ultralytics 8.2.81__py3-none-any.whl → 8.2.83__py3-none-any.whl

ultralytics/models/sam/model.py

@@ -41,8 +41,8 @@ class SAM(Model):
         info: Logs information about the SAM model.
 
     Examples:
-        >>> sam = SAM('sam_b.pt')
-        >>> results = sam.predict('image.jpg', points=[[500, 375]])
+        >>> sam = SAM("sam_b.pt")
+        >>> results = sam.predict("image.jpg", points=[[500, 375]])
         >>> for r in results:
         >>>     print(f"Detected {len(r.masks)} masks")
     """
@@ -58,7 +58,7 @@ class SAM(Model):
             NotImplementedError: If the model file extension is not .pt or .pth.
 
         Examples:
-            >>> sam = SAM('sam_b.pt')
+            >>> sam = SAM("sam_b.pt")
             >>> print(sam.is_sam2)
         """
         if model and Path(model).suffix not in {".pt", ".pth"}:
@@ -78,8 +78,8 @@ class SAM(Model):
             task (str | None): Task name. If provided, it specifies the particular task the model is being loaded for.
 
         Examples:
-            >>> sam = SAM('sam_b.pt')
-            >>> sam._load('path/to/custom_weights.pt')
+            >>> sam = SAM("sam_b.pt")
+            >>> sam._load("path/to/custom_weights.pt")
         """
         self.model = build_sam(weights)
 
@@ -100,8 +100,8 @@ class SAM(Model):
             (List): The model predictions.
 
         Examples:
-            >>> sam = SAM('sam_b.pt')
-            >>> results = sam.predict('image.jpg', points=[[500, 375]])
+            >>> sam = SAM("sam_b.pt")
+            >>> results = sam.predict("image.jpg", points=[[500, 375]])
             >>> for r in results:
             ...     print(f"Detected {len(r.masks)} masks")
         """
@@ -130,8 +130,8 @@ class SAM(Model):
             (List): The model predictions, typically containing segmentation masks and other relevant information.
 
         Examples:
-            >>> sam = SAM('sam_b.pt')
-            >>> results = sam('image.jpg', points=[[500, 375]])
+            >>> sam = SAM("sam_b.pt")
+            >>> results = sam("image.jpg", points=[[500, 375]])
             >>> print(f"Detected {len(results[0].masks)} masks")
         """
         return self.predict(source, stream, bboxes, points, labels, **kwargs)
@@ -151,7 +151,7 @@ class SAM(Model):
             (Tuple): A tuple containing the model's information (string representations of the model).
 
         Examples:
-            >>> sam = SAM('sam_b.pt')
+            >>> sam = SAM("sam_b.pt")
             >>> info = sam.info()
             >>> print(info[0])  # Print summary information
         """
@@ -167,7 +167,7 @@ class SAM(Model):
                 class. For SAM2 models, it maps to SAM2Predictor, otherwise to the standard Predictor.
 
         Examples:
-            >>> sam = SAM('sam_b.pt')
+            >>> sam = SAM("sam_b.pt")
             >>> task_map = sam.task_map
             >>> print(task_map)
             {'segment': <class 'ultralytics.models.sam.predict.Predictor'>}

ultralytics/models/sam/modules/decoders.py

@@ -32,8 +32,9 @@ class MaskDecoder(nn.Module):
 
     Examples:
         >>> decoder = MaskDecoder(transformer_dim=256, transformer=transformer_module)
-        >>> masks, iou_pred = decoder(image_embeddings, image_pe, sparse_prompt_embeddings,
-        ...                           dense_prompt_embeddings, multimask_output=True)
+        >>> masks, iou_pred = decoder(
+        ...     image_embeddings, image_pe, sparse_prompt_embeddings, dense_prompt_embeddings, multimask_output=True
+        ... )
         >>> print(f"Predicted masks shape: {masks.shape}, IoU predictions shape: {iou_pred.shape}")
     """
 
@@ -213,7 +214,8 @@ class SAM2MaskDecoder(nn.Module):
         >>> dense_prompt_embeddings = torch.rand(1, 256, 64, 64)
         >>> decoder = SAM2MaskDecoder(256, transformer)
         >>> masks, iou_pred, sam_tokens_out, obj_score_logits = decoder.forward(
-        ...     image_embeddings, image_pe, sparse_prompt_embeddings, dense_prompt_embeddings, True, False)
+        ...     image_embeddings, image_pe, sparse_prompt_embeddings, dense_prompt_embeddings, True, False
+        ... )
     """
 
     def __init__(
@@ -345,7 +347,8 @@ class SAM2MaskDecoder(nn.Module):
             >>> dense_prompt_embeddings = torch.rand(1, 256, 64, 64)
             >>> decoder = SAM2MaskDecoder(256, transformer)
             >>> masks, iou_pred, sam_tokens_out, obj_score_logits = decoder.forward(
-            ...     image_embeddings, image_pe, sparse_prompt_embeddings, dense_prompt_embeddings, True, False)
+            ...     image_embeddings, image_pe, sparse_prompt_embeddings, dense_prompt_embeddings, True, False
+            ... )
         """
         masks, iou_pred, mask_tokens_out, object_score_logits = self.predict_masks(
             image_embeddings=image_embeddings,

ultralytics/models/sam/modules/sam.py

@@ -417,7 +417,15 @@ class SAM2Model(torch.nn.Module):
             >>> point_inputs = {"point_coords": torch.rand(1, 2, 2), "point_labels": torch.tensor([[1, 0]])}
             >>> mask_inputs = torch.rand(1, 1, 512, 512)
             >>> results = model._forward_sam_heads(backbone_features, point_inputs, mask_inputs)
-            >>> low_res_multimasks, high_res_multimasks, ious, low_res_masks, high_res_masks, obj_ptr, object_score_logits = results
+            >>> (
+            ...     low_res_multimasks,
+            ...     high_res_multimasks,
+            ...     ious,
+            ...     low_res_masks,
+            ...     high_res_masks,
+            ...     obj_ptr,
+            ...     object_score_logits,
+            ... ) = results
         """
         B = backbone_features.size(0)
         device = backbone_features.device

ultralytics/models/sam/modules/tiny_encoder.py

@@ -716,7 +716,7 @@ class BasicLayer(nn.Module):
 
         Examples:
             >>> layer = BasicLayer(dim=96, input_resolution=(56, 56), depth=2, num_heads=3, window_size=7)
-            >>> x = torch.randn(1, 56*56, 96)
+            >>> x = torch.randn(1, 56 * 56, 96)
             >>> output = layer(x)
             >>> print(output.shape)
         """

ultralytics/models/sam/modules/transformer.py

@@ -232,7 +232,6 @@ class TwoWayAttentionBlock(nn.Module):
 
     def forward(self, queries: Tensor, keys: Tensor, query_pe: Tensor, key_pe: Tensor) -> Tuple[Tensor, Tensor]:
         """Applies two-way attention to process query and key embeddings in a transformer block."""
-
         # Self attention block
         if self.skip_first_layer_pe:
             queries = self.self_attn(q=queries, k=queries, v=queries)
@@ -353,7 +352,6 @@ class Attention(nn.Module):
 
     def forward(self, q: Tensor, k: Tensor, v: Tensor) -> Tensor:
         """Applies multi-head attention to query, key, and value tensors with optional downsampling."""
-
         # Input projections
         q = self.q_proj(q)
         k = self.k_proj(k)

ultralytics/models/sam/modules/utils.py

@@ -22,7 +22,7 @@ def select_closest_cond_frames(frame_idx, cond_frame_outputs, max_cond_frame_num
 
     Examples:
         >>> frame_idx = 5
-        >>> cond_frame_outputs = {1: 'a', 3: 'b', 7: 'c', 9: 'd'}
+        >>> cond_frame_outputs = {1: "a", 3: "b", 7: "c", 9: "d"}
         >>> max_cond_frame_num = 2
         >>> selected, unselected = select_closest_cond_frames(frame_idx, cond_frame_outputs, max_cond_frame_num)
         >>> print(selected)

ultralytics/models/sam/predict.py

@@ -69,8 +69,8 @@ class Predictor(BasePredictor):
 
     Examples:
         >>> predictor = Predictor()
-        >>> predictor.setup_model(model_path='sam_model.pt')
-        >>> predictor.set_image('image.jpg')
+        >>> predictor.setup_model(model_path="sam_model.pt")
+        >>> predictor.set_image("image.jpg")
         >>> masks, scores, boxes = predictor.generate()
         >>> results = predictor.postprocess((masks, scores, boxes), im, orig_img)
     """
@@ -90,8 +90,8 @@ class Predictor(BasePredictor):
 
         Examples:
             >>> predictor = Predictor(cfg=DEFAULT_CFG)
-            >>> predictor = Predictor(overrides={'imgsz': 640})
-            >>> predictor = Predictor(_callbacks={'on_predict_start': custom_callback})
+            >>> predictor = Predictor(overrides={"imgsz": 640})
+            >>> predictor = Predictor(_callbacks={"on_predict_start": custom_callback})
         """
         if overrides is None:
             overrides = {}
@@ -188,8 +188,8 @@ class Predictor(BasePredictor):
 
         Examples:
             >>> predictor = Predictor()
-            >>> predictor.setup_model(model_path='sam_model.pt')
-            >>> predictor.set_image('image.jpg')
+            >>> predictor.setup_model(model_path="sam_model.pt")
+            >>> predictor.set_image("image.jpg")
             >>> masks, scores, logits = predictor.inference(im, bboxes=[[0, 0, 100, 100]])
         """
         # Override prompts if any stored in self.prompts
@@ -475,8 +475,8 @@ class Predictor(BasePredictor):
 
         Examples:
             >>> predictor = Predictor()
-            >>> predictor.setup_source('path/to/images')
-            >>> predictor.setup_source('video.mp4')
+            >>> predictor.setup_source("path/to/images")
+            >>> predictor.setup_source("video.mp4")
             >>> predictor.setup_source(None)  # Uses default source if available
 
         Notes:
@@ -504,8 +504,8 @@ class Predictor(BasePredictor):
 
         Examples:
             >>> predictor = Predictor()
-            >>> predictor.set_image('path/to/image.jpg')
-            >>> predictor.set_image(cv2.imread('path/to/image.jpg'))
+            >>> predictor.set_image("path/to/image.jpg")
+            >>> predictor.set_image(cv2.imread("path/to/image.jpg"))
 
         Notes:
             - This method should be called before performing inference on a new image.

ultralytics/models/utils/loss.py

@@ -34,15 +34,19 @@ class DETRLoss(nn.Module):
         self, nc=80, loss_gain=None, aux_loss=True, use_fl=True, use_vfl=False, use_uni_match=False, uni_match_ind=0
     ):
         """
-        DETR loss function.
+        Initialize DETR loss function with customizable components and gains.
+
+        Uses default loss_gain if not provided. Initializes HungarianMatcher with
+        preset cost gains. Supports auxiliary losses and various loss types.
 
         Args:
-            nc (int): The number of classes.
-            loss_gain (dict): The coefficient of loss.
-            aux_loss (bool): If 'aux_loss = True', loss at each decoder layer are to be used.
-            use_vfl (bool): Use VarifocalLoss or not.
-            use_uni_match (bool): Whether to use a fixed layer to assign labels for auxiliary branch.
-            uni_match_ind (int): The fixed indices of a layer.
+            nc (int): Number of classes.
+            loss_gain (dict): Coefficients for different loss components.
+            aux_loss (bool): Use auxiliary losses from each decoder layer.
+            use_fl (bool): Use FocalLoss.
+            use_vfl (bool): Use VarifocalLoss.
+            use_uni_match (bool): Use fixed layer for auxiliary branch label assignment.
+            uni_match_ind (int): Index of fixed layer for uni_match.
         """
         super().__init__()
 
@@ -82,9 +86,7 @@ class DETRLoss(nn.Module):
         return {name_class: loss_cls.squeeze() * self.loss_gain["class"]}
 
     def _get_loss_bbox(self, pred_bboxes, gt_bboxes, postfix=""):
-        """Calculates and returns the bounding box loss and GIoU loss for the predicted and ground truth bounding
-        boxes.
-        """
+        """Computes bounding box and GIoU losses for predicted and ground truth bounding boxes."""
         # Boxes: [b, query, 4], gt_bbox: list[[n, 4]]
         name_bbox = f"loss_bbox{postfix}"
         name_giou = f"loss_giou{postfix}"
@@ -250,14 +252,24 @@ class DETRLoss(nn.Module):
 
     def forward(self, pred_bboxes, pred_scores, batch, postfix="", **kwargs):
         """
+        Calculate loss for predicted bounding boxes and scores.
+
         Args:
-            pred_bboxes (torch.Tensor): [l, b, query, 4]
-            pred_scores (torch.Tensor): [l, b, query, num_classes]
-            batch (dict): A dict includes:
-                gt_cls (torch.Tensor) with shape [num_gts, ],
-                gt_bboxes (torch.Tensor): [num_gts, 4],
-                gt_groups (List(int)): a list of batch size length includes the number of gts of each image.
-            postfix (str): postfix of loss name.
+            pred_bboxes (torch.Tensor): Predicted bounding boxes, shape [l, b, query, 4].
+            pred_scores (torch.Tensor): Predicted class scores, shape [l, b, query, num_classes].
+            batch (dict): Batch information containing:
+                cls (torch.Tensor): Ground truth classes, shape [num_gts].
+                bboxes (torch.Tensor): Ground truth bounding boxes, shape [num_gts, 4].
+                gt_groups (List[int]): Number of ground truths for each image in the batch.
+            postfix (str): Postfix for loss names.
+            **kwargs (Any): Additional arguments, may include 'match_indices'.
+
+        Returns:
+            (dict): Computed losses, including main and auxiliary (if enabled).
+
+        Note:
+            Uses last elements of pred_bboxes and pred_scores for main loss, and the rest for auxiliary losses if
+            self.aux_loss is True.
         """
         self.device = pred_bboxes.device
         match_indices = kwargs.get("match_indices", None)

ultralytics/models/utils/ops.py

@@ -32,9 +32,7 @@ class HungarianMatcher(nn.Module):
     """
 
     def __init__(self, cost_gain=None, use_fl=True, with_mask=False, num_sample_points=12544, alpha=0.25, gamma=2.0):
-        """Initializes HungarianMatcher with cost coefficients, Focal Loss, mask prediction, sample points, and alpha
-        gamma factors.
-        """
+        """Initializes a HungarianMatcher module for optimal assignment of predicted and ground truth bounding boxes."""
         super().__init__()
         if cost_gain is None:
             cost_gain = {"class": 1, "bbox": 5, "giou": 2, "mask": 1, "dice": 1}
@@ -70,7 +68,6 @@ class HungarianMatcher(nn.Module):
                 For each batch element, it holds:
                     len(index_i) = len(index_j) = min(num_queries, num_target_boxes)
         """
-
         bs, nq, nc = pred_scores.shape
 
         if sum(gt_groups) == 0:
@@ -175,7 +172,6 @@ def get_cdn_group(
             bounding boxes, attention mask and meta information for denoising. If not in training mode or 'num_dn'
             is less than or equal to 0, the function returns None for all elements in the tuple.
     """
-
     if (not training) or num_dn <= 0:
         return None, None, None, None
     gt_groups = batch["gt_groups"]

ultralytics/models/yolo/classify/predict.py

@@ -21,7 +21,7 @@ class ClassificationPredictor(BasePredictor):
         from ultralytics.utils import ASSETS
         from ultralytics.models.yolo.classify import ClassificationPredictor
 
-        args = dict(model='yolov8n-cls.pt', source=ASSETS)
+        args = dict(model="yolov8n-cls.pt", source=ASSETS)
         predictor = ClassificationPredictor(overrides=args)
         predictor.predict_cli()
         ```

ultralytics/models/yolo/classify/train.py

@@ -22,7 +22,7 @@ class ClassificationTrainer(BaseTrainer):
         ```python
         from ultralytics.models.yolo.classify import ClassificationTrainer
 
-        args = dict(model='yolov8n-cls.pt', data='imagenet10', epochs=3)
+        args = dict(model="yolov8n-cls.pt", data="imagenet10", epochs=3)
         trainer = ClassificationTrainer(overrides=args)
         trainer.train()
         ```

ultralytics/models/yolo/classify/val.py

@@ -20,7 +20,7 @@ class ClassificationValidator(BaseValidator):
         ```python
         from ultralytics.models.yolo.classify import ClassificationValidator
 
-        args = dict(model='yolov8n-cls.pt', data='imagenet10')
+        args = dict(model="yolov8n-cls.pt", data="imagenet10")
         validator = ClassificationValidator(args=args)
         validator()
         ```

ultralytics/models/yolo/detect/predict.py

@@ -14,7 +14,7 @@ class DetectionPredictor(BasePredictor):
         from ultralytics.utils import ASSETS
         from ultralytics.models.yolo.detect import DetectionPredictor
 
-        args = dict(model='yolov8n.pt', source=ASSETS)
+        args = dict(model="yolov8n.pt", source=ASSETS)
         predictor = DetectionPredictor(overrides=args)
         predictor.predict_cli()
         ```

ultralytics/models/yolo/detect/train.py

@@ -24,7 +24,7 @@ class DetectionTrainer(BaseTrainer):
         ```python
         from ultralytics.models.yolo.detect import DetectionTrainer
 
-        args = dict(model='yolov8n.pt', data='coco8.yaml', epochs=3)
+        args = dict(model="yolov8n.pt", data="coco8.yaml", epochs=3)
         trainer = DetectionTrainer(overrides=args)
         trainer.train()
         ```

ultralytics/models/yolo/detect/val.py

@@ -22,7 +22,7 @@ class DetectionValidator(BaseValidator):
         ```python
         from ultralytics.models.yolo.detect import DetectionValidator
 
-        args = dict(model='yolov8n.pt', data='coco8.yaml')
+        args = dict(model="yolov8n.pt", data="coco8.yaml")
         validator = DetectionValidator(args=args)
         validator()
         ```

ultralytics/models/yolo/model.py

@@ -64,10 +64,14 @@ class YOLOWorld(Model):
 
     def __init__(self, model="yolov8s-world.pt", verbose=False) -> None:
         """
-        Initializes the YOLOv8-World model with the given pre-trained model file. Supports *.pt and *.yaml formats.
+        Initialize YOLOv8-World model with a pre-trained model file.
+
+        Loads a YOLOv8-World model for object detection. If no custom class names are provided, it assigns default
+        COCO class names.
 
         Args:
-            model (str | Path): Path to the pre-trained model. Defaults to 'yolov8s-world.pt'.
+            model (str | Path): Path to the pre-trained model file. Supports *.pt and *.yaml formats.
+            verbose (bool): If True, prints additional information during initialization.
         """
         super().__init__(model=model, task="detect", verbose=verbose)
 

ultralytics/models/yolo/obb/predict.py

@@ -16,7 +16,7 @@ class OBBPredictor(DetectionPredictor):
         from ultralytics.utils import ASSETS
         from ultralytics.models.yolo.obb import OBBPredictor
 
-        args = dict(model='yolov8n-obb.pt', source=ASSETS)
+        args = dict(model="yolov8n-obb.pt", source=ASSETS)
         predictor = OBBPredictor(overrides=args)
         predictor.predict_cli()
         ```

ultralytics/models/yolo/obb/train.py

@@ -15,7 +15,7 @@ class OBBTrainer(yolo.detect.DetectionTrainer):
         ```python
         from ultralytics.models.yolo.obb import OBBTrainer
 
-        args = dict(model='yolov8n-obb.pt', data='dota8.yaml', epochs=3)
+        args = dict(model="yolov8n-obb.pt", data="dota8.yaml", epochs=3)
         trainer = OBBTrainer(overrides=args)
         trainer.train()
         ```

ultralytics/models/yolo/obb/val.py

@@ -18,9 +18,9 @@ class OBBValidator(DetectionValidator):
         ```python
         from ultralytics.models.yolo.obb import OBBValidator
 
-        args = dict(model='yolov8n-obb.pt', data='dota8.yaml')
+        args = dict(model="yolov8n-obb.pt", data="dota8.yaml")
         validator = OBBValidator(args=args)
-        validator(model=args['model'])
+        validator(model=args["model"])
         ```
     """
 

ultralytics/models/yolo/pose/predict.py

@@ -14,7 +14,7 @@ class PosePredictor(DetectionPredictor):
         from ultralytics.utils import ASSETS
         from ultralytics.models.yolo.pose import PosePredictor
 
-        args = dict(model='yolov8n-pose.pt', source=ASSETS)
+        args = dict(model="yolov8n-pose.pt", source=ASSETS)
         predictor = PosePredictor(overrides=args)
         predictor.predict_cli()
         ```

ultralytics/models/yolo/pose/train.py

@@ -16,7 +16,7 @@ class PoseTrainer(yolo.detect.DetectionTrainer):
         ```python
         from ultralytics.models.yolo.pose import PoseTrainer
 
-        args = dict(model='yolov8n-pose.pt', data='coco8-pose.yaml', epochs=3)
+        args = dict(model="yolov8n-pose.pt", data="coco8-pose.yaml", epochs=3)
         trainer = PoseTrainer(overrides=args)
         trainer.train()
         ```

ultralytics/models/yolo/pose/val.py

@@ -20,7 +20,7 @@ class PoseValidator(DetectionValidator):
         ```python
         from ultralytics.models.yolo.pose import PoseValidator
 
-        args = dict(model='yolov8n-pose.pt', data='coco8-pose.yaml')
+        args = dict(model="yolov8n-pose.pt", data="coco8-pose.yaml")
         validator = PoseValidator(args=args)
         validator()
         ```

ultralytics/models/yolo/segment/predict.py

@@ -14,7 +14,7 @@ class SegmentationPredictor(DetectionPredictor):
         from ultralytics.utils import ASSETS
         from ultralytics.models.yolo.segment import SegmentationPredictor
 
-        args = dict(model='yolov8n-seg.pt', source=ASSETS)
+        args = dict(model="yolov8n-seg.pt", source=ASSETS)
         predictor = SegmentationPredictor(overrides=args)
         predictor.predict_cli()
         ```

ultralytics/models/yolo/segment/train.py

@@ -16,7 +16,7 @@ class SegmentationTrainer(yolo.detect.DetectionTrainer):
         ```python
         from ultralytics.models.yolo.segment import SegmentationTrainer
 
-        args = dict(model='yolov8n-seg.pt', data='coco8-seg.yaml', epochs=3)
+        args = dict(model="yolov8n-seg.pt", data="coco8-seg.yaml", epochs=3)
         trainer = SegmentationTrainer(overrides=args)
         trainer.train()
         ```

ultralytics/models/yolo/segment/val.py

@@ -22,7 +22,7 @@ class SegmentationValidator(DetectionValidator):
         ```python
         from ultralytics.models.yolo.segment import SegmentationValidator
 
-        args = dict(model='yolov8n-seg.pt', data='coco8-seg.yaml')
+        args = dict(model="yolov8n-seg.pt", data="coco8-seg.yaml")
         validator = SegmentationValidator(args=args)
         validator()
         ```

ultralytics/models/yolo/world/train.py

@@ -29,7 +29,7 @@ class WorldTrainer(yolo.detect.DetectionTrainer):
         ```python
         from ultralytics.models.yolo.world import WorldModel
 
-        args = dict(model='yolov8s-world.pt', data='coco8.yaml', epochs=3)
+        args = dict(model="yolov8s-world.pt", data="coco8.yaml", epochs=3)
         trainer = WorldTrainer(overrides=args)
         trainer.train()
         ```

ultralytics/nn/autobackend.py

@@ -641,8 +641,8 @@ class AutoBackend(nn.Module):
     @staticmethod
     def _model_type(p="path/to/model.pt"):
         """
-        This function takes a path to a model file and returns the model type. Possibles types are pt, jit, onnx, xml,
-        engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, ncnn or paddle.
+        Takes a path to a model file and returns the model type. Possibles types are pt, jit, onnx, xml, engine, coreml,
+        saved_model, pb, tflite, edgetpu, tfjs, ncnn or paddle.
 
         Args:
             p: path to the model file. Defaults to path/to/model.pt

ultralytics/nn/modules/__init__.py

@@ -11,9 +11,9 @@ Example:
 
     x = torch.ones(1, 128, 40, 40)
     m = Conv(128, 128)
-    f = f'{m._get_name()}.onnx'
+    f = f"{m._get_name()}.onnx"
     torch.onnx.export(m, x, f)
-    os.system(f'onnxslim {f} {f} && open {f}')  # pip install onnxslim
+    os.system(f"onnxslim {f} {f} && open {f}")  # pip install onnxslim
     ```
 """
 

ultralytics/nn/modules/block.py

@@ -204,9 +204,7 @@ class C2(nn.Module):
     """CSP Bottleneck with 2 convolutions."""
 
     def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
-        """Initializes the CSP Bottleneck with 2 convolutions module with arguments ch_in, ch_out, number, shortcut,
-        groups, expansion.
-        """
+        """Initializes a CSP Bottleneck with 2 convolutions and optional shortcut connection."""
         super().__init__()
         self.c = int(c2 * e)  # hidden channels
         self.cv1 = Conv(c1, 2 * self.c, 1, 1)
@@ -224,9 +222,7 @@ class C2f(nn.Module):
     """Faster Implementation of CSP Bottleneck with 2 convolutions."""
 
     def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
-        """Initialize CSP bottleneck layer with two convolutions with arguments ch_in, ch_out, number, shortcut, groups,
-        expansion.
-        """
+        """Initializes a CSP bottleneck with 2 convolutions and n Bottleneck blocks for faster processing."""
         super().__init__()
         self.c = int(c2 * e)  # hidden channels
         self.cv1 = Conv(c1, 2 * self.c, 1, 1)
@@ -335,9 +331,7 @@ class Bottleneck(nn.Module):
     """Standard bottleneck."""
 
     def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
-        """Initializes a bottleneck module with given input/output channels, shortcut option, group, kernels, and
-        expansion.
-        """
+        """Initializes a standard bottleneck module with optional shortcut connection and configurable parameters."""
         super().__init__()
         c_ = int(c2 * e)  # hidden channels
         self.cv1 = Conv(c1, c_, k[0], 1)
@@ -345,7 +339,7 @@ class Bottleneck(nn.Module):
         self.add = shortcut and c1 == c2
 
     def forward(self, x):
-        """'forward()' applies the YOLO FPN to input data."""
+        """Applies the YOLO FPN to input data."""
         return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
 
 
@@ -449,9 +443,7 @@ class C2fAttn(nn.Module):
     """C2f module with an additional attn module."""
 
     def __init__(self, c1, c2, n=1, ec=128, nh=1, gc=512, shortcut=False, g=1, e=0.5):
-        """Initialize CSP bottleneck layer with two convolutions with arguments ch_in, ch_out, number, shortcut, groups,
-        expansion.
-        """
+        """Initializes C2f module with attention mechanism for enhanced feature extraction and processing."""
         super().__init__()
         self.c = int(c2 * e)  # hidden channels
         self.cv1 = Conv(c1, 2 * self.c, 1, 1)
@@ -521,9 +513,7 @@ class ImagePoolingAttn(nn.Module):
 
 
 class ContrastiveHead(nn.Module):
-    """Contrastive Head for YOLO-World compute the region-text scores according to the similarity between image and text
-    features.
-    """
+    """Implements contrastive learning head for region-text similarity in vision-language models."""
 
     def __init__(self):
         """Initializes ContrastiveHead with specified region-text similarity parameters."""
@@ -569,16 +559,14 @@ class RepBottleneck(Bottleneck):
     """Rep bottleneck."""
 
     def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
-        """Initializes a RepBottleneck module with customizable in/out channels, shortcut option, groups and expansion
-        ratio.
-        """
+        """Initializes a RepBottleneck module with customizable in/out channels, shortcuts, groups and expansion."""
         super().__init__(c1, c2, shortcut, g, k, e)
         c_ = int(c2 * e)  # hidden channels
         self.cv1 = RepConv(c1, c_, k[0], 1)
 
 
 class RepCSP(C3):
-    """Rep CSP Bottleneck with 3 convolutions."""
+    """Repeatable Cross Stage Partial Network (RepCSP) module for efficient feature extraction."""
 
     def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
         """Initializes RepCSP layer with given channels, repetitions, shortcut, groups and expansion ratio."""

ultralytics/nn/modules/conv.py

@@ -158,9 +158,7 @@ class GhostConv(nn.Module):
     """Ghost Convolution https://github.com/huawei-noah/ghostnet."""
 
     def __init__(self, c1, c2, k=1, s=1, g=1, act=True):
-        """Initializes the GhostConv object with input channels, output channels, kernel size, stride, groups and
-        activation.
-        """
+        """Initializes Ghost Convolution module with primary and cheap operations for efficient feature learning."""
         super().__init__()
         c_ = c2 // 2  # hidden channels
         self.cv1 = Conv(c1, c_, k, s, None, g, act=act)