int): Number of points to sample along each side of the image.
             points_batch_size (int): Batch size for the number of points processed simultaneously.
             conf_thres (float): Confidence threshold [0,1] for filtering based on mask quality prediction.
@@ -490,10 +490,10 @@ class Predictor(BasePredictor):
                 - pred_scores (torch.Tensor): Confidence scores for each mask with shape (N, 1).
                 - pred_bboxes (torch.Tensor, optional): Predicted bounding boxes if segment_all is True.
             img (torch.Tensor): The processed input image tensor with shape (C, H, W).
-            orig_imgs (List[np.ndarray] | torch.Tensor): The original, unprocessed images.
+            orig_imgs (list[np.ndarray] | torch.Tensor): The original, unprocessed images.
 
         Returns:
-            (List[Results]): List of Results objects containing detection masks, bounding boxes, and other
+            (list[Results]): List of Results objects containing detection masks, bounding boxes, and other
                 metadata for each processed image.
 
         Examples:
@@ -623,7 +623,7 @@ class Predictor(BasePredictor):
 
         Returns:
             new_masks (torch.Tensor): Processed masks with small regions removed, shape (N, H, W).
-            keep (List[int]): Indices of remaining masks after NMS, for filtering corresponding boxes.
+            keep (list[int]): Indices of remaining masks after NMS, for filtering corresponding boxes.
 
         Examples:
             >>> masks = torch.rand(5, 640, 640) > 0.5  # 5 random binary masks
@@ -673,13 +673,13 @@ class Predictor(BasePredictor):
         Perform prompts preprocessing and inference on provided image features using the SAM model.
 
         Args:
-            features (torch.Tensor | Dict[str, Any]): Extracted image features from the SAM/SAM2 model image encoder.
-            src_shape (Tuple[int, int]): The source shape (height, width) of the input image.
-            dst_shape (Tuple[int, int] | None): The target shape (height, width) for the prompts. If None, defaults to (imgsz, imgsz).
-            bboxes (np.ndarray | List[List[float]] | None): Bounding boxes in xyxy format with shape (N, 4).
-            points (np.ndarray | List[List[float]] | None): Points indicating object locations with shape (N, 2), in pixels.
-            labels (np.ndarray | List[int] | None): Point prompt labels with shape (N, ).
-            masks (List[np.ndarray] | np.ndarray | None): Masks for the objects, where each mask is a 2D array.
+            features (torch.Tensor | dict[str, Any]): Extracted image features from the SAM/SAM2 model image encoder.
+            src_shape (tuple[int, int]): The source shape (height, width) of the input image.
+            dst_shape (tuple[int, int] | None): The target shape (height, width) for the prompts. If None, defaults to (imgsz, imgsz).
+            bboxes (np.ndarray | list[list[float]] | None): Bounding boxes in xyxy format with shape (N, 4).
+            points (np.ndarray | list[list[float]] | None): Points indicating object locations with shape (N, 2), in pixels.
+            labels (np.ndarray | list[int] | None): Point prompt labels with shape (N, ).
+            masks (list[np.ndarray] | np.ndarray | None): Masks for the objects, where each mask is a 2D array.
             multimask_output (bool): Flag to return multiple masks for ambiguous prompts.
 
         Returns:
@@ -688,7 +688,7 @@ class Predictor(BasePredictor):
                 Each box is in xyxy format with additional columns for score and class.
 
         Notes:
-            - The input features is a torch.Tensor of shape (B, C, H, W) if performing on SAM, or a Dict[str, Any] if performing on SAM2.
+            - The input features is a torch.Tensor of shape (B, C, H, W) if performing on SAM, or a dict[str, Any] if performing on SAM2.
         """
         dst_shape = dst_shape or (self.args.imgsz, self.args.imgsz)
         prompts = self._prepare_prompts(dst_shape, src_shape, bboxes, points, labels, masks)
@@ -714,12 +714,12 @@ class SAM2Predictor(Predictor):
     prompt-based inference.
 
     Attributes:
-        _bb_feat_sizes (List[tuple]): Feature sizes for different backbone levels.
+        _bb_feat_sizes (list[tuple]): Feature sizes for different backbone levels.
         model (torch.nn.Module): The loaded SAM2 model.
         device (torch.device): The device (CPU or GPU) on which the model is loaded.
         features (dict): Cached image features for efficient inference.
         segment_all (bool): Flag to indicate if all segments should be predicted.
-        prompts (Dict[str, Any]): Dictionary to store various types of prompts for inference.
+        prompts (dict[str, Any]): Dictionary to store various types of prompts for inference.
 
     Methods:
         get_model: Retrieve and initialize the SAM2 model.
@@ -752,12 +752,12 @@ class SAM2Predictor(Predictor):
         Prepare and transform the input prompts for processing based on the destination shape.
 
         Args:
-            dst_shape (Tuple[int, int]): The target shape (height, width) for the prompts.
-            src_shape (Tuple[int, int]): The source shape (height, width) of the input image.
-            bboxes (np.ndarray | List | None): Bounding boxes in XYXY format with shape (N, 4).
-            points (np.ndarray | List | None): Points indicating object locations with shape (N, 2) or (N, num_points, 2), in pixels.
-            labels (np.ndarray | List | None): Point prompt labels with shape (N,) or (N, num_points). 1 for foreground, 0 for background.
-            masks (List | np.ndarray | None): Masks for the objects, where each mask is a 2D array.
+            dst_shape (tuple[int, int]): The target shape (height, width) for the prompts.
+            src_shape (tuple[int, int]): The source shape (height, width) of the input image.
+            bboxes (np.ndarray | list | None): Bounding boxes in XYXY format with shape (N, 4).
+            points (np.ndarray | list | None): Points indicating object locations with shape (N, 2) or (N, num_points, 2), in pixels.
+            labels (np.ndarray | list | None): Point prompt labels with shape (N,) or (N, num_points). 1 for foreground, 0 for background.
+            masks (list | np.ndarray | None): Masks for the objects, where each mask is a 2D array.
 
         Returns:
             points (torch.Tensor | None): Transformed points.
@@ -842,13 +842,13 @@ class SAM2Predictor(Predictor):
         Perform inference on image features using the SAM2 model.
 
         Args:
-            features (torch.Tensor | Dict[str, Any]): Extracted image features with shape (B, C, H, W) from the SAM2 model image encoder, it
+            features (torch.Tensor | dict[str, Any]): Extracted image features with shape (B, C, H, W) from the SAM2 model image encoder, it
                 could also be a dictionary including:
                 - image_embed (torch.Tensor): Image embedding with shape (B, C, H, W).
-                - high_res_feats (List[torch.Tensor]): List of high-resolution feature maps from the backbone, each with shape (B, C, H, W).
-            points (np.ndarray | List[List[float]] | None): Object location points with shape (N, 2), in pixels.
-            labels (np.ndarray | List[int] | None): Point prompt labels with shape (N,). 1 = foreground, 0 = background.
-            masks (List[np.ndarray] | np.ndarray | None): Masks for the objects, where each mask is a 2D array.
+                - high_res_feats (list[torch.Tensor]): List of high-resolution feature maps from the backbone, each with shape (B, C, H, W).
+            points (np.ndarray | list[list[float]] | None): Object location points with shape (N, 2), in pixels.
+            labels (np.ndarray | list[int] | None): Point prompt labels with shape (N,). 1 = foreground, 0 = background.
+            masks (list[np.ndarray] | np.ndarray | None): Masks for the objects, where each mask is a 2D array.
             multimask_output (bool): Flag to return multiple masks for ambiguous prompts.
             img_idx (int): Index of the image in the batch to process.
 
@@ -962,9 +962,9 @@ class SAM2VideoPredictor(SAM2Predictor):
 
         Args:
             im (torch.Tensor): The preprocessed input image in tensor format, with shape (N, C, H, W).
-            bboxes (np.ndarray | List, optional): Bounding boxes with shape (N, 4), in XYXY format.
-            points (np.ndarray | List, optional): Points indicating object locations with shape (N, 2), in pixels.
-            labels (np.ndarray | List, optional): Labels for point prompts, shape (N, ). 1 = foreground, 0 = background.
+            bboxes (np.ndarray | list, optional): Bounding boxes with shape (N, 4), in XYXY format.
+            points (np.ndarray | list, optional): Points indicating object locations with shape (N, 2), in pixels.
+            labels (np.ndarray | list, optional): Labels for point prompts, shape (N, ). 1 = foreground, 0 = background.
             masks (np.ndarray, optional): Low-resolution masks from previous predictions shape (N,H,W). For SAM H=W=256.
 
         Returns:
@@ -1036,9 +1036,9 @@ class SAM2VideoPredictor(SAM2Predictor):
         the masks do not overlap, which can be useful for certain applications.
 
         Args:
-            preds (Tuple[torch.Tensor, torch.Tensor]): The predicted masks and scores from the model.
+            preds (tuple[torch.Tensor, torch.Tensor]): The predicted masks and scores from the model.
             img (torch.Tensor): The processed image tensor.
-            orig_imgs (List[np.ndarray]): The original images before processing.
+            orig_imgs (list[np.ndarray]): The original images before processing.
 
         Returns:
             (list): The post-processed predictions.
@@ -1286,7 +1286,7 @@ class SAM2VideoPredictor(SAM2Predictor):
         Returns:
             vis_feats (torch.Tensor): The visual features extracted from the image.
             vis_pos_embed (torch.Tensor): The positional embeddings for the visual features.
-            feat_sizes (List[tuple]): A list containing the sizes of the extracted features.
+            feat_sizes (list[tuple]): A list containing the sizes of the extracted features.
 
         Note:
             - If `batch` is greater than 1, the features are expanded to fit the batch size.
@@ -1442,11 +1442,11 @@ class SAM2VideoPredictor(SAM2Predictor):
         the current batch size.
 
         Args:
-            out_maskmem_pos_enc (List[torch.Tensor] | None): The positional encoding for mask memory.
+            out_maskmem_pos_enc (list[torch.Tensor] | None): The positional encoding for mask memory.
                 Should be a list of tensors or None.
 
         Returns:
-            (List[torch.Tensor]): The positional encoding for mask memory, either cached or expanded.
+            (list[torch.Tensor]): The positional encoding for mask memory, either cached or expanded.
 
         Note:
             - The method assumes that `out_maskmem_pos_enc` is a list of tensors or None.
@@ -1730,10 +1730,10 @@ class SAM2DynamicInteractivePredictor(SAM2Predictor):
         specified overrides
 
         Args:
-            cfg (Dict[str, Any]): Configuration dictionary containing default settings.
-            overrides (Dict[str, Any] | None): Dictionary of values to override default configuration.
+            cfg (dict[str, Any]): Configuration dictionary containing default settings.
+            overrides (dict[str, Any] | None): Dictionary of values to override default configuration.
             max_obj_num (int): Maximum number of objects to track. Default is 3. this is set to keep fix feature size for the model.
-            _callbacks (Dict[str, Any] | None): Dictionary of callback functions to customize behavior.
+            _callbacks (dict[str, Any] | None): Dictionary of callback functions to customize behavior.
 
         Examples:
             >>> predictor = SAM2DynamicInteractivePredictor(cfg=DEFAULT_CFG)
@@ -1778,11 +1778,11 @@ class SAM2DynamicInteractivePredictor(SAM2Predictor):
 
         Args:
             im (torch.Tensor | np.ndarray): The input image tensor or numpy array.
-            bboxes (List[List[float]] | None): Optional list of bounding boxes to update the memory.
-            masks (List[torch.Tensor | np.ndarray] | None): Optional masks to update the memory.
-            points (List[List[float]] | None): Optional list of points to update the memory, each point is [x, y].
-            labels (List[int] | None): Optional list of object IDs corresponding to the points (>0 for positive, 0 for negative).
-            obj_ids (List[int] | None): Optional list of object IDs corresponding to the prompts.
+            bboxes (list[list[float]] | None): Optional list of bounding boxes to update the memory.
+            masks (list[torch.Tensor | np.ndarray] | None): Optional masks to update the memory.
+            points (list[list[float]] | None): Optional list of points to update the memory, each point is [x, y].
+            labels (list[int] | None): Optional list of object IDs corresponding to the points (>0 for positive, 0 for negative).
+            obj_ids (list[int] | None): Optional list of object IDs corresponding to the prompts.
             update_memory (bool): Flag to indicate whether to update the memory with new objects.
 
         Returns:
@@ -1855,7 +1855,7 @@ class SAM2DynamicInteractivePredictor(SAM2Predictor):
         Append the imgState to the memory_bank and update the memory for the model.
 
         Args:
-            obj_ids (List[int]): List of object IDs corresponding to the prompts.
+            obj_ids (list[int]): List of object IDs corresponding to the prompts.
             points (torch.Tensor | None): Tensor of shape (B, N, 2) representing the input points for N objects.
             labels (torch.Tensor | None): Tensor of shape (B, N) representing the labels for the input points.
             masks (torch.Tensor | None): Optional tensor of shape (N, H, W) representing the input masks for N objects.
@@ -2009,7 +2009,7 @@ class SAM2DynamicInteractivePredictor(SAM2Predictor):
             mask (torch.Tensor | None): The mask input for the object with shape (H, W).
 
         Returns:
-            current_out (Dict[str, Any]): A dictionary containing the current output with mask predictions and object pointers.
+            current_out (dict[str, Any]): A dictionary containing the current output with mask predictions and object pointers.
                 Keys include 'point_inputs', 'mask_inputs', 'pred_masks', 'pred_masks_high_res', 'obj_ptr', 'object_score_logits'.
         """
         if mask is not None and self.model.use_mask_input_as_output_without_sam:

ultralytics/models/utils/loss.py

@@ -23,7 +23,7 @@ class DETRLoss(nn.Module):
 
     Attributes:
         nc (int): Number of classes.
-        loss_gain (Dict[str, float]): Coefficients for different loss components.
+        loss_gain (dict[str, float]): 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.
@@ -55,7 +55,7 @@ class DETRLoss(nn.Module):
 
         Args:
             nc (int): Number of classes.
-            loss_gain (Dict[str, float], optional): Coefficients for different loss components.
+            loss_gain (dict[str, float], optional): 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.
@@ -93,7 +93,7 @@ class DETRLoss(nn.Module):
             postfix (str, optional): String to append to the loss name for identification in multi-loss scenarios.
 
         Returns:
-            (Dict[str, torch.Tensor]): Dictionary containing classification loss value.
+            (dict[str, torch.Tensor]): Dictionary containing classification loss value.
 
         Notes:
             The function supports different classification loss types:
@@ -133,7 +133,7 @@ class DETRLoss(nn.Module):
             postfix (str, optional): String to append to the loss names for identification in multi-loss scenarios.
 
         Returns:
-            (Dict[str, torch.Tensor]): Dictionary containing:
+            (dict[str, torch.Tensor]): Dictionary containing:
                 - loss_bbox{postfix}: L1 loss between predicted and ground truth boxes, scaled by the bbox loss gain.
                 - loss_giou{postfix}: GIoU loss between predicted and ground truth boxes, scaled by the giou loss gain.
 
@@ -207,14 +207,14 @@ class DETRLoss(nn.Module):
             pred_scores (torch.Tensor): Predicted scores from auxiliary layers.
             gt_bboxes (torch.Tensor): Ground truth bounding boxes.
             gt_cls (torch.Tensor): Ground truth classes.
-            gt_groups (List[int]): Number of ground truths per image.
-            match_indices (List[Tuple], optional): Pre-computed matching indices.
+            gt_groups (list[int]): Number of ground truths per image.
+            match_indices (list[tuple], optional): Pre-computed matching indices.
             postfix (str, optional): String to append to loss names.
             masks (torch.Tensor, optional): Predicted masks if using segmentation.
             gt_mask (torch.Tensor, optional): Ground truth masks if using segmentation.
 
         Returns:
-            (Dict[str, torch.Tensor]): Dictionary of auxiliary losses.
+            (dict[str, torch.Tensor]): 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)
@@ -265,10 +265,10 @@ class DETRLoss(nn.Module):
         Extract batch indices, source indices, and destination indices from match indices.
 
         Args:
-            match_indices (List[Tuple]): List of tuples containing matched indices.
+            match_indices (list[tuple]): List of tuples containing matched indices.
 
         Returns:
-            batch_idx (Tuple[torch.Tensor, torch.Tensor]): Tuple containing (batch_idx, src_idx).
+            batch_idx (tuple[torch.Tensor, torch.Tensor]): Tuple containing (batch_idx, src_idx).
             dst_idx (torch.Tensor): Destination indices.
         """
         batch_idx = torch.cat([torch.full_like(src, i) for i, (src, _) in enumerate(match_indices)])
@@ -285,7 +285,7 @@ class DETRLoss(nn.Module):
         Args:
             pred_bboxes (torch.Tensor): Predicted bounding boxes.
             gt_bboxes (torch.Tensor): Ground truth bounding boxes.
-            match_indices (List[Tuple]): List of tuples containing matched indices.
+            match_indices (list[tuple]): List of tuples containing matched indices.
 
         Returns:
             pred_assigned (torch.Tensor): Assigned predicted bounding boxes.
@@ -325,14 +325,14 @@ class DETRLoss(nn.Module):
             pred_scores (torch.Tensor): Predicted class scores.
             gt_bboxes (torch.Tensor): Ground truth bounding boxes.
             gt_cls (torch.Tensor): Ground truth classes.
-            gt_groups (List[int]): Number of ground truths per image.
+            gt_groups (list[int]): Number of ground truths per image.
             masks (torch.Tensor, optional): Predicted masks if using segmentation.
             gt_mask (torch.Tensor, optional): Ground truth masks if using segmentation.
             postfix (str, optional): String to append to loss names.
-            match_indices (List[Tuple], optional): Pre-computed matching indices.
+            match_indices (list[tuple], optional): Pre-computed matching indices.
 
         Returns:
-            (Dict[str, torch.Tensor]): Dictionary of losses.
+            (dict[str, torch.Tensor]): Dictionary of losses.
         """
         if match_indices is None:
             match_indices = self.matcher(
@@ -370,12 +370,12 @@ class DETRLoss(nn.Module):
         Args:
             pred_bboxes (torch.Tensor): Predicted bounding boxes, shape (L, B, N, 4).
             pred_scores (torch.Tensor): Predicted class scores, shape (L, B, N, C).
-            batch (Dict[str, Any]): Batch information containing cls, bboxes, and gt_groups.
+            batch (dict[str, Any]): Batch information containing cls, bboxes, and gt_groups.
             postfix (str, optional): Postfix for loss names.
             **kwargs (Any): Additional arguments, may include 'match_indices'.
 
         Returns:
-            (Dict[str, torch.Tensor]): Computed losses, including main and auxiliary (if enabled).
+            (dict[str, torch.Tensor]): 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
@@ -419,14 +419,14 @@ class RTDETRDetectionLoss(DETRLoss):
         Forward pass to compute detection loss with optional denoising loss.
 
         Args:
-            preds (Tuple[torch.Tensor, torch.Tensor]): Tuple containing predicted bounding boxes and scores.
-            batch (Dict[str, Any]): Batch data containing ground truth information.
+            preds (tuple[torch.Tensor, torch.Tensor]): Tuple containing predicted bounding boxes and scores.
+            batch (dict[str, Any]): Batch data containing ground truth information.
             dn_bboxes (torch.Tensor, optional): Denoising bounding boxes.
             dn_scores (torch.Tensor, optional): Denoising scores.
-            dn_meta (Dict[str, Any], optional): Metadata for denoising.
+            dn_meta (dict[str, Any], optional): Metadata for denoising.
 
         Returns:
-            (Dict[str, torch.Tensor]): Dictionary containing total loss and denoising loss if applicable.
+            (dict[str, torch.Tensor]): Dictionary containing total loss and denoising loss if applicable.
         """
         pred_bboxes, pred_scores = preds
         total_loss = super().forward(pred_bboxes, pred_scores, batch)
@@ -456,12 +456,12 @@ class RTDETRDetectionLoss(DETRLoss):
         Get match indices for denoising.
 
         Args:
-            dn_pos_idx (List[torch.Tensor]): List of tensors containing positive indices for denoising.
+            dn_pos_idx (list[torch.Tensor]): List of tensors containing positive indices for denoising.
             dn_num_group (int): Number of denoising groups.
-            gt_groups (List[int]): List of integers representing number of ground truths per image.
+            gt_groups (list[int]): List of integers representing number of ground truths per image.
 
         Returns:
-            (List[Tuple[torch.Tensor, torch.Tensor]]): List of tuples containing matched indices for denoising.
+            (list[tuple[torch.Tensor, torch.Tensor]]): List of tuples containing matched indices for denoising.
         """
         dn_match_indices = []
         idx_groups = torch.as_tensor([0, *gt_groups[:-1]]).cumsum_(0)

ultralytics/models/utils/ops.py

@@ -22,7 +22,7 @@ class HungarianMatcher(nn.Module):
     used in end-to-end object detection models like DETR.
 
     Attributes:
-        cost_gain (Dict[str, float]): Dictionary of cost coefficients for 'class', 'bbox', 'giou', 'mask', and 'dice'
+        cost_gain (dict[str, float]): Dictionary of cost coefficients for 'class', 'bbox', 'giou', 'mask', and 'dice'
             components.
         use_fl (bool): Whether to use Focal Loss for classification cost calculation.
         with_mask (bool): Whether the model makes mask predictions.
@@ -60,7 +60,7 @@ class HungarianMatcher(nn.Module):
         Initialize HungarianMatcher for optimal assignment of predicted and ground truth bounding boxes.
 
         Args:
-            cost_gain (Dict[str, float], optional): Dictionary of cost coefficients for different matching cost
+            cost_gain (dict[str, float], optional): Dictionary of cost coefficients for different matching cost
                 components. Should contain keys 'class', 'bbox', 'giou', 'mask', and 'dice'.
             use_fl (bool): Whether to use Focal Loss for classification cost calculation.
             with_mask (bool): Whether the model makes mask predictions.
@@ -100,12 +100,12 @@ class HungarianMatcher(nn.Module):
                 num_classes).
             gt_bboxes (torch.Tensor): Ground truth bounding boxes with shape (num_gts, 4).
             gt_cls (torch.Tensor): Ground truth class labels with shape (num_gts,).
-            gt_groups (List[int]): Number of ground truth boxes for each image in the batch.
+            gt_groups (list[int]): Number of ground truth boxes for each image in the batch.
             masks (torch.Tensor, optional): Predicted masks with shape (batch_size, num_queries, height, width).
-            gt_mask (List[torch.Tensor], optional): Ground truth masks, each with shape (num_masks, Height, Width).
+            gt_mask (list[torch.Tensor], optional): 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
+            (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)
                 and 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).
@@ -205,8 +205,8 @@ def get_cdn_group(
     bounding boxes and class labels. It generates both positive and negative samples to improve model robustness.
 
     Args:
-        batch (Dict[str, Any]): Batch dictionary containing 'gt_cls' (torch.Tensor with shape (num_gts,)),
-            'gt_bboxes' (torch.Tensor with shape (num_gts, 4)), and 'gt_groups' (List[int]) indicating number of
+        batch (dict[str, Any]): Batch dictionary containing 'gt_cls' (torch.Tensor with shape (num_gts,)),
+            'gt_bboxes' (torch.Tensor with shape (num_gts, 4)), and 'gt_groups' (list[int]) indicating number of
             ground truths per image.
         num_classes (int): Total number of object classes.
         num_queries (int): Number of object queries.
@@ -220,7 +220,7 @@ def get_cdn_group(
         padding_cls (torch.Tensor | None): Modified class embeddings for denoising with shape (bs, num_dn, embed_dim).
         padding_bbox (torch.Tensor | None): Modified bounding boxes for denoising with shape (bs, num_dn, 4).
         attn_mask (torch.Tensor | None): Attention mask for denoising with shape (tgt_size, tgt_size).
-        dn_meta (Dict[str, Any] | None): Meta information dictionary containing denoising parameters.
+        dn_meta (dict[str, Any] | None): Meta information dictionary containing denoising parameters.
 
     Examples:
         Generate denoising group for training

ultralytics/models/yolo/classify/predict.py

@@ -78,10 +78,10 @@ class ClassificationPredictor(BasePredictor):
         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.
+            orig_imgs (list[np.ndarray] | torch.Tensor): Original images before preprocessing.
 
         Returns:
-            (List[Results]): List of Results objects containing classification results for each image.
+            (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)

ultralytics/models/yolo/classify/train.py

@@ -25,8 +25,8 @@ class ClassificationTrainer(BaseTrainer):
 
     Attributes:
         model (ClassificationModel): The classification model to be trained.
-        data (Dict[str, Any]): Dictionary containing dataset information including class names and number of classes.
-        loss_names (List[str]): Names of the loss functions used during training.
+        data (dict[str, Any]): 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:
@@ -59,9 +59,9 @@ class ClassificationTrainer(BaseTrainer):
         image size if not specified.
 
         Args:
-            cfg (Dict[str, Any], optional): Default configuration dictionary containing training parameters.
-            overrides (Dict[str, Any], optional): Dictionary of parameter overrides for the default configuration.
-            _callbacks (List[Any], optional): List of callback functions to be executed during training.
+            cfg (dict[str, Any], optional): Default configuration dictionary containing training parameters.
+            overrides (dict[str, Any], optional): Dictionary of parameter overrides for the default configuration.
+            _callbacks (list[Any], optional): List of callback functions to be executed during training.
 
         Examples:
             Create a trainer with custom configuration
@@ -196,8 +196,8 @@ class ClassificationTrainer(BaseTrainer):
             prefix (str, optional): Prefix to prepend to loss names.
 
         Returns:
-            keys (List[str]): List of loss keys if loss_items is None.
-            loss_dict (Dict[str, float]): Dictionary of loss items if loss_items is provided.
+            keys (list[str]): List of loss keys if loss_items is None.
+            loss_dict (dict[str, float]): Dictionary of loss items if loss_items is provided.
         """
         keys = [f"{prefix}/{x}" for x in self.loss_names]
         if loss_items is None:
@@ -227,7 +227,7 @@ class ClassificationTrainer(BaseTrainer):
         Plot training samples with their annotations.
 
         Args:
-            batch (Dict[str, torch.Tensor]): Batch containing images and class labels.
+            batch (dict[str, torch.Tensor]): Batch containing images and class labels.
             ni (int): Number of iterations.
         """
         batch["batch_idx"] = torch.arange(len(batch["img"]))  # add batch index for plotting

ultralytics/models/yolo/classify/val.py

@@ -22,8 +22,8 @@ class ClassificationValidator(BaseValidator):
     confusion matrix generation, and visualization of results.
 
     Attributes:
-        targets (List[torch.Tensor]): Ground truth class labels.
-        pred (List[torch.Tensor]): Model predictions.
+        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.
         nc (int): Number of classes.
@@ -170,7 +170,7 @@ class ClassificationValidator(BaseValidator):
         Plot validation image samples with their ground truth labels.
 
         Args:
-            batch (Dict[str, Any]): Dictionary containing batch data with 'img' (images) and 'cls' (class labels).
+            batch (dict[str, Any]): Dictionary containing batch data with 'img' (images) and 'cls' (class labels).
             ni (int): Batch index used for naming the output file.
 
         Examples:
@@ -191,7 +191,7 @@ class ClassificationValidator(BaseValidator):
         Plot images with their predicted class labels and save the visualization.
 
         Args:
-            batch (Dict[str, Any]): Batch data containing images and other information.
+            batch (dict[str, Any]): Batch data containing images and other information.
             preds (torch.Tensor): Model predictions with shape (batch_size, num_classes).
             ni (int): Batch index used for naming the output file.
 

ultralytics/models/yolo/detect/predict.py

@@ -96,12 +96,12 @@ class DetectionPredictor(BasePredictor):
         Construct a list of Results objects from model predictions.
 
         Args:
-            preds (List[torch.Tensor]): List of predicted bounding boxes and scores for each image.
+            preds (list[torch.Tensor]): List of predicted bounding boxes and scores for each image.
             img (torch.Tensor): Batch of preprocessed images used for inference.
-            orig_imgs (List[np.ndarray]): List of original images before preprocessing.
+            orig_imgs (list[np.ndarray]): List of original images before preprocessing.
 
         Returns:
-            (List[Results]): List of Results objects containing detection information for each image.
+            (list[Results]): List of Results objects containing detection information for each image.
         """
         return [
             self.construct_result(pred, img, orig_img, img_path)