# 结合BiFPN 设置可学习参数 学习不同分支的权重
# 两个分支concat操作
class BiFPN_Concat2(nn.Module):
    def __init__(self, dimension=1):
        super(BiFPN_Concat2, self).__init__()
        self.d = dimension
        self.w = nn.Parameter(torch.ones(2, dtype=torch.float32), requires_grad=True)
        self.epsilon = 0.0001
        # 设置可学习参数 nn.Parameter的作用是：将一个不可训练的类型Tensor转换成可以训练的类型 
        parameter
        # 并且会向宿主模型注册该参数 成为其一部分 即model.parameters()会包含这个parameter
        # 从而在参数优化的时候可以自动一起优化

    def forward(self, x):
        w = self.w
        weight = w / (torch.sum(w, dim=0) + self.epsilon)  # 将权重进行归一化
        # Fast normalized fusion
        x = [weight[0] * x[0], weight[1] * x[1]]
        return torch.cat(x, self.d)


# 三个分支concat操作
class BiFPN_Concat3(nn.Module):
    def __init__(self, dimension=1):
        super(BiFPN_Concat3, self).__init__()
        self.d = dimension
        self.w = nn.Parameter(torch.ones(3, dtype=torch.float32), requires_grad=True)
        self.epsilon = 0.0001

    def forward(self, x):
        w = self.w
        weight = w / (torch.sum(w, dim=0) + self.epsilon)  # 将权重进行归一化
        # Fast normalized fusion
        x = [weight[0] * x[0], weight[1] * x[1], weight[2] * x[2]]
        return torch.cat(x, self.d)

# 添加bifpn_concat结构
elif m in [Concat, BiFPN_Concat2, BiFPN_Concat3]:
    c2 = sum(ch[x] for x in f)

from models.common import BiFPN_Concat2, BiFPN_Concat3

 pg0, pg1, pg2 = [], [], []  # optimizer parameter groups
    for k, v in model.named_modules():
        # hasattr: 测试指定的对象是否具有给定的属性，返回一个布尔值
        if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter):
            pg2.append(v.bias)  # biases
        if isinstance(v, nn.BatchNorm2d):
            pg0.append(v.weight)  # no decay
        elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter):
            pg1.append(v.weight)  # apply decay

        elif isinstance(v, BiFPN_Concat2) and hasattr(v, 'w') and isinstance(v.w, nn.Parameter):
            pg1.append(v.w)
        elif isinstance(v, BiFPN_Concat3) and hasattr(v, 'w') and isinstance(v.w, nn.Parameter):
            pg1.append(v.w)


    if opt.adam:
        optimizer = optim.Adam(pg0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999))  # adjust beta1 to momentum
    else:
        optimizer = optim.SGD(pg0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)

    optimizer.add_param_group({'params': pg1, 'weight_decay': hyp['weight_decay']})  # add pg1 with weight_decay
    optimizer.add_param_group({'params': pg2})  # add pg2 (biases)
    logger.info('Optimizer groups: %g .bias, %g conv.weight, %g other' % (len(pg2), len(pg1), len(pg0)))
    del pg0, pg1, pg2

# parameters
nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple

# anchors
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# YOLOv5 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 9, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 1, SPP, [1024, [5, 9, 13]]],
   [-1, 3, C3, [1024, False]],  # 9
  ]

# YOLOv5 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, BiFPN_Concat2, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, BiFPN_Concat2, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14,6], 1,BiFPN_Concat3, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, BiFPN_Concat2, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]