dgenerate-ultralytics-headless 8.3.230__py3-none-any.whl → 8.3.231__py3-none-any.whl

ultralytics/models/sam/modules/blocks.py

@@ -156,13 +156,6 @@ class CXBlock(nn.Module):
             drop_path (float): Stochastic depth rate.
             layer_scale_init_value (float): Initial value for Layer Scale.
             use_dwconv (bool): Whether to use depthwise convolution.
-
-        Examples:
-            >>> block = CXBlock(dim=64, kernel_size=7, padding=3)
-            >>> x = torch.randn(1, 64, 32, 32)
-            >>> output = block(x)
-            >>> print(output.shape)
-            torch.Size([1, 64, 32, 32])
         """
         super().__init__()
         self.dwconv = nn.Conv2d(
@@ -231,12 +224,6 @@ class Fuser(nn.Module):
             num_layers (int): The number of times to replicate the layer.
             dim (int | None): The dimension for input projection, if used.
             input_projection (bool): Whether to use input projection.
-
-        Examples:
-            >>> layer = nn.Linear(64, 64)
-            >>> fuser = Fuser(layer, num_layers=3, dim=64, input_projection=True)
-            >>> input_tensor = torch.randn(1, 64)
-            >>> output = fuser(input_tensor)
         """
         super().__init__()
         self.proj = nn.Identity()
@@ -304,12 +291,6 @@ class SAM2TwoWayAttentionBlock(TwoWayAttentionBlock):
             activation (Type[nn.Module]): The activation function of the MLP block.
             attention_downsample_rate (int): The downsample rate for attention computations.
             skip_first_layer_pe (bool): Whether to skip the positional encoding in the first layer.
-
-        Examples:
-            >>> block = SAM2TwoWayAttentionBlock(embedding_dim=256, num_heads=8, mlp_dim=2048)
-            >>> sparse_inputs = torch.randn(1, 100, 256)
-            >>> dense_inputs = torch.randn(1, 256, 32, 32)
-            >>> sparse_outputs, dense_outputs = block(sparse_inputs, dense_inputs)
         """
         super().__init__(embedding_dim, num_heads, mlp_dim, activation, attention_downsample_rate, skip_first_layer_pe)
         self.mlp = MLP(embedding_dim, mlp_dim, embedding_dim, num_layers=2, act=activation)
@@ -364,17 +345,6 @@ class SAM2TwoWayTransformer(TwoWayTransformer):
             mlp_dim (int): Channel dimension internal to the MLP block.
             activation (Type[nn.Module]): Activation function to use in the MLP block.
             attention_downsample_rate (int): Downsampling rate for attention computations.
-
-        Examples:
-            >>> transformer = SAM2TwoWayTransformer(depth=5, embedding_dim=256, num_heads=8, mlp_dim=2048)
-            >>> transformer
-            SAM2TwoWayTransformer(
-              (layers): ModuleList(
-                (0-4): 5 x SAM2TwoWayAttentionBlock(...)
-              )
-              (final_attn_token_to_image): Attention(...)
-              (norm_final_attn): LayerNorm(...)
-            )
         """
         super().__init__(depth, embedding_dim, num_heads, mlp_dim, activation, attention_downsample_rate)
         self.layers = nn.ModuleList()
@@ -917,13 +887,6 @@ class Block(nn.Module):
             rel_pos_zero_init (bool): If True, initializes relative positional parameters to zero.
             window_size (int): Size of attention window. If 0, uses global attention.
             input_size (tuple[int, int] | None): Input resolution for calculating relative positional parameter size.
-
-        Examples:
-            >>> block = Block(dim=256, num_heads=8, window_size=7)
-            >>> x = torch.randn(1, 56, 56, 256)
-            >>> output = block(x)
-            >>> print(output.shape)
-            torch.Size([1, 56, 56, 256])
         """
         super().__init__()
         self.norm1 = norm_layer(dim)
@@ -1008,13 +971,6 @@ class REAttention(nn.Module):
             rel_pos_zero_init (bool): If True, initializes relative positional parameters to zero.
             input_size (tuple[int, int] | None): Input resolution for calculating relative positional parameter size.
                 Required if use_rel_pos is True.
-
-        Examples:
-            >>> attention = REAttention(dim=256, num_heads=8, input_size=(32, 32))
-            >>> x = torch.randn(1, 32, 32, 256)
-            >>> output = attention(x)
-            >>> print(output.shape)
-            torch.Size([1, 32, 32, 256])
         """
         super().__init__()
         self.num_heads = num_heads
@@ -1089,13 +1045,6 @@ class PatchEmbed(nn.Module):
             padding (tuple[int, int]): Padding applied to the input before convolution.
             in_chans (int): Number of input image channels.
             embed_dim (int): Dimensionality of the output patch embeddings.
-
-        Examples:
-            >>> patch_embed = PatchEmbed(kernel_size=(16, 16), stride=(16, 16), in_chans=3, embed_dim=768)
-            >>> x = torch.randn(1, 3, 224, 224)
-            >>> output = patch_embed(x)
-            >>> print(output.shape)
-            torch.Size([1, 768, 14, 14])
         """
         super().__init__()
 

ultralytics/models/sam/modules/decoders.py

@@ -55,11 +55,6 @@ class MaskDecoder(nn.Module):
             activation (Type[nn.Module]): Type of activation to use when upscaling masks.
             iou_head_depth (int): Depth of the MLP used to predict mask quality.
             iou_head_hidden_dim (int): Hidden dimension of the MLP used to predict mask quality.
-
-        Examples:
-            >>> transformer = nn.TransformerEncoder(nn.TransformerEncoderLayer(d_model=256, nhead=8), num_layers=6)
-            >>> decoder = MaskDecoder(transformer_dim=256, transformer=transformer)
-            >>> print(decoder)
         """
         super().__init__()
         self.transformer_dim = transformer_dim
@@ -249,11 +244,6 @@ class SAM2MaskDecoder(nn.Module):
             pred_obj_scores (bool): Whether to predict object scores.
             pred_obj_scores_mlp (bool): Whether to use MLP for object score prediction.
             use_multimask_token_for_obj_ptr (bool): Whether to use multimask token for object pointer.
-
-        Examples:
-            >>> transformer = nn.TransformerEncoder(nn.TransformerEncoderLayer(d_model=256, nhead=8), num_layers=6)
-            >>> decoder = SAM2MaskDecoder(transformer_dim=256, transformer=transformer)
-            >>> print(decoder)
         """
         super().__init__()
         self.transformer_dim = transformer_dim

ultralytics/models/sam/modules/encoders.py

@@ -82,12 +82,6 @@ class ImageEncoderViT(nn.Module):
             rel_pos_zero_init (bool): If True, initializes relative positional parameters to zero.
             window_size (int): Size of attention window for windowed attention blocks.
             global_attn_indexes (tuple[int, ...]): Indices of blocks that use global attention.
-
-        Examples:
-            >>> encoder = ImageEncoderViT(img_size=224, patch_size=16, embed_dim=768, depth=12, num_heads=12)
-            >>> input_image = torch.randn(1, 3, 224, 224)
-            >>> output = encoder(input_image)
-            >>> print(output.shape)
         """
         super().__init__()
         self.img_size = img_size
@@ -198,15 +192,6 @@ class PromptEncoder(nn.Module):
             input_image_size (tuple[int, int]): The padded size of the input image as (H, W).
             mask_in_chans (int): The number of hidden channels used for encoding input masks.
             activation (Type[nn.Module]): The activation function to use when encoding input masks.
-
-        Examples:
-            >>> prompt_encoder = PromptEncoder(256, (64, 64), (1024, 1024), 16)
-            >>> points = (torch.rand(1, 5, 2), torch.randint(0, 4, (1, 5)))
-            >>> boxes = torch.rand(1, 2, 2)
-            >>> masks = torch.rand(1, 1, 256, 256)
-            >>> sparse_embeddings, dense_embeddings = prompt_encoder(points, boxes, masks)
-            >>> print(sparse_embeddings.shape, dense_embeddings.shape)
-            torch.Size([1, 7, 256]) torch.Size([1, 256, 64, 64])
         """
         super().__init__()
         self.embed_dim = embed_dim
@@ -385,14 +370,6 @@ class MemoryEncoder(nn.Module):
         Args:
             out_dim (int): Output dimension of the encoded features.
             in_dim (int): Input dimension of the pixel features.
-
-        Examples:
-            >>> encoder = MemoryEncoder(out_dim=256, in_dim=256)
-            >>> pix_feat = torch.randn(1, 256, 64, 64)
-            >>> masks = torch.randn(1, 1, 64, 64)
-            >>> encoded_feat, pos = encoder(pix_feat, masks)
-            >>> print(encoded_feat.shape, pos.shape)
-            torch.Size([1, 256, 64, 64]) torch.Size([1, 128, 64, 64])
         """
         super().__init__()
 
@@ -468,15 +445,6 @@ class ImageEncoder(nn.Module):
             trunk (nn.Module): The trunk network for initial feature extraction.
             neck (nn.Module): The neck network for feature refinement and positional encoding generation.
             scalp (int): Number of lowest resolution feature levels to discard.
-
-        Examples:
-            >>> trunk = SomeTrunkNetwork()
-            >>> neck = SomeNeckNetwork()
-            >>> encoder = ImageEncoder(trunk, neck, scalp=1)
-            >>> image = torch.randn(1, 3, 224, 224)
-            >>> output = encoder(image)
-            >>> print(output.keys())
-            dict_keys(['vision_features', 'vision_pos_enc', 'backbone_fpn'])
         """
         super().__init__()
         self.trunk = trunk
@@ -552,11 +520,6 @@ class FpnNeck(nn.Module):
             fpn_interp_model (str): Interpolation mode for FPN feature resizing.
             fuse_type (str): Type of feature fusion, either 'sum' or 'avg'.
             fpn_top_down_levels (Optional[list[int]]): Levels to have top-down features in outputs.
-
-        Examples:
-            >>> backbone_channels = [64, 128, 256, 512]
-            >>> fpn_neck = FpnNeck(256, backbone_channels)
-            >>> print(fpn_neck)
         """
         super().__init__()
         self.position_encoding = PositionEmbeddingSine(num_pos_feats=256)
@@ -720,13 +683,6 @@ class Hiera(nn.Module):
             window_spec (tuple[int, ...]): Window sizes for each stage when not using global attention.
             global_att_blocks (tuple[int, ...]): Indices of blocks that use global attention.
             return_interm_layers (bool): Whether to return intermediate layer outputs.
-
-        Examples:
-            >>> model = Hiera(embed_dim=96, num_heads=1, stages=(2, 3, 16, 3))
-            >>> input_tensor = torch.randn(1, 3, 224, 224)
-            >>> output_features = model(input_tensor)
-            >>> for feat in output_features:
-            ...     print(feat.shape)
         """
         super().__init__()
 

ultralytics/models/sam/modules/memory_attention.py

@@ -213,18 +213,6 @@ class MemoryAttention(nn.Module):
             layer (nn.Module): The attention layer to be used in the module.
             num_layers (int): The number of attention layers.
             batch_first (bool): Whether the input tensors are in batch-first format.
-
-        Examples:
-            >>> d_model = 256
-            >>> layer = MemoryAttentionLayer(d_model)
-            >>> attention = MemoryAttention(d_model, pos_enc_at_input=True, layer=layer, num_layers=3)
-            >>> curr = torch.randn(10, 32, d_model)  # (seq_len, batch_size, d_model)
-            >>> memory = torch.randn(20, 32, d_model)  # (mem_len, batch_size, d_model)
-            >>> curr_pos = torch.randn(10, 32, d_model)
-            >>> memory_pos = torch.randn(20, 32, d_model)
-            >>> output = attention(curr, memory, curr_pos, memory_pos)
-            >>> print(output.shape)
-            torch.Size([10, 32, 256])
         """
         super().__init__()
         self.d_model = d_model

ultralytics/models/sam/modules/sam.py

@@ -69,13 +69,6 @@ class SAMModel(nn.Module):
             pixel_mean (list[float]): Mean values for normalizing pixels in the input image.
             pixel_std (list[float]): Standard deviation values for normalizing pixels in the input image.
 
-        Examples:
-            >>> image_encoder = ImageEncoderViT(...)
-            >>> prompt_encoder = PromptEncoder(...)
-            >>> mask_decoder = MaskDecoder(...)
-            >>> sam_model = SAMModel(image_encoder, prompt_encoder, mask_decoder)
-            >>> # Further usage depends on SAMPredictor class
-
         Notes:
             All forward() operations moved to SAMPredictor.
         """
@@ -253,15 +246,6 @@ class SAM2Model(torch.nn.Module):
             no_obj_embed_spatial (bool): Whether add no obj embedding to spatial frames.
             sam_mask_decoder_extra_args (dict | None): Extra arguments for constructing the SAM mask decoder.
             compile_image_encoder (bool): Whether to compile the image encoder for faster inference.
-
-        Examples:
-            >>> image_encoder = ImageEncoderViT(...)
-            >>> memory_attention = SAM2TwoWayTransformer(...)
-            >>> memory_encoder = nn.Sequential(...)
-            >>> model = SAM2Model(image_encoder, memory_attention, memory_encoder)
-            >>> image_batch = torch.rand(1, 3, 512, 512)
-            >>> features = model.forward_image(image_batch)
-            >>> track_results = model.track_step(0, True, features, None, None, None, {})
         """
         super().__init__()
 

ultralytics/models/sam/predict.py

@@ -90,11 +90,6 @@ class Predictor(BasePredictor):
             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.
-
-        Examples:
-            >>> predictor_example = Predictor(cfg=DEFAULT_CFG)
-            >>> predictor_example_with_imgsz = Predictor(overrides={"imgsz": 640})
-            >>> predictor_example_with_callback = Predictor(_callbacks={"on_predict_start": custom_callback})
         """
         if overrides is None:
             overrides = {}
@@ -918,11 +913,6 @@ class SAM2VideoPredictor(SAM2Predictor):
             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.
-
-        Examples:
-            >>> predictor = SAM2VideoPredictor(cfg=DEFAULT_CFG)
-            >>> predictor_example_with_imgsz = SAM2VideoPredictor(overrides={"imgsz": 640})
-            >>> predictor_example_with_callback = SAM2VideoPredictor(_callbacks={"on_predict_start": custom_callback})
         """
         super().__init__(cfg, overrides, _callbacks)
         self.inference_state = {}
@@ -1710,13 +1700,6 @@ class SAM2DynamicInteractivePredictor(SAM2Predictor):
             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.
-
-        Examples:
-            >>> predictor = SAM2DynamicInteractivePredictor(cfg=DEFAULT_CFG)
-            >>> predictor_example_with_imgsz = SAM2DynamicInteractivePredictor(overrides={"imgsz": 640})
-            >>> predictor_example_with_callback = SAM2DynamicInteractivePredictor(
-            ...     _callbacks={"on_predict_start": custom_callback}
-            ... )
         """
         super().__init__(cfg, overrides, _callbacks)
         self.non_overlap_masks = True

ultralytics/models/yolo/classify/val.py

@@ -61,12 +61,6 @@ class ClassificationValidator(BaseValidator):
             save_dir (str | Path, optional): Directory to save results.
             args (dict, optional): Arguments containing model and validation configuration.
             _callbacks (list, optional): List of callback functions to be called during validation.
-
-        Examples:
-            >>> from ultralytics.models.yolo.classify import ClassificationValidator
-            >>> args = dict(model="yolo11n-cls.pt", data="imagenet10")
-            >>> validator = ClassificationValidator(args=args)
-            >>> validator()
         """
         super().__init__(dataloader, save_dir, args, _callbacks)
         self.targets = None

ultralytics/models/yolo/model.py

@@ -61,11 +61,6 @@ class YOLO(Model):
             task (str, optional): YOLO task specification, i.e. 'detect', 'segment', 'classify', 'pose', 'obb'. Defaults
                 to auto-detection based on model.
             verbose (bool): Display model info on load.
-
-        Examples:
-            >>> from ultralytics import YOLO
-            >>> model = YOLO("yolo11n.pt")  # load a pretrained YOLO11n detection model
-            >>> model = YOLO("yolo11n-seg.pt")  # load a pretrained YOLO11n segmentation model
         """
         path = Path(model if isinstance(model, (str, Path)) else "")
         if "-world" in path.stem and path.suffix in {".pt", ".yaml", ".yml"}:  # if YOLOWorld PyTorch model

ultralytics/models/yolo/obb/predict.py

@@ -32,12 +32,6 @@ class OBBPredictor(DetectionPredictor):
             cfg (dict, optional): Default configuration for the predictor.
             overrides (dict, optional): Configuration overrides that take precedence over the default config.
             _callbacks (list, optional): List of callback functions to be invoked during prediction.
-
-        Examples:
-            >>> from ultralytics.utils import ASSETS
-            >>> from ultralytics.models.yolo.obb import OBBPredictor
-            >>> args = dict(model="yolo11n-obb.pt", source=ASSETS)
-            >>> predictor = OBBPredictor(overrides=args)
         """
         super().__init__(cfg, overrides, _callbacks)
         self.args.task = "obb"

ultralytics/models/yolo/pose/predict.py

@@ -1,7 +1,7 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 from ultralytics.models.yolo.detect.predict import DetectionPredictor
-from ultralytics.utils import DEFAULT_CFG, LOGGER, ops
+from ultralytics.utils import DEFAULT_CFG, ops
 
 
 class PosePredictor(DetectionPredictor):
@@ -35,21 +35,9 @@ class PosePredictor(DetectionPredictor):
             cfg (Any): Configuration for the predictor.
             overrides (dict, optional): Configuration overrides that take precedence over cfg.
             _callbacks (list, optional): List of callback functions to be invoked during prediction.
-
-        Examples:
-            >>> from ultralytics.utils import ASSETS
-            >>> from ultralytics.models.yolo.pose import PosePredictor
-            >>> args = dict(model="yolo11n-pose.pt", source=ASSETS)
-            >>> predictor = PosePredictor(overrides=args)
-            >>> predictor.predict_cli()
         """
         super().__init__(cfg, overrides, _callbacks)
         self.args.task = "pose"
-        if isinstance(self.args.device, str) and self.args.device.lower() == "mps":
-            LOGGER.warning(
-                "Apple MPS known Pose bug. Recommend 'device=cpu' for Pose models. "
-                "See https://github.com/ultralytics/ultralytics/issues/4031."
-            )
 
     def construct_result(self, pred, img, orig_img, img_path):
         """Construct the result object from the prediction, including keypoints.

ultralytics/models/yolo/pose/train.py

@@ -8,7 +8,7 @@ from typing import Any
 
 from ultralytics.models import yolo
 from ultralytics.nn.tasks import PoseModel
-from ultralytics.utils import DEFAULT_CFG, LOGGER
+from ultralytics.utils import DEFAULT_CFG
 
 
 class PoseTrainer(yolo.detect.DetectionTrainer):
@@ -54,12 +54,6 @@ class PoseTrainer(yolo.detect.DetectionTrainer):
         overrides["task"] = "pose"
         super().__init__(cfg, overrides, _callbacks)
 
-        if isinstance(self.args.device, str) and self.args.device.lower() == "mps":
-            LOGGER.warning(
-                "Apple MPS known Pose bug. Recommend 'device=cpu' for Pose models. "
-                "See https://github.com/ultralytics/ultralytics/issues/4031."
-            )
-
     def get_model(
         self,
         cfg: str | Path | dict[str, Any] | None = None,

ultralytics/models/yolo/pose/val.py

@@ -9,7 +9,7 @@ import numpy as np
 import torch
 
 from ultralytics.models.yolo.detect import DetectionValidator
-from ultralytics.utils import LOGGER, ops
+from ultralytics.utils import ops
 from ultralytics.utils.metrics import OKS_SIGMA, PoseMetrics, kpt_iou
 
 
@@ -45,6 +45,11 @@ class PoseValidator(DetectionValidator):
         >>> args = dict(model="yolo11n-pose.pt", data="coco8-pose.yaml")
         >>> validator = PoseValidator(args=args)
         >>> validator()
+
+    Notes:
+        This class extends DetectionValidator with pose-specific functionality. It initializes with sigma values
+        for OKS calculation and sets up PoseMetrics for evaluation. A warning is displayed when using Apple MPS
+        due to a known bug with pose models.
     """
 
     def __init__(self, dataloader=None, save_dir=None, args=None, _callbacks=None) -> None:
@@ -58,28 +63,12 @@ class PoseValidator(DetectionValidator):
             save_dir (Path | str, optional): Directory to save results.
             args (dict, optional): Arguments for the validator including task set to "pose".
             _callbacks (list, optional): List of callback functions to be executed during validation.
-
-        Examples:
-            >>> from ultralytics.models.yolo.pose import PoseValidator
-            >>> args = dict(model="yolo11n-pose.pt", data="coco8-pose.yaml")
-            >>> validator = PoseValidator(args=args)
-            >>> validator()
-
-        Notes:
-            This class extends DetectionValidator with pose-specific functionality. It initializes with sigma values
-            for OKS calculation and sets up PoseMetrics for evaluation. A warning is displayed when using Apple MPS
-            due to a known bug with pose models.
         """
         super().__init__(dataloader, save_dir, args, _callbacks)
         self.sigma = None
         self.kpt_shape = None
         self.args.task = "pose"
         self.metrics = PoseMetrics()
-        if isinstance(self.args.device, str) and self.args.device.lower() == "mps":
-            LOGGER.warning(
-                "Apple MPS known Pose bug. Recommend 'device=cpu' for Pose models. "
-                "See https://github.com/ultralytics/ultralytics/issues/4031."
-            )
 
     def preprocess(self, batch: dict[str, Any]) -> dict[str, Any]:
         """Preprocess batch by converting keypoints data to float and moving it to the device."""

ultralytics/models/yolo/world/train_world.py

@@ -61,24 +61,6 @@ class WorldTrainerFromScratch(WorldTrainer):
             cfg (dict): Configuration dictionary with default parameters for model training.
             overrides (dict, optional): Dictionary of parameter overrides to customize the configuration.
             _callbacks (list, optional): List of callback functions to be executed during different stages of training.
-
-        Examples:
-            >>> from ultralytics.models.yolo.world.train_world import WorldTrainerFromScratch
-            >>> from ultralytics import YOLOWorld
-            >>> data = dict(
-            ...     train=dict(
-            ...         yolo_data=["Objects365.yaml"],
-            ...         grounding_data=[
-            ...             dict(
-            ...                 img_path="flickr30k/images",
-            ...                 json_file="flickr30k/final_flickr_separateGT_train.json",
-            ...             ),
-            ...         ],
-            ...     ),
-            ...     val=dict(yolo_data=["lvis.yaml"]),
-            ... )
-            >>> model = YOLOWorld("yolov8s-worldv2.yaml")
-            >>> model.train(data=data, trainer=WorldTrainerFromScratch)
         """
         if overrides is None:
             overrides = {}

ultralytics/nn/text_model.py

@@ -77,11 +77,6 @@ class CLIP(TextModel):
         Args:
             size (str): Model size identifier (e.g., 'ViT-B/32').
             device (torch.device): Device to load the model on.
-
-        Examples:
-            >>> import torch
-            >>> clip_model = CLIP("ViT-B/32", device=torch.device("cuda:0"))
-            >>> text_features = clip_model.encode_text(["a photo of a cat", "a photo of a dog"])
         """
         super().__init__()
         self.model, self.image_preprocess = clip.load(size, device=device)
@@ -199,12 +194,6 @@ class MobileCLIP(TextModel):
         Args:
             size (str): Model size identifier (e.g., 's0', 's1', 's2', 'b', 'blt').
             device (torch.device): Device to load the model on.
-
-        Examples:
-            >>> import torch
-            >>> model = MobileCLIP("s0", device=torch.device("cpu"))
-            >>> tokens = model.tokenize(["a photo of a cat", "a photo of a dog"])
-            >>> features = model.encode_text(tokens)
         """
         try:
             import warnings
@@ -299,11 +288,6 @@ class MobileCLIPTS(TextModel):
 
         Args:
             device (torch.device): Device to load the model on.
-
-        Examples:
-            >>> model = MobileCLIPTS(device=torch.device("cpu"))
-            >>> tokens = model.tokenize(["a photo of a cat", "a photo of a dog"])
-            >>> features = model.encode_text(tokens)
         """
         super().__init__()
         from ultralytics.utils.downloads import attempt_download_asset

ultralytics/trackers/bot_sort.py

@@ -64,14 +64,6 @@ class BOTrack(STrack):
             cls (int): Class ID of the detected object.
             feat (np.ndarray, optional): Feature vector associated with the detection.
             feat_history (int): Maximum length of the feature history deque.
-
-        Examples:
-            Initialize a BOTrack object with bounding box, score, class ID, and feature vector
-            >>> xywh = np.array([100, 150, 60, 50])
-            >>> score = 0.9
-            >>> cls = 1
-            >>> feat = np.random.rand(128)
-            >>> bo_track = BOTrack(xywh, score, cls, feat)
         """
         super().__init__(xywh, score, cls)
 
@@ -184,11 +176,6 @@ class BOTSORT(BYTETracker):
         Args:
             args (Any): Parsed command-line arguments containing tracking parameters.
             frame_rate (int): Frame rate of the video being processed.
-
-        Examples:
-            Initialize BOTSORT with command-line arguments and a specified frame rate:
-            >>> args = parse_args()
-            >>> bot_sort = BOTSORT(args, frame_rate=30)
         """
         super().__init__(args, frame_rate)
         self.gmc = GMC(method=args.gmc_method)

ultralytics/trackers/byte_tracker.py

@@ -60,12 +60,6 @@ class STrack(BaseTrack):
                 y) is the center, (w, h) are width and height, [a] is optional aspect ratio, and idx is the id.
             score (float): Confidence score of the detection.
             cls (Any): Class label for the detected object.
-
-        Examples:
-            >>> xywh = [100.0, 150.0, 50.0, 75.0, 1]
-            >>> score = 0.9
-            >>> cls = "person"
-            >>> track = STrack(xywh, score, cls)
         """
         super().__init__()
         # xywh+idx or xywha+idx
@@ -275,11 +269,6 @@ class BYTETracker:
         Args:
             args (Namespace): Command-line arguments containing tracking parameters.
             frame_rate (int): Frame rate of the video sequence.
-
-        Examples:
-            Initialize BYTETracker with command-line arguments and a frame rate of 30
-            >>> args = Namespace(track_buffer=30)
-            >>> tracker = BYTETracker(args, frame_rate=30)
         """
         self.tracked_stracks = []  # type: list[STrack]
         self.lost_stracks = []  # type: list[STrack]

ultralytics/trackers/utils/gmc.py

@@ -47,10 +47,6 @@ class GMC:
         Args:
             method (str): The tracking method to use. Options include 'orb', 'sift', 'ecc', 'sparseOptFlow', 'none'.
             downscale (int): Downscale factor for processing frames.
-
-        Examples:
-            Initialize a GMC object with the 'sparseOptFlow' method and a downscale factor of 2
-            >>> gmc = GMC(method="sparseOptFlow", downscale=2)
         """
         super().__init__()
 

ultralytics/trackers/utils/kalman_filter.py

@@ -42,10 +42,6 @@ class KalmanFilterXYAH:
         represents the bounding box center position, 'a' is the aspect ratio, 'h' is the height, and their respective
         velocities are (vx, vy, va, vh). The filter uses a constant velocity model for object motion and a linear
         observation model for bounding box location.
-
-        Examples:
-            Initialize a Kalman filter for tracking:
-            >>> kf = KalmanFilterXYAH()
         """
         ndim, dt = 4, 1.0
 

ultralytics/utils/__init__.py

@@ -1181,7 +1181,8 @@ class JSONDict(dict):
         try:
             if self.file_path.exists():
                 with open(self.file_path) as f:
-                    self.update(json.load(f))
+                    # Use the base dict update to avoid persisting during reads
+                    super().update(json.load(f))
         except json.JSONDecodeError:
             LOGGER.warning(f"Error decoding JSON from {self.file_path}. Starting with an empty dictionary.")
         except Exception as e:

ultralytics/utils/benchmarks.py

@@ -423,12 +423,6 @@ class ProfileModels:
             trt (bool): Flag to indicate whether to profile using TensorRT.
             device (torch.device | str | None): Device used for profiling. If None, it is determined automatically.
 
-        Examples:
-            Initialize and profile models
-            >>> from ultralytics.utils.benchmarks import ProfileModels
-            >>> profiler = ProfileModels(["yolo11n.yaml", "yolov8s.yaml"], imgsz=640)
-            >>> profiler.run()
-
         Notes:
             FP16 'half' argument option removed for ONNX as slower on CPU than FP32.
         """

ultralytics/utils/errors.py

@@ -31,11 +31,5 @@ class HUBModelError(Exception):
 
         Args:
             message (str, optional): The error message to display when the exception is raised.
-
-        Examples:
-            >>> try:
-            ...     raise HUBModelError("Custom model error message")
-            ... except HUBModelError as e:
-            ...     print(e)
         """
         super().__init__(emojis(message))

ultralytics/utils/metrics.py

@@ -15,7 +15,10 @@ import torch
 from ultralytics.utils import LOGGER, DataExportMixin, SimpleClass, TryExcept, checks, plt_settings
 
 OKS_SIGMA = (
-    np.array([0.26, 0.25, 0.25, 0.35, 0.35, 0.79, 0.79, 0.72, 0.72, 0.62, 0.62, 1.07, 1.07, 0.87, 0.87, 0.89, 0.89])
+    np.array(
+        [0.26, 0.25, 0.25, 0.35, 0.35, 0.79, 0.79, 0.72, 0.72, 0.62, 0.62, 1.07, 1.07, 0.87, 0.87, 0.89, 0.89],
+        dtype=np.float32,
+    )
     / 10.0
 )
 

ultralytics/utils/tqdm.py

@@ -109,11 +109,6 @@ class TQDM:
             bar_format (str, optional): Custom bar format string.
             initial (int, optional): Initial counter value.
             **kwargs (Any): Additional keyword arguments for compatibility (ignored).
-
-        Examples:
-            >>> pbar = TQDM(range(100), desc="Processing")
-            >>> with TQDM(total=1000, unit="B", unit_scale=True) as pbar:
-            ...     pbar.update(1024)  # Updates by 1KB
         """
         # Disable if not verbose
         if disable is None: