ultralytics 8.2.80__py3-none-any.whl → 8.2.82__py3-none-any.whl

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)

ultralytics/nn/modules/head.py

@@ -8,7 +8,6 @@ import torch
 import torch.nn as nn
 from torch.nn.init import constant_, xavier_uniform_
 
-from ultralytics.utils import MACOS
 from ultralytics.utils.tal import TORCH_1_10, dist2bbox, dist2rbox, make_anchors
 
 from .block import DFL, BNContrastiveHead, ContrastiveHead, Proto
@@ -133,38 +132,26 @@ class Detect(nn.Module):
     @staticmethod
     def postprocess(preds: torch.Tensor, max_det: int, nc: int = 80):
         """
-        Post-processes the predictions obtained from a YOLOv10 model.
+        Post-processes YOLO model predictions.
 
         Args:
-            preds (torch.Tensor): The predictions obtained from the model. It should have a shape of (batch_size, num_boxes, 4 + num_classes).
-            max_det (int): The maximum number of detections to keep.
-            nc (int, optional): The number of classes. Defaults to 80.
+            preds (torch.Tensor): Raw predictions with shape (batch_size, num_anchors, 4 + nc) with last dimension
+                format [x, y, w, h, class_probs].
+            max_det (int): Maximum detections per image.
+            nc (int, optional): Number of classes. Default: 80.
 
         Returns:
-            (torch.Tensor): The post-processed predictions with shape (batch_size, max_det, 6),
-                including bounding boxes, scores and cls.
+            (torch.Tensor): Processed predictions with shape (batch_size, min(max_det, num_anchors), 6) and last
+                dimension format [x, y, w, h, max_class_prob, class_index].
         """
-        assert 4 + nc == preds.shape[-1]
+        batch_size, anchors, predictions = preds.shape  # i.e. shape(16,8400,84)
         boxes, scores = preds.split([4, nc], dim=-1)
-        max_scores = scores.amax(dim=-1)
-        max_scores, index = torch.topk(max_scores, min(max_det, max_scores.shape[1]), axis=-1)
-        index = index.unsqueeze(-1)
-        boxes = torch.gather(boxes, dim=1, index=index.repeat(1, 1, boxes.shape[-1]))
-        scores = torch.gather(scores, dim=1, index=index.repeat(1, 1, scores.shape[-1]))
-
-        # NOTE: simplify result but slightly lower mAP
-        # scores, labels = scores.max(dim=-1)
-        # return torch.cat([boxes, scores.unsqueeze(-1), labels.unsqueeze(-1)], dim=-1)
-
-        scores, index = torch.topk(scores.flatten(1), max_det, axis=-1)
-        labels = index % nc
-        index = index // nc
-        # Set int64 dtype for MPS and CoreML compatibility to avoid 'gather_along_axis' ops error
-        if MACOS:
-            index = index.to(torch.int64)
-        boxes = boxes.gather(dim=1, index=index.unsqueeze(-1).repeat(1, 1, boxes.shape[-1]))
-
-        return torch.cat([boxes, scores.unsqueeze(-1), labels.unsqueeze(-1).to(boxes.dtype)], dim=-1)
+        index = scores.amax(dim=-1).topk(min(max_det, anchors))[1].unsqueeze(-1)
+        boxes = boxes.gather(dim=1, index=index.repeat(1, 1, 4))
+        scores = scores.gather(dim=1, index=index.repeat(1, 1, nc))
+        scores, index = scores.flatten(1).topk(max_det)
+        i = torch.arange(batch_size)[..., None]  # batch indices
+        return torch.cat([boxes[i, index // nc], scores[..., None], (index % nc)[..., None].float()], dim=-1)
 
 
 class Segment(Detect):
@@ -266,9 +253,7 @@ class Classify(nn.Module):
     """YOLOv8 classification head, i.e. x(b,c1,20,20) to x(b,c2)."""
 
     def __init__(self, c1, c2, k=1, s=1, p=None, g=1):
-        """Initializes YOLOv8 classification head with specified input and output channels, kernel size, stride,
-        padding, and groups.
-        """
+        """Initializes YOLOv8 classification head to transform input tensor from (b,c1,20,20) to (b,c2) shape."""
         super().__init__()
         c_ = 1280  # efficientnet_b0 size
         self.conv = Conv(c1, c_, k, s, p, g)
@@ -571,7 +556,7 @@ class RTDETRDecoder(nn.Module):
 
 class v10Detect(Detect):
     """
-    v10 Detection head from https://arxiv.org/pdf/2405.14458
+    v10 Detection head from https://arxiv.org/pdf/2405.14458.
 
     Args:
         nc (int): Number of classes.

ultralytics/nn/modules/transformer.py

@@ -352,7 +352,6 @@ class DeformableTransformerDecoderLayer(nn.Module):
 
     def forward(self, embed, refer_bbox, feats, shapes, padding_mask=None, attn_mask=None, query_pos=None):
         """Perform the forward pass through the entire decoder layer."""
-
         # Self attention
         q = k = self.with_pos_embed(embed, query_pos)
         tgt = self.self_attn(q.transpose(0, 1), k.transpose(0, 1), embed.transpose(0, 1), attn_mask=attn_mask)[

ultralytics/nn/modules/utils.py

@@ -50,7 +50,6 @@ def multi_scale_deformable_attn_pytorch(
 
     https://github.com/IDEA-Research/detrex/blob/main/detrex/layers/multi_scale_deform_attn.py
     """
-
     bs, _, num_heads, embed_dims = value.shape
     _, num_queries, num_heads, num_levels, num_points, _ = sampling_locations.shape
     value_list = value.split([H_ * W_ for H_, W_ in value_spatial_shapes], dim=1)

ultralytics/nn/tasks.py

@@ -89,13 +89,17 @@ class BaseModel(nn.Module):
 
     def forward(self, x, *args, **kwargs):
         """
-        Forward pass of the model on a single scale. Wrapper for `_forward_once` method.
+        Perform forward pass of the model for either training or inference.
+
+        If x is a dict, calculates and returns the loss for training. Otherwise, returns predictions for inference.
 
         Args:
-            x (torch.Tensor | dict): The input image tensor or a dict including image tensor and gt labels.
+            x (torch.Tensor | dict): Input tensor for inference, or dict with image tensor and labels for training.
+            *args (Any): Variable length argument list.
+            **kwargs (Any): Arbitrary keyword arguments.
 
         Returns:
-            (torch.Tensor): The output of the network.
+            (torch.Tensor): Loss if x is a dict (training), or network predictions (inference).
         """
         if isinstance(x, dict):  # for cases of training and validating while training.
             return self.loss(x, *args, **kwargs)
@@ -713,7 +717,7 @@ def temporary_modules(modules=None, attributes=None):
 
     Example:
         ```python
-        with temporary_modules({'old.module': 'new.module'}, {'old.module.attribute': 'new.module.attribute'}):
+        with temporary_modules({"old.module": "new.module"}, {"old.module.attribute": "new.module.attribute"}):
             import old.module  # this will now import new.module
             from old.module import attribute  # this will now import new.module.attribute
         ```
@@ -723,7 +727,6 @@ def temporary_modules(modules=None, attributes=None):
         Be aware that directly manipulating `sys.modules` can lead to unpredictable results, especially in larger
         applications or libraries. Use this function with caution.
     """
-
     if modules is None:
         modules = {}
     if attributes is None:
@@ -752,9 +755,9 @@ def temporary_modules(modules=None, attributes=None):
 
 def torch_safe_load(weight):
     """
-    This function attempts to load a PyTorch model with the torch.load() function. If a ModuleNotFoundError is raised,
-    it catches the error, logs a warning message, and attempts to install the missing module via the
-    check_requirements() function. After installation, the function again attempts to load the model using torch.load().
+    Attempts to load a PyTorch model with the torch.load() function. If a ModuleNotFoundError is raised, it catches the
+    error, logs a warning message, and attempts to install the missing module via the check_requirements() function.
+    After installation, the function again attempts to load the model using torch.load().
 
     Args:
         weight (str): The file path of the PyTorch model.
@@ -813,7 +816,6 @@ def torch_safe_load(weight):
 
 def attempt_load_weights(weights, device=None, inplace=True, fuse=False):
     """Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a."""
-
     ensemble = Ensemble()
     for w in weights if isinstance(weights, list) else [weights]:
         ckpt, w = torch_safe_load(w)  # load ckpt

ultralytics/solutions/__init__.py

@@ -20,4 +20,5 @@ __all__ = (
     "QueueManager",
     "SpeedEstimator",
     "Analytics",
+    "inference",
 )

ultralytics/solutions/ai_gym.py

@@ -29,7 +29,6 @@ class AIGym:
             pose_down_angle (float, optional): Angle threshold for the 'down' pose. Defaults to 90.0.
             pose_type (str, optional): Type of pose to detect ('pullup', 'pushup', 'abworkout'). Defaults to "pullup".
         """
-
         # Image and line thickness
         self.im0 = None
         self.tf = line_thickness
@@ -65,7 +64,6 @@ class AIGym:
             im0 (ndarray): Current frame from the video stream.
             results (list): Pose estimation data.
         """
-
         self.im0 = im0
 
         if not len(results[0]):

ultralytics/solutions/analytics.py

@@ -51,7 +51,6 @@ class Analytics:
             save_img (bool): Whether to save the image.
             max_points (int): Specifies when to remove the oldest points in a graph for multiple lines.
         """
-
         self.bg_color = bg_color
         self.fg_color = fg_color
         self.view_img = view_img
@@ -115,7 +114,6 @@ class Analytics:
             frame_number (int): The current frame number.
             counts_dict (dict): Dictionary with class names as keys and counts as values.
         """
-
         x_data = np.array([])
         y_data_dict = {key: np.array([]) for key in counts_dict.keys()}
 
@@ -177,7 +175,6 @@ class Analytics:
             frame_number (int): The current frame number.
             total_counts (int): The total counts to plot.
         """
-
         # Update line graph data
         x_data = self.line.get_xdata()
         y_data = self.line.get_ydata()
@@ -230,7 +227,7 @@ class Analytics:
         """
         Write and display the line graph
         Args:
-            im0 (ndarray): Image for processing
+            im0 (ndarray): Image for processing.
         """
         im0 = cv2.cvtColor(im0[:, :, :3], cv2.COLOR_RGBA2BGR)
         cv2.imshow(self.title, im0) if self.view_img else None
@@ -243,7 +240,6 @@ class Analytics:
         Args:
             count_dict (dict): Dictionary containing the count data to plot.
         """
-
         # Update bar graph data
         self.ax.clear()
         self.ax.set_facecolor(self.bg_color)
@@ -282,7 +278,6 @@ class Analytics:
         Args:
             classes_dict (dict): Dictionary containing the class data to plot.
         """
-
         # Update pie chart data
         labels = list(classes_dict.keys())
         sizes = list(classes_dict.values())