源码级解读：YOLO26的新架构与创新设计

class SPPF(nn.Module):
    """Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher."""

    def __init__(self, c1: int, c2: int, k: int = 5, n: int = 3, shortcut: bool = False):
        """Initialize the SPPF layer with given input/output channels and kernel size.

        Args:
            c1 (int): Input channels.
            c2 (int): Output channels.
            k (int): Kernel size.
            n (int): Number of pooling iterations.
            shortcut (bool): Whether to use shortcut connection.

        Notes:
            This module is equivalent to SPP(k=(5, 9, 13)).
        """
        super().__init__()
        c_ = c1 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1, act=False)
        self.cv2 = Conv(c_ * (n + 1), c2, 1, 1)
        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
        self.n = n
        self.add = shortcut and c1 == c2

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        """Apply sequential pooling operations to input and return concatenated feature maps."""
        y = [self.cv1(x)]
        y.extend(self.m(y[-1]) for _ in range(getattr(self, "n", 3)))
        y = self.cv2(torch.cat(y, 1))
        return y + x if getattr(self, "add", False) else y

class SPPF(nn.Module):
    """Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher."""

    def __init__(self, c1, c2, k=5):
        """
        Initializes the SPPF layer with given input/output channels and kernel size.

        This module is equivalent to SPP(k=(5, 9, 13)).
        """
        super().__init__()
        c_ = c1 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_ * 4, c2, 1, 1)
        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)

    def forward(self, x):
        """Forward pass through Ghost Convolution block."""
        y = [self.cv1(x)]
        y.extend(self.m(y[-1]) for _ in range(3))
        return self.cv2(torch.cat(y, 1))

重复模块m (n次迭代):
┌─────────────────────────────────────────────────────────┐
│                                                         │
│  如果 attn=True:                                        │
│    Sequential(                                          │
│        Bottleneck(self.c, self.c),                     │  ←─ 先特征提取
│        PSABlock(self.c, attn_ratio=0.5, num_heads=...) │  ←─ 后注意力增强
│    )                                                    │
│                                                         │
│  否则如果 c3k=True:                                     │
│    C3k(self.c, self.c, 2)                             │  ←─ 同YOLOv11
│                                                         │
│  否则:                                                  │
│    Bottleneck(self.c, self.c)                         │  ←─ 同YOLOv11
│                                                         │
└─────────────────────────────────────────────────────────┘

YOLO26 C3k2代码：	
class C3k2(C2f):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""

    def __init__(
        self,
        c1: int,
        c2: int,
        n: int = 1,
        c3k: bool = False,
        e: float = 0.5,
        attn: bool = False,
        g: int = 1,
        shortcut: bool = True,
    ):
        """Initialize C3k2 module.

        Args:
            c1 (int): Input channels.
            c2 (int): Output channels.
            n (int): Number of blocks.
            c3k (bool): Whether to use C3k blocks.
            e (float): Expansion ratio.
            attn (bool): Whether to use attention blocks.
            g (int): Groups for convolutions.
            shortcut (bool): Whether to use shortcut connections.
        """
        super().__init__(c1, c2, n, shortcut, g, e)
        self.m = nn.ModuleList(
            nn.Sequential(
                Bottleneck(self.c, self.c, shortcut, g),
                PSABlock(self.c, attn_ratio=0.5, num_heads=max(self.c // 64, 1)),
            )
            if attn
            else C3k(self.c, self.c, 2, shortcut, g)
            if c3k
            else Bottleneck(self.c, self.c, shortcut, g)
            for _ in range(n)
        )

YOLO11 C3k2代码：		

class C3k2(C2f):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""

    def __init__(self, c1, c2, n=1, c3k=False, e=0.5, g=1, shortcut=True):
        """Initializes the C3k2 module, a faster CSP Bottleneck with 2 convolutions and optional C3k blocks."""
        super().__init__(c1, c2, n, shortcut, g, e)
        self.m = nn.ModuleList(
            C3k(self.c, self.c, 2, shortcut, g) if c3k else Bottleneck(self.c, self.c, shortcut, g) for _ in range(n)
        )

class BboxLoss(nn.Module):
    """Criterion class for computing training losses for bounding boxes."""

    def __init__(self, reg_max: int = 16):
        """Initialize the BboxLoss module with regularization maximum and DFL settings."""
        super().__init__()
        self.dfl_loss = DFLoss(reg_max) if reg_max > 1 else None

def non_max_suppression(
    prediction,
    conf_thres: float = 0.25,
    iou_thres: float = 0.45,
    classes=None,
    agnostic: bool = False,
    multi_label: bool = False,
    labels=(),
    max_det: int = 300,
    nc: int = 0,  # number of classes (optional)
    max_time_img: float = 0.05,
    max_nms: int = 30000,
    max_wh: int = 7680,
    rotated: bool = False,
    end2end: bool = False,
    return_idxs: bool = False,
):
    """Perform non-maximum suppression (NMS) on prediction results.

    Applies NMS to filter overlapping bounding boxes based on confidence and IoU thresholds. Supports multiple detection
    formats including standard boxes, rotated boxes, and masks.

    Args:
        prediction (torch.Tensor): Predictions with shape (batch_size, num_classes + 4 + num_masks, num_boxes)
            containing boxes, classes, and optional masks.
        conf_thres (float): Confidence threshold for filtering detections. Valid values are between 0.0 and 1.0.
        iou_thres (float): IoU threshold for NMS filtering. Valid values are between 0.0 and 1.0.
        classes (list[int], optional): List of class indices to consider. If None, all classes are considered.
        agnostic (bool): Whether to perform class-agnostic NMS.
        multi_label (bool): Whether each box can have multiple labels.
        labels (list[list[Union[int, float, torch.Tensor]]]): A priori labels for each image.
        max_det (int): Maximum number of detections to keep per image.
        nc (int): Number of classes. Indices after this are considered masks.
        max_time_img (float): Maximum time in seconds for processing one image.
        max_nms (int): Maximum number of boxes for NMS.
        max_wh (int): Maximum box width and height in pixels.
        rotated (bool): Whether to handle Oriented Bounding Boxes (OBB).
        end2end (bool): Whether the model is end-to-end and doesn't require NMS.
        return_idxs (bool): Whether to return the indices of kept detections.

    Returns:
        output (list[torch.Tensor]): List of detections per image with shape (num_boxes, 6 + num_masks) containing (x1,
            y1, x2, y2, confidence, class, mask1, mask2, ...).
        keepi (list[torch.Tensor]): Indices of kept detections if return_idxs=True.
    """

class MuSGD(optim.Optimizer):
    """Hybrid optimizer combining Muon and SGD updates for neural network training.

    This optimizer implements a combination of Muon (a momentum-based optimizer with orthogonalization via Newton-Schulz
    iterations) and standard SGD with momentum. It allows different parameter groups to use either the hybrid Muon+SGD
    approach or pure SGD.

    Args:
        param_groups (list): List of parameter groups with their optimization settings.
        muon (float, optional): Weight factor for Muon updates in hybrid mode. Default: 0.5.
        sgd (float, optional): Weight factor for SGD updates in hybrid mode. Default: 0.5.

    Attributes:
        muon (float): Scaling factor applied to Muon learning rate.
        sgd (float): Scaling factor applied to SGD learning rate in hybrid mode.

    Examples:
        >>> param_groups = [
        ...     {
        ...         "params": model.conv_params,
        ...         "lr": 0.02,
        ...         "use_muon": True,
        ...         "momentum": 0.95,
        ...         "nesterov": True,
        ...         "weight_decay": 0.01,
        ...     },
        ...     {
        ...         "params": model.other_params,
        ...         "lr": 0.01,
        ...         "use_muon": False,
        ...         "momentum": 0.9,
        ...         "nesterov": False,
        ...         "weight_decay": 0,
        ...     },
        ... ]
        >>> optimizer = MuSGD(param_groups, muon=0.5, sgd=0.5)
        >>> loss = model(data)
        >>> loss.backward()
        >>> optimizer.step()

    Notes:
        - Parameter groups with 'use_muon': True will receive both Muon and SGD updates.
        - Parameter groups with 'use_muon': False will receive only SGD updates.
        - The Muon update uses orthogonalization which works best for 2D+ parameter tensors.
    """

    def __init__(
        self,
        params,
        lr: float = 1e-3,
        momentum: float = 0.0,
        weight_decay: float = 0.0,
        nesterov: bool = False,
        use_muon: bool = False,
        muon: float = 0.5,
        sgd: float = 0.5,
    ):
        """Initialize MuSGD optimizer with hybrid Muon and SGD capabilities.

        Args:
            params: Iterable of parameters to optimize or dicts defining parameter groups.
            lr (float): Learning rate.
            momentum (float): Momentum factor for SGD.
            weight_decay (float): Weight decay (L2 penalty).
            nesterov (bool): Whether to use Nesterov momentum.
            use_muon (bool): Whether to enable Muon updates.
            muon (float): Scaling factor for Muon component.
            sgd (float): Scaling factor for SGD component.
        """
        defaults = dict(
            lr=lr,
            momentum=momentum,
            weight_decay=weight_decay,
            nesterov=nesterov,
            use_muon=use_muon,
        )
        super().__init__(params, defaults)
        self.muon = muon
        self.sgd = sgd

    @torch.no_grad()
    def step(self, closure=None):
        """Perform a single optimization step.

        Applies either hybrid Muon+SGD updates or pure SGD updates depending on the
        'use_muon' flag in each parameter group. For Muon-enabled groups, parameters
        receive both an orthogonalized Muon update and a standard SGD momentum update.

        Args:
            closure (Callable, optional): A closure that reevaluates the model
                and returns the loss. Default: None.

        Returns:
            (torch.Tensor | None): The loss value if closure is provided, otherwise None.

        Notes:
            - Parameters with None gradients are assigned zero gradients for synchronization.
            - Muon updates use Newton-Schulz orthogonalization and work best on 2D+ tensors.
            - Weight decay is applied only to the SGD component in hybrid mode.
        """
        loss = None
        if closure is not None:
            with torch.enable_grad():
                loss = closure()

        for group in self.param_groups:
            # Muon
            if group["use_muon"]:
                # generate weight updates in distributed fashion
                for p in group["params"]:
                    lr = group["lr"]
                    if p.grad is None:
                        continue
                    grad = p.grad
                    state = self.state[p]
                    if len(state) == 0:
                        state["momentum_buffer"] = torch.zeros_like(p)
                        state["momentum_buffer_SGD"] = torch.zeros_like(p)

                    update = muon_update(
                        grad, state["momentum_buffer"], beta=group["momentum"], nesterov=group["nesterov"]
                    )
                    p.add_(update.reshape(p.shape), alpha=-(lr * self.muon))

                    # SGD update
                    if group["weight_decay"] != 0:
                        grad = grad.add(p, alpha=group["weight_decay"])
                    state["momentum_buffer_SGD"].mul_(group["momentum"]).add_(grad)
                    sgd_update = (
                        grad.add(state["momentum_buffer_SGD"], alpha=group["momentum"])
                        if group["nesterov"]
                        else state["momentum_buffer_SGD"]
                    )
                    p.add_(sgd_update, alpha=-(lr * self.sgd))
            else:  # SGD
                for p in group["params"]:
                    lr = group["lr"]
                    if p.grad is None:
                        continue
                    grad = p.grad
                    if group["weight_decay"] != 0:
                        grad = grad.add(p, alpha=group["weight_decay"])
                    state = self.state[p]
                    if len(state) == 0:
                        state["momentum_buffer"] = torch.zeros_like(p)
                    state["momentum_buffer"].mul_(group["momentum"]).add_(grad)
                    update = (
                        grad.add(state["momentum_buffer"], alpha=group["momentum"])
                        if group["nesterov"]
                        else state["momentum_buffer"]
                    )
                    p.add_(update, alpha=-lr)
        return loss