# BiFPN 
# 兩個特征圖add操作
class BiFPN_Add2(nn.Module):
    def __init__(self, c1, c2):
        super(BiFPN_Add2, self).__init__()
        # 設(shè)置可學(xué)習(xí)參數(shù) nn.Parameter的作用是：將一個不可訓(xùn)練的類型Tensor轉(zhuǎn)換成可以訓(xùn)練的類型parameter
        # 并且會向宿主模型注冊該參數(shù) 成為其一部分 即model.parameters()會包含這個parameter
        # 從而在參數(shù)優(yōu)化的時候可以自動一起優(yōu)化
        self.w = nn.Parameter(torch.ones(2, dtype=torch.float32), requires_grad=True)
        self.epsilon = 0.0001
        self.conv = nn.Conv2d(c1, c2, kernel_size=1, stride=1, padding=0)
        self.silu = nn.SiLU()

    def forward(self, x):
        w = self.w
        weight = w / (torch.sum(w, dim=0) + self.epsilon)
        return self.conv(self.silu(weight[0] * x[0] + weight[1] * x[1]))


# 三個特征圖add操作
class BiFPN_Add3(nn.Module):
    def __init__(self, c1, c2):
        super(BiFPN_Add3, self).__init__()
        self.w = nn.Parameter(torch.ones(3, dtype=torch.float32), requires_grad=True)
        self.epsilon = 0.0001
        self.conv = nn.Conv2d(c1, c2, kernel_size=1, stride=1, padding=0)
        self.silu = nn.SiLU()

    def forward(self, x):
        w = self.w
        weight = w / (torch.sum(w, dim=0) + self.epsilon)  
        # Fast normalized fusion
        return self.conv(self.silu(weight[0] * x[0] + weight[1] * x[1] + weight[2] * x[2]))

elif m is Concat:
    c2 = sum(ch[x] for x in f)
# 添加bifpn_add結(jié)構(gòu)
elif m in [BiFPN_Add2, BiFPN_Add3]:
    c2 = max([ch[x] for x in f])

g = [], [], []  # optimizer parameter groups
    bn = tuple(v for k, v in nn.__dict__.items() if 'Norm' in k)  # normalization layers, i.e. BatchNorm2d()
    for v in model.modules():
        # hasattr: 測試指定的對象是否具有給定的屬性，返回一個布爾值
        if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter):  # bias
            g[2].append(v.bias)
        if isinstance(v, bn):  # weight (no decay)
            g[1].append(v.weight)
        elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter):  # weight (with decay)
            g[0].append(v.weight)
        # BiFPN_Concat
        elif isinstance(v, BiFPN_Add2) and hasattr(v, 'w') and isinstance(v.w, nn.Parameter):
            g[1].append(v.w)
        elif isinstance(v, BiFPN_Add3) and hasattr(v, 'w') and isinstance(v.w, nn.Parameter):
            g[1].append(v.w)

from models.common import BiFPN_Add3, BiFPN_Add2