解决Ultralytics-YOLOv8-seg 由pt文件导出onnx后精度损失

前言：使用Ultralytics 8.1.34中yolov8n-seg进行训练，并到处onnx模型后，onnx模型精度对比pt文件有明显损失，具体表现为检测到的分割区域会出现缺少情况。如下图所示：

pt文件推理正常分割图片

onnx模型推理分割图片

产生该问题原因(参考注释)：

class Detect(nn.Module):
    """YOLOv8 Detect head for detection models."""

    dynamic = False  # force grid reconstruction
    export = False  # export mode
    shape = None
    anchors = torch.empty(0)  # init
    strides = torch.empty(0)  # init

    def __init__(self, nc=80, ch=()):
        """Initializes the YOLOv8 detection layer with specified number of classes and channels."""
        super().__init__()
        self.nc = nc  # number of classes
        self.nl = len(ch)  # number of detection layers
        self.reg_max = 16  # DFL channels (ch[0] // 16 to scale 4/8/12/16/20 for n/s/m/l/x)
        self.no = nc + self.reg_max * 4  # number of outputs per anchor
        self.stride = torch.zeros(self.nl)  # strides computed during build
        c2, c3 = max((16, ch[0] // 4, self.reg_max * 4)), max(ch[0], min(self.nc, 100))  # channels
        self.cv2 = nn.ModuleList(
            nn.Sequential(Conv(x, c2, 3), Conv(c2, c2, 3), nn.Conv2d(c2, 4 * self.reg_max, 1)) for x in ch
        )
        self.cv3 = nn.ModuleList(nn.Sequential(Conv(x, c3, 3), Conv(c3, c3, 3), nn.Conv2d(c3, self.nc, 1)) for x in ch)
        self.dfl = DFL(self.reg_max) if self.reg_max > 1 else nn.Identity()
    ......

    def decode_bboxes(self, bboxes, anchors):
        """Decode bounding boxes."""
        if self.export:
            return dist2bbox(bboxes, anchors, xywh=False, dim=1)   # 导出onnx时xywh入参为False
        return dist2bbox(bboxes, anchors, xywh=True, dim=1) # pt训练推理时xywh入参为True
        
def dist2bbox(distance, anchor_points, xywh=True, dim=-1):
    """Transform distance(ltrb) to box(xywh or xyxy)."""
    assert(distance.shape[dim] == 4)
    lt, rb = distance.split([2, 2], dim)
    x1y1 = anchor_points - lt
    x2y2 = anchor_points + rb
    if xywh: # pt训练推理时的代码实现
        c_xy = (x1y1 + x2y2) / 2
        wh = x2y2 - x1y1
        return torch.cat((c_xy, wh), dim)  # xywh bbox
    return torch.cat((x1y1, x2y2), dim)  # 导出onnx时代码实现

xywh的入参不同导致模型结构出现不同，需要将入参部分全部置为True即可。