dgenerate-ultralytics-headless 8.3.194__py3-none-any.whl → 8.3.196__py3-none-any.whl

ultralytics/models/yolo/segment/val.py

@@ -57,13 +57,13 @@ class SegmentationValidator(DetectionValidator):
         Preprocess batch of images for YOLO segmentation validation.
 
         Args:
-            batch (Dict[str, Any]): Batch containing images and annotations.
+            batch (dict[str, Any]): Batch containing images and annotations.
 
         Returns:
-            (Dict[str, Any]): Preprocessed batch.
+            (dict[str, Any]): Preprocessed batch.
         """
         batch = super().preprocess(batch)
-        batch["masks"] = batch["masks"].to(self.device, non_blocking=True).float()
+        batch["masks"] = batch["masks"].float()
         return batch
 
     def init_metrics(self, model: torch.nn.Module) -> None:
@@ -100,10 +100,10 @@ class SegmentationValidator(DetectionValidator):
         Post-process YOLO predictions and return output detections with proto.
 
         Args:
-            preds (List[torch.Tensor]): Raw predictions from the model.
+            preds (list[torch.Tensor]): Raw predictions from the model.
 
         Returns:
-            List[Dict[str, torch.Tensor]]: Processed detection predictions with masks.
+            list[dict[str, torch.Tensor]]: Processed detection predictions with masks.
         """
         proto = preds[1][-1] if len(preds[1]) == 3 else preds[1]  # second output is len 3 if pt, but only 1 if exported
         preds = super().postprocess(preds[0])
@@ -127,10 +127,10 @@ class SegmentationValidator(DetectionValidator):
 
         Args:
             si (int): Batch index.
-            batch (Dict[str, Any]): Batch data containing images and annotations.
+            batch (dict[str, Any]): Batch data containing images and annotations.
 
         Returns:
-            (Dict[str, Any]): Prepared batch with processed annotations.
+            (dict[str, Any]): Prepared batch with processed annotations.
         """
         prepared_batch = super()._prepare_batch(si, batch)
         nl = len(prepared_batch["cls"])
@@ -151,11 +151,11 @@ class SegmentationValidator(DetectionValidator):
         Compute correct prediction matrix for a batch based on bounding boxes and optional masks.
 
         Args:
-            preds (Dict[str, torch.Tensor]): Dictionary containing predictions with keys like 'cls' and 'masks'.
-            batch (Dict[str, Any]): Dictionary containing batch data with keys like 'cls' and 'masks'.
+            preds (dict[str, torch.Tensor]): Dictionary containing predictions with keys like 'cls' and 'masks'.
+            batch (dict[str, Any]): Dictionary containing batch data with keys like 'cls' and 'masks'.
 
         Returns:
-            (Dict[str, np.ndarray]): A dictionary containing correct prediction matrices including 'tp_m' for mask IoU.
+            (dict[str, np.ndarray]): A dictionary containing correct prediction matrices including 'tp_m' for mask IoU.
 
         Notes:
             - If `masks` is True, the function computes IoU between predicted and ground truth masks.
@@ -181,8 +181,8 @@ class SegmentationValidator(DetectionValidator):
         Plot batch predictions with masks and bounding boxes.
 
         Args:
-            batch (Dict[str, Any]): Batch containing images and annotations.
-            preds (List[Dict[str, torch.Tensor]]): List of predictions from the model.
+            batch (dict[str, Any]): Batch containing images and annotations.
+            preds (list[dict[str, torch.Tensor]]): List of predictions from the model.
             ni (int): Batch index.
         """
         for p in preds:
@@ -199,7 +199,7 @@ class SegmentationValidator(DetectionValidator):
         Args:
             predn (torch.Tensor): Predictions in the format (x1, y1, x2, y2, conf, class).
             save_conf (bool): Whether to save confidence scores.
-            shape (Tuple[int, int]): Shape of the original image.
+            shape (tuple[int, int]): Shape of the original image.
             file (Path): File path to save the detections.
         """
         from ultralytics.engine.results import Results
@@ -217,8 +217,8 @@ class SegmentationValidator(DetectionValidator):
         Save one JSON result for COCO evaluation.
 
         Args:
-            predn (Dict[str, torch.Tensor]): Predictions containing bboxes, masks, confidence scores, and classes.
-            pbatch (Dict[str, Any]): Batch dictionary containing 'imgsz', 'ori_shape', 'ratio_pad', and 'im_file'.
+            predn (dict[str, torch.Tensor]): Predictions containing bboxes, masks, confidence scores, and classes.
+            pbatch (dict[str, Any]): Batch dictionary containing 'imgsz', 'ori_shape', 'ratio_pad', and 'im_file'.
         """
         from faster_coco_eval.core.mask import encode  # noqa
 

ultralytics/models/yolo/world/train.py

@@ -12,7 +12,7 @@ from ultralytics.data import build_yolo_dataset
 from ultralytics.models.yolo.detect import DetectionTrainer
 from ultralytics.nn.tasks import WorldModel
 from ultralytics.utils import DEFAULT_CFG, LOGGER, RANK
-from ultralytics.utils.torch_utils import de_parallel
+from ultralytics.utils.torch_utils import unwrap_model
 
 
 def on_pretrain_routine_end(trainer) -> None:
@@ -20,7 +20,7 @@ def on_pretrain_routine_end(trainer) -> None:
     if RANK in {-1, 0}:
         # Set class names for evaluation
         names = [name.split("/", 1)[0] for name in list(trainer.test_loader.dataset.data["names"].values())]
-        de_parallel(trainer.ema.ema).set_classes(names, cache_clip_model=False)
+        unwrap_model(trainer.ema.ema).set_classes(names, cache_clip_model=False)
 
 
 class WorldTrainer(DetectionTrainer):
@@ -32,10 +32,10 @@ class WorldTrainer(DetectionTrainer):
     accelerate training with multi-modal data.
 
     Attributes:
-        text_embeddings (Dict[str, torch.Tensor] | None): Cached text embeddings for category names to accelerate
+        text_embeddings (dict[str, torch.Tensor] | None): Cached text embeddings for category names to accelerate
             training.
         model (WorldModel): The YOLO World model being trained.
-        data (Dict[str, Any]): Dataset configuration containing class information.
+        data (dict[str, Any]): Dataset configuration containing class information.
         args (Any): Training arguments and configuration.
 
     Methods:
@@ -58,9 +58,9 @@ class WorldTrainer(DetectionTrainer):
         Initialize a WorldTrainer object with given arguments.
 
         Args:
-            cfg (Dict[str, Any]): Configuration for the trainer.
-            overrides (Dict[str, Any], optional): Configuration overrides.
-            _callbacks (List[Any], optional): List of callback functions.
+            cfg (dict[str, Any]): Configuration for the trainer.
+            overrides (dict[str, Any], optional): Configuration overrides.
+            _callbacks (list[Any], optional): List of callback functions.
         """
         if overrides is None:
             overrides = {}
@@ -72,7 +72,7 @@ class WorldTrainer(DetectionTrainer):
         Return WorldModel initialized with specified config and weights.
 
         Args:
-            cfg (Dict[str, Any] | str, optional): Model configuration.
+            cfg (dict[str, Any] | str, optional): Model configuration.
             weights (str, optional): Path to pretrained weights.
             verbose (bool): Whether to display model info.
 
@@ -105,7 +105,7 @@ class WorldTrainer(DetectionTrainer):
         Returns:
             (Any): YOLO dataset configured for training or validation.
         """
-        gs = max(int(de_parallel(self.model).stride.max() if self.model else 0), 32)
+        gs = max(int(unwrap_model(self.model).stride.max() if self.model else 0), 32)
         dataset = build_yolo_dataset(
             self.args, img_path, batch, self.data, mode=mode, rect=mode == "val", stride=gs, multi_modal=mode == "train"
         )
@@ -121,7 +121,7 @@ class WorldTrainer(DetectionTrainer):
         for these categories to improve training efficiency.
 
         Args:
-            datasets (List[Any]): List of datasets from which to extract category names.
+            datasets (list[Any]): List of datasets from which to extract category names.
             batch (int | None): Batch size used for processing.
 
         Notes:
@@ -144,12 +144,12 @@ class WorldTrainer(DetectionTrainer):
         Generate text embeddings for a list of text samples.
 
         Args:
-            texts (List[str]): List of text samples to encode.
+            texts (list[str]): List of text samples to encode.
             batch (int): Batch size for processing.
             cache_dir (Path): Directory to save/load cached embeddings.
 
         Returns:
-            (Dict[str, torch.Tensor]): Dictionary mapping text samples to their embeddings.
+            (dict[str, torch.Tensor]): Dictionary mapping text samples to their embeddings.
         """
         model = "clip:ViT-B/32"
         cache_path = cache_dir / f"text_embeddings_{model.replace(':', '_').replace('/', '_')}.pt"
@@ -160,7 +160,7 @@ class WorldTrainer(DetectionTrainer):
                 return txt_map
         LOGGER.info(f"Caching text embeddings to '{cache_path}'")
         assert self.model is not None
-        txt_feats = de_parallel(self.model).get_text_pe(texts, batch, cache_clip_model=False)
+        txt_feats = unwrap_model(self.model).get_text_pe(texts, batch, cache_clip_model=False)
         txt_map = dict(zip(texts, txt_feats.squeeze(0)))
         torch.save(txt_map, cache_path)
         return txt_map

ultralytics/models/yolo/world/train_world.py

@@ -6,7 +6,7 @@ from ultralytics.data import YOLOConcatDataset, build_grounding, build_yolo_data
 from ultralytics.data.utils import check_det_dataset
 from ultralytics.models.yolo.world import WorldTrainer
 from ultralytics.utils import DATASETS_DIR, DEFAULT_CFG, LOGGER
-from ultralytics.utils.torch_utils import de_parallel
+from ultralytics.utils.torch_utils import unwrap_model
 
 
 class WorldTrainerFromScratch(WorldTrainer):
@@ -94,14 +94,14 @@ class WorldTrainerFromScratch(WorldTrainer):
         standard YOLO datasets and grounding datasets with different formats.
 
         Args:
-            img_path (List[str] | str): Path to the folder containing images or list of paths.
+            img_path (list[str] | str): Path to the folder containing images or list of paths.
             mode (str): 'train' mode or 'val' mode, allowing customized augmentations for each mode.
             batch (int, optional): Size of batches, used for rectangular training/validation.
 
         Returns:
             (YOLOConcatDataset | Dataset): The constructed dataset for training or validation.
         """
-        gs = max(int(de_parallel(self.model).stride.max() if self.model else 0), 32)
+        gs = max(int(unwrap_model(self.model).stride.max() if self.model else 0), 32)
         if mode != "train":
             return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, rect=False, stride=gs)
         datasets = [

ultralytics/models/yolo/yoloe/predict.py

@@ -75,12 +75,12 @@ class YOLOEVPDetectPredictor(DetectionPredictor):
         else:
             # NOTE: only supports bboxes as prompts for now
             assert bboxes is not None, f"Expected bboxes, but got {bboxes}!"
-            # NOTE: needs List[np.ndarray]
+            # NOTE: needs list[np.ndarray]
             assert isinstance(bboxes, list) and all(isinstance(b, np.ndarray) for b in bboxes), (
-                f"Expected List[np.ndarray], but got {bboxes}!"
+                f"Expected list[np.ndarray], but got {bboxes}!"
             )
             assert isinstance(category, list) and all(isinstance(b, np.ndarray) for b in category), (
-                f"Expected List[np.ndarray], but got {category}!"
+                f"Expected list[np.ndarray], but got {category}!"
             )
             assert len(im) == len(category) == len(bboxes), (
                 f"Expected same length for all inputs, but got {len(im)}vs{len(category)}vs{len(bboxes)}!"
@@ -149,7 +149,7 @@ class YOLOEVPDetectPredictor(DetectionPredictor):
         Process the source to get the visual prompt embeddings (VPE).
 
         Args:
-            source (str | Path | int | PIL.Image | np.ndarray | torch.Tensor | List | Tuple): The source
+            source (str | Path | int | PIL.Image | np.ndarray | torch.Tensor | list | tuple): The source
                 of the image to make predictions on. Accepts various types including file paths, URLs, PIL
                 images, numpy arrays, and torch tensors.
 

ultralytics/models/yolo/yoloe/train.py

@@ -13,7 +13,7 @@ from ultralytics.data.augment import LoadVisualPrompt
 from ultralytics.models.yolo.detect import DetectionTrainer, DetectionValidator
 from ultralytics.nn.tasks import YOLOEModel
 from ultralytics.utils import DEFAULT_CFG, LOGGER, RANK
-from ultralytics.utils.torch_utils import de_parallel
+from ultralytics.utils.torch_utils import unwrap_model
 
 from ..world.train_world import WorldTrainerFromScratch
 from .val import YOLOEDetectValidator
@@ -39,9 +39,6 @@ class YOLOETrainer(DetectionTrainer):
         """
         Initialize the YOLOE Trainer with specified configurations.
 
-        This method sets up the YOLOE trainer with the provided configuration and overrides, initializing
-        the training environment, model, and callbacks for YOLOE object detection training.
-
         Args:
             cfg (dict): Configuration dictionary with default training settings from DEFAULT_CFG.
             overrides (dict, optional): Dictionary of parameter overrides for the default configuration.
@@ -102,7 +99,7 @@ class YOLOETrainer(DetectionTrainer):
         Returns:
             (Dataset): YOLO dataset configured for training or validation.
         """
-        gs = max(int(de_parallel(self.model).stride.max() if self.model else 0), 32)
+        gs = max(int(unwrap_model(self.model).stride.max() if self.model else 0), 32)
         return build_yolo_dataset(
             self.args, img_path, batch, self.data, mode=mode, rect=mode == "val", stride=gs, multi_modal=mode == "train"
         )
@@ -183,7 +180,7 @@ class YOLOETrainerFromScratch(YOLOETrainer, WorldTrainerFromScratch):
         standard YOLO datasets and grounding datasets with different formats.
 
         Args:
-            img_path (List[str] | str): Path to the folder containing images or list of paths.
+            img_path (list[str] | str): Path to the folder containing images or list of paths.
             mode (str): 'train' mode or 'val' mode, allowing customized augmentations for each mode.
             batch (int, optional): Size of batches, used for rectangular training/validation.
 
@@ -207,7 +204,7 @@ class YOLOETrainerFromScratch(YOLOETrainer, WorldTrainerFromScratch):
         Generate text embeddings for a list of text samples.
 
         Args:
-            texts (List[str]): List of text samples to encode.
+            texts (list[str]): List of text samples to encode.
             batch (int): Batch size for processing.
             cache_dir (Path): Directory to save/load cached embeddings.
 
@@ -223,7 +220,7 @@ class YOLOETrainerFromScratch(YOLOETrainer, WorldTrainerFromScratch):
                 return txt_map
         LOGGER.info(f"Caching text embeddings to '{cache_path}'")
         assert self.model is not None
-        txt_feats = de_parallel(self.model).get_text_pe(texts, batch, without_reprta=True, cache_clip_model=False)
+        txt_feats = unwrap_model(self.model).get_text_pe(texts, batch, without_reprta=True, cache_clip_model=False)
         txt_map = dict(zip(texts, txt_feats.squeeze(0)))
         torch.save(txt_map, cache_path)
         return txt_map
@@ -262,7 +259,7 @@ class YOLOEPEFreeTrainer(YOLOEPETrainer, YOLOETrainerFromScratch):
         in the parent directory of the first dataset's image path.
 
         Args:
-            datasets (List[Dataset]): List of datasets containing category names to process.
+            datasets (list[Dataset]): List of datasets containing category names to process.
             batch (int): Batch size for processing text embeddings.
 
         Notes:
@@ -290,7 +287,7 @@ class YOLOEVPTrainer(YOLOETrainerFromScratch):
         Build YOLO Dataset for training or validation with visual prompts.
 
         Args:
-            img_path (List[str] | str): Path to the folder containing images or list of paths.
+            img_path (list[str] | str): Path to the folder containing images or list of paths.
             mode (str): 'train' mode or 'val' mode, allowing customized augmentations for each mode.
             batch (int, optional): Size of batches, used for rectangular training/validation.
 
@@ -313,9 +310,3 @@ class YOLOEVPTrainer(YOLOETrainerFromScratch):
                 d.transforms.append(LoadVisualPrompt())
         else:
             self.train_loader.dataset.transforms.append(LoadVisualPrompt())
-
-    def preprocess_batch(self, batch):
-        """Preprocess a batch of images for YOLOE training, moving visual prompts to the appropriate device."""
-        batch = super().preprocess_batch(batch)
-        batch["visuals"] = batch["visuals"].to(self.device, non_blocking=True)
-        return batch

ultralytics/models/yolo/yoloe/val.py

@@ -98,13 +98,6 @@ class YOLOEDetectValidator(DetectionValidator):
         visual_pe[cls_visual_num == 0] = 0
         return visual_pe.unsqueeze(0)
 
-    def preprocess(self, batch: dict[str, Any]) -> dict[str, Any]:
-        """Preprocess batch data, ensuring visuals are on the same device as images."""
-        batch = super().preprocess(batch)
-        if "visuals" in batch:
-            batch["visuals"] = batch["visuals"].to(batch["img"].device, non_blocking=True)
-        return batch
-
     def get_vpe_dataloader(self, data: dict[str, Any]) -> torch.utils.data.DataLoader:
         """
         Create a dataloader for LVIS training visual prompt samples.

ultralytics/nn/autobackend.py

@@ -624,7 +624,7 @@ class AutoBackend(nn.Module):
             **kwargs (Any): Additional keyword arguments for model configuration.
 
         Returns:
-            (torch.Tensor | List[torch.Tensor]): The raw output tensor(s) from the model.
+            (torch.Tensor | list[torch.Tensor]): The raw output tensor(s) from the model.
         """
         b, ch, h, w = im.shape  # batch, channel, height, width
         if self.fp16 and im.dtype != torch.float16:
@@ -860,7 +860,7 @@ class AutoBackend(nn.Module):
             p (str): Path to the model file.
 
         Returns:
-            (List[bool]): List of booleans indicating the model type.
+            (list[bool]): List of booleans indicating the model type.
 
         Examples:
             >>> model = AutoBackend(model="path/to/model.onnx")

ultralytics/nn/modules/block.py

@@ -745,7 +745,7 @@ class ImagePoolingAttn(nn.Module):
         Forward pass of ImagePoolingAttn.
 
         Args:
-            x (List[torch.Tensor]): List of input feature maps.
+            x (list[torch.Tensor]): List of input feature maps.
             text (torch.Tensor): Text embeddings.
 
         Returns:
@@ -1032,7 +1032,7 @@ class CBLinear(nn.Module):
 
         Args:
             c1 (int): Input channels.
-            c2s (List[int]): List of output channel sizes.
+            c2s (list[int]): List of output channel sizes.
             k (int): Kernel size.
             s (int): Stride.
             p (int | None): Padding.
@@ -1055,7 +1055,7 @@ class CBFuse(nn.Module):
         Initialize CBFuse module.
 
         Args:
-            idx (List[int]): Indices for feature selection.
+            idx (list[int]): Indices for feature selection.
         """
         super().__init__()
         self.idx = idx
@@ -1065,7 +1065,7 @@ class CBFuse(nn.Module):
         Forward pass through CBFuse layer.
 
         Args:
-            xs (List[torch.Tensor]): List of input tensors.
+            xs (list[torch.Tensor]): List of input tensors.
 
         Returns:
             (torch.Tensor): Fused output tensor.
@@ -1676,7 +1676,7 @@ class TorchVision(nn.Module):
             x (torch.Tensor): Input tensor.
 
         Returns:
-            (torch.Tensor | List[torch.Tensor]): Output tensor or list of tensors.
+            (torch.Tensor | list[torch.Tensor]): Output tensor or list of tensors.
         """
         if self.split:
             y = [x]
@@ -1979,7 +1979,7 @@ class SAVPE(nn.Module):
         Initialize SAVPE module with channels, intermediate channels, and embedding dimension.
 
         Args:
-            ch (List[int]): List of input channel dimensions.
+            ch (list[int]): List of input channel dimensions.
             c3 (int): Intermediate channels.
             embed (int): Embedding dimension.
         """

ultralytics/nn/modules/conv.py

@@ -675,7 +675,7 @@ class Concat(nn.Module):
         Concatenate input tensors along specified dimension.
 
         Args:
-            x (List[torch.Tensor]): List of input tensors.
+            x (list[torch.Tensor]): List of input tensors.
 
         Returns:
             (torch.Tensor): Concatenated tensor.
@@ -706,7 +706,7 @@ class Index(nn.Module):
         Select and return a particular index from input.
 
         Args:
-            x (List[torch.Tensor]): List of input tensors.
+            x (list[torch.Tensor]): List of input tensors.
 
         Returns:
             (torch.Tensor): Selected tensor.

ultralytics/nn/modules/head.py

@@ -13,7 +13,7 @@ from torch.nn.init import constant_, xavier_uniform_
 
 from ultralytics.utils import NOT_MACOS14
 from ultralytics.utils.tal import TORCH_1_10, dist2bbox, dist2rbox, make_anchors
-from ultralytics.utils.torch_utils import fuse_conv_and_bn, smart_inference_mode
+from ultralytics.utils.torch_utils import disable_dynamo, fuse_conv_and_bn, smart_inference_mode
 
 from .block import DFL, SAVPE, BNContrastiveHead, ContrastiveHead, Proto, Residual, SwiGLUFFN
 from .conv import Conv, DWConv
@@ -130,7 +130,7 @@ class Detect(nn.Module):
         Perform forward pass of the v10Detect module.
 
         Args:
-            x (List[torch.Tensor]): Input feature maps from different levels.
+            x (list[torch.Tensor]): Input feature maps from different levels.
 
         Returns:
             outputs (dict | tuple): Training mode returns dict with one2many and one2one outputs.
@@ -149,12 +149,13 @@ class Detect(nn.Module):
         y = self.postprocess(y.permute(0, 2, 1), self.max_det, self.nc)
         return y if self.export else (y, {"one2many": x, "one2one": one2one})
 
+    @disable_dynamo
     def _inference(self, x: list[torch.Tensor]) -> torch.Tensor:
         """
         Decode predicted bounding boxes and class probabilities based on multiple-level feature maps.
 
         Args:
-            x (List[torch.Tensor]): List of feature maps from different detection layers.
+            x (list[torch.Tensor]): List of feature maps from different detection layers.
 
         Returns:
             (torch.Tensor): Concatenated tensor of decoded bounding boxes and class probabilities.
@@ -985,7 +986,7 @@ class RTDETRDecoder(nn.Module):
         Run the forward pass of the module, returning bounding box and classification scores for the input.
 
         Args:
-            x (List[torch.Tensor]): List of feature maps from the backbone.
+            x (list[torch.Tensor]): List of feature maps from the backbone.
             batch (dict, optional): Batch information for training.
 
         Returns:
@@ -1075,7 +1076,7 @@ class RTDETRDecoder(nn.Module):
         Process and return encoder inputs by getting projection features from input and concatenating them.
 
         Args:
-            x (List[torch.Tensor]): List of feature maps from the backbone.
+            x (list[torch.Tensor]): List of feature maps from the backbone.
 
         Returns:
             feats (torch.Tensor): Processed features.

ultralytics/nn/tasks.py

@@ -69,7 +69,7 @@ from ultralytics.nn.modules import (
     YOLOESegment,
     v10Detect,
 )
-from ultralytics.utils import DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, YAML, colorstr, emojis
+from ultralytics.utils import DEFAULT_CFG_DICT, LOGGER, YAML, colorstr, emojis
 from ultralytics.utils.checks import check_requirements, check_suffix, check_yaml
 from ultralytics.utils.loss import (
     E2EDetectLoss,
@@ -329,12 +329,13 @@ class BaseModel(torch.nn.Module):
 
         Args:
             batch (dict): Batch to compute loss on.
-            preds (torch.Tensor | List[torch.Tensor], optional): Predictions.
+            preds (torch.Tensor | list[torch.Tensor], optional): Predictions.
         """
         if getattr(self, "criterion", None) is None:
             self.criterion = self.init_criterion()
 
-        preds = self.forward(batch["img"]) if preds is None else preds
+        if preds is None:
+            preds = self.forward(batch["img"])
         return self.criterion(preds, batch)
 
     def init_criterion(self):
@@ -480,10 +481,10 @@ class DetectionModel(BaseModel):
         Clip YOLO augmented inference tails.
 
         Args:
-            y (List[torch.Tensor]): List of detection tensors.
+            y (list[torch.Tensor]): List of detection tensors.
 
         Returns:
-            (List[torch.Tensor]): Clipped detection tensors.
+            (list[torch.Tensor]): Clipped detection tensors.
         """
         nl = self.model[-1].nl  # number of detection layers (P3-P5)
         g = sum(4**x for x in range(nl))  # grid points
@@ -775,7 +776,8 @@ class RTDETRDetectionModel(DetectionModel):
             "gt_groups": gt_groups,
         }
 
-        preds = self.predict(img, batch=targets) if preds is None else preds
+        if preds is None:
+            preds = self.predict(img, batch=targets)
         dec_bboxes, dec_scores, enc_bboxes, enc_scores, dn_meta = preds if self.training else preds[1]
         if dn_meta is None:
             dn_bboxes, dn_scores = None, None
@@ -874,7 +876,7 @@ class WorldModel(DetectionModel):
         Set classes in advance so that model could do offline-inference without clip model.
 
         Args:
-            text (List[str]): List of class names.
+            text (list[str]): List of class names.
             batch (int): Batch size for processing text tokens.
             cache_clip_model (bool): Whether to cache the CLIP model.
         """
@@ -886,7 +888,7 @@ class WorldModel(DetectionModel):
         Set classes in advance so that model could do offline-inference without clip model.
 
         Args:
-            text (List[str]): List of class names.
+            text (list[str]): List of class names.
             batch (int): Batch size for processing text tokens.
             cache_clip_model (bool): Whether to cache the CLIP model.
 
@@ -956,7 +958,7 @@ class WorldModel(DetectionModel):
 
         Args:
             batch (dict): Batch to compute loss on.
-            preds (torch.Tensor | List[torch.Tensor], optional): Predictions.
+            preds (torch.Tensor | list[torch.Tensor], optional): Predictions.
         """
         if not hasattr(self, "criterion"):
             self.criterion = self.init_criterion()
@@ -1012,7 +1014,7 @@ class YOLOEModel(DetectionModel):
         Set classes in advance so that model could do offline-inference without clip model.
 
         Args:
-            text (List[str]): List of class names.
+            text (list[str]): List of class names.
             batch (int): Batch size for processing text tokens.
             cache_clip_model (bool): Whether to cache the CLIP model.
             without_reprta (bool): Whether to return text embeddings cooperated with reprta module.
@@ -1060,7 +1062,7 @@ class YOLOEModel(DetectionModel):
 
         Args:
             vocab (nn.ModuleList): List of vocabulary items.
-            names (List[str]): List of class names.
+            names (list[str]): List of class names.
         """
         assert not self.training
         head = self.model[-1]
@@ -1114,7 +1116,7 @@ class YOLOEModel(DetectionModel):
         Set classes in advance so that model could do offline-inference without clip model.
 
         Args:
-            names (List[str]): List of class names.
+            names (list[str]): List of class names.
             embeddings (torch.Tensor): Embeddings tensor.
         """
         assert not hasattr(self.model[-1], "lrpc"), (
@@ -1203,7 +1205,7 @@ class YOLOEModel(DetectionModel):
 
         Args:
             batch (dict): Batch to compute loss on.
-            preds (torch.Tensor | List[torch.Tensor], optional): Predictions.
+            preds (torch.Tensor | list[torch.Tensor], optional): Predictions.
         """
         if not hasattr(self, "criterion"):
             from ultralytics.utils.loss import TVPDetectLoss
@@ -1251,7 +1253,7 @@ class YOLOESegModel(YOLOEModel, SegmentationModel):
 
         Args:
             batch (dict): Batch to compute loss on.
-            preds (torch.Tensor | List[torch.Tensor], optional): Predictions.
+            preds (torch.Tensor | list[torch.Tensor], optional): Predictions.
         """
         if not hasattr(self, "criterion"):
             from ultralytics.utils.loss import TVPSegmentLoss
@@ -1502,7 +1504,7 @@ def load_checkpoint(weight, device=None, inplace=True, fuse=False):
     model = (ckpt.get("ema") or ckpt["model"]).float()  # FP32 model
 
     # Model compatibility updates
-    model.args = {k: v for k, v in args.items() if k in DEFAULT_CFG_KEYS}  # attach args to model
+    model.args = args  # attach args to model
     model.pt_path = weight  # attach *.pt file path to model
     model.task = getattr(model, "task", guess_model_task(model))
     if not hasattr(model, "stride"):

ultralytics/nn/text_model.py

@@ -97,7 +97,7 @@ class CLIP(TextModel):
         Convert input texts to CLIP tokens.
 
         Args:
-            texts (str | List[str]): Input text or list of texts to tokenize.
+            texts (str | list[str]): Input text or list of texts to tokenize.
 
         Returns:
             (torch.Tensor): Tokenized text tensor with shape (batch_size, context_length) ready for model processing.
@@ -240,7 +240,7 @@ class MobileCLIP(TextModel):
         Convert input texts to MobileCLIP tokens.
 
         Args:
-            texts (List[str]): List of text strings to tokenize.
+            texts (list[str]): List of text strings to tokenize.
 
         Returns:
             (torch.Tensor): Tokenized text inputs with shape (batch_size, sequence_length).
@@ -325,7 +325,7 @@ class MobileCLIPTS(TextModel):
         Convert input texts to MobileCLIP tokens.
 
         Args:
-            texts (List[str]): List of text strings to tokenize.
+            texts (list[str]): List of text strings to tokenize.
 
         Returns:
             (torch.Tensor): Tokenized text inputs with shape (batch_size, sequence_length).

ultralytics/solutions/ai_gym.py

@@ -14,10 +14,10 @@ class AIGym(BaseSolution):
     repetitions of exercises based on predefined angle thresholds for up and down positions.
 
     Attributes:
-        states (Dict[float, int, str]): Stores per-track angle, count, and stage for workout monitoring.
+        states (dict[float, int, str]): Stores per-track angle, count, and stage for workout monitoring.
         up_angle (float): Angle threshold for considering the 'up' position of an exercise.
         down_angle (float): Angle threshold for considering the 'down' position of an exercise.
-        kpts (List[int]): Indices of keypoints used for angle calculation.
+        kpts (list[int]): Indices of keypoints used for angle calculation.
 
     Methods:
         process: Process a frame to detect poses, calculate angles, and count repetitions.