How to set parameters for Conv

Question

I am modifying YOLOV5 into a rotating object detection network and replacing its head part with a decoupled head. I successfully replaced the head of the origin YOLOV5 with a decoupled head, but when I tried to replace it for my modified YOLOV5, it reported an error :RuntimeError: Given groups=1, weight of size [256, 128, 1, 1], expected input[1, 63, 32, 32] to have 128 channels, but got 63 channels instead. The only part I changed in the head of YOLOV5 is that I turned self.no = nc + 5 into self.no = nc + 5 + 180, to adapt to rotating target detection scenarios.

This is the modification I made for the decoupled head

class DecoupledHead(nn.Module):
    def __init__(self, ch=256, nc=80, width=1.0, anchors=()):
        super().__init__()
        self.nc = nc  # number of classes
        self.nl = len(anchors)  # number of detection layers
        self.na = len(anchors[0]) // 2  # number of anchors
        self.merge = Conv(ch, 256 * width, 1, 1)
        self.cls_convs1 = Conv(256 * width, 256 * width, 3, 1, 1)
        self.cls_convs2 = Conv(256 * width, 256 * width, 3, 1, 1)
        self.reg_convs1 = Conv(256 * width, 256 * width, 3, 1, 1)
        self.reg_convs2 = Conv(256 * width, 256 * width, 3, 1, 1)
        self.cls_preds = nn.Conv2d(256 * width, self.nc * self.na, 1)
        self.reg_preds = nn.Conv2d(256 * width, 4 * self.na, 1)
        self.obj_preds = nn.Conv2d(256 * width, 1 * self.na, 1)

    def forward(self, x):
        x = self.merge(x)
        x1 = self.cls_convs1(x)
        x1 = self.cls_convs2(x1)
        x1 = self.cls_preds(x1)
        x2 = self.reg_convs1(x)
        x2 = self.reg_convs2(x2)
        x21 = self.reg_preds(x2)
        x22 = self.obj_preds(x2)
        out = torch.cat([x21, x22, x1], 1)
        return out

and I changed __init__ in class Detect with

    def __init__(self, nc=80, anchors=(), ch=(), inplace=True):  # detection layer
        super().__init__()
        self.n_anchors = 1
        self.nc = nc  # number of classes
        self.no = nc + 5 + 180  # number of outputs per anchor
        self.nl = len(anchors)  # number of detection layers
        self.na = len(anchors[0]) // 2  # number of anchors
        self.grid = [torch.zeros(1)] * self.nl  # init grid
        self.anchor_grid = [torch.zeros(1)] * self.nl  # init anchor grid
        self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2))  # shape(nl,na,2)
        # self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
        self.m = nn.ModuleList(DecoupledHead(x, nc, 1, anchors) for x in ch)

        self.inplace = inplace  # use in-place ops (e.g. slice assignment)

The origin __init__ was like

    def __init__(self, nc=80, anchors=(), ch=(), inplace=True):  # detection layer
        super().__init__()
        self.n_anchors = 1
        self.nc = nc  # number of classes
        self.no = nc + 5  # number of outputs per anchor
        self.nl = len(anchors)  # number of detection layers
        self.na = len(anchors[0]) // 2  # number of anchors
        self.grid = [torch.zeros(1)] * self.nl  # init grid
        self.anchor_grid = [torch.zeros(1)] * self.nl  # init anchor grid
        self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2))  # shape(nl,na,2)
        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv


        self.inplace = inplace  # use in-place ops (e.g. slice assignment)

How to modify the class DecoupledHead to make it work?