Yolov9的DualDDetect层

Yolov9中DualDDetect是两个DDetect的级联，而DDetect则是一个完全解耦的检测模块。

train_dual: one aux branch + one main branch.

triple_branch: two aux branches + one main branch

Provide these codes to show how to extend aux branches for training. Everyone could follow the rule to make related researches. For example, we also extend train_multiple to implement training strategy which is similar to Co-DETR.

class DualDDetect(nn.Module):
    # YOLO 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=(), inplace=True):  # detection layer
        super().__init__()
        self.nc = nc  # number of classes
        self.nl = len(ch) // 2  # number of detection layers
        self.reg_max = 16
        self.no