class UniRepLKNetBlock(nn.Module):

    def __init__(self,
                 dim,
                 kernel_size,
                 drop_path=0.,
                 layer_scale_init_value=1e-6,
                 deploy=False,
                 attempt_use_lk_impl=True,
                 with_cp=False,
                 use_sync_bn=False,
                 ffn_factor=4):
        super().__init__()
        self.with_cp = with_cp
        # if deploy:
        #     print('------------------------------- Note: deploy mode')
        # if self.with_cp:
        #     print('****** note with_cp = True, reduce memory consumption but may slow down training ******')

        self.need_contiguous = (not deploy) or kernel_size >= 7

        if kernel_size == 0:
            self.dwconv = nn.Identity()
            self.norm = nn.Identity()
        elif deploy:
            self.dwconv = get_conv2d(dim, dim, kernel_size=kernel_size, stride=1, padding=kernel_size // 2,
                                     dilation=1, groups=dim, bias=True,
                                     attempt_use_lk_impl=attempt_use_lk_impl)
            self.norm = nn.Identity()
        elif kernel_size >= 7:
            self.dwconv = DilatedReparamBlock(dim, kernel_size, deploy=deploy,
                                              use_sync_bn=use_sync_bn,
                                              attempt_use_lk_impl=attempt_use_lk_impl)
            self.norm = get_bn(dim, use_sync_bn=use_sync_bn)
        elif kernel_size == 1:
            self.dwconv = nn.Conv2d(dim, dim, kernel_size=kernel_size, stride=1, padding=kernel_size // 2,
                                    dilation=1, groups=1, bias=deploy)
            self.norm = get_bn(dim, use_sync_bn=use_sync_bn)
        else:
            assert kernel_size in [3, 5]
            self.dwconv = nn.Conv2d(dim, dim, kernel_size=kernel_size, stride=1, padding=kernel_size // 2,
                                    dilation=1, groups=dim, bias=deploy)
            self.norm = get_bn(dim, use_sync_bn=use_sync_bn)

        self.se = SEBlock(dim, dim // 4)

        ffn_dim = int(ffn_factor * dim)
        self.pwconv1 = nn.Sequential(
            NCHWtoNHWC(),
            nn.Linear(dim, ffn_dim))
        self.act = nn.Sequential(
            nn.GELU(),
            GRNwithNHWC(ffn_dim, use_bias=not deploy))
        if deploy:
            self.pwconv2 = nn.Sequential(
                nn.Linear(ffn_dim, dim),
                NHWCtoNCHW())
        else:
            self.pwconv2 = nn.Sequential(
                nn.Linear(ffn_dim, dim, bias=False),
                NHWCtoNCHW(),
                get_bn(dim, use_sync_bn=use_sync_bn))

        self.gamma = nn.Parameter(layer_scale_init_value * torch.ones(dim),
                                  requires_grad=True) if (not deploy) and layer_scale_init_value is not None \
                                                         and layer_scale_init_value > 0 else None
        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()

    def forward(self, inputs):

        def _f(x):
            if self.need_contiguous:
                x = x.contiguous()
            y = self.se(self.norm(self.dwconv(x)))
            y = self.pwconv2(self.act(self.pwconv1(y)))
            if self.gamma is not None:
                y = self.gamma.view(1, -1, 1, 1) * y
            return self.drop_path(y) + x

        if self.with_cp and inputs.requires_grad:
            return checkpoint.checkpoint(_f, inputs)
        else:
            return _f(inputs)

    def reparameterize(self):
        if hasattr(self.dwconv, 'merge_dilated_branches'):
            self.dwconv.merge_dilated_branches()
        if hasattr(self.norm, 'running_var') and hasattr(self.dwconv, 'lk_origin'):
            std = (self.norm.running_var + self.norm.eps).sqrt()
            self.dwconv.lk_origin.weight.data *= (self.norm.weight / std).view(-1, 1, 1, 1)
            self.dwconv.lk_origin.bias.data = self.norm.bias + (self.dwconv.lk_origin.bias - self.norm.running_mean) * self.norm.weight / std
            self.norm = nn.Identity()
        if self.gamma is not None:
            final_scale = self.gamma.data
            self.gamma = None
        else:
            final_scale = 1
        if self.act[1].use_bias and len(self.pwconv2) == 3:
            grn_bias = self.act[1].beta.data
            self.act[1].__delattr__('beta')
            self.act[1].use_bias = False
            linear = self.pwconv2[0]
            grn_bias_projected_bias = (linear.weight.data @ grn_bias.view(-1, 1)).squeeze()
            bn = self.pwconv2[2]
            std = (bn.running_var + bn.eps).sqrt()
            new_linear = nn.Linear(linear.in_features, linear.out_features, bias=True)
            new_linear.weight.data = linear.weight * (bn.weight / std * final_scale).view(-1, 1)
            linear_bias = 0 if linear.bias is None else linear.bias.data
            linear_bias += grn_bias_projected_bias
            new_linear.bias.data = (bn.bias + (linear_bias - bn.running_mean) * bn.weight / std) * final_scale
            self.pwconv2 = nn.Sequential(new_linear, self.pwconv2[1])

class SPPF_UniRepLK(nn.Module):
    """Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher."""

    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
        super().__init__()
        c_ = c1 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_ * 4, c2, 1, 1)
        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
        self.UniRepLK = UniRepLKNetBlock(c_ * 4, kernel_size=k)

    def forward(self, x):
        """Forward pass through Ghost Convolution block."""
        x = self.cv1(x)
        y1 = self.m(x)
        y2 = self.m(y1)
        return self.cv2(self.UniRepLK(torch.cat((x, y1, y2, self.m(y2)), 1)))

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect

# Parameters
nc: 80  # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024]  # YOLOv8n summary: 225 layers,  3157200 parameters,  3157184 gradients,   8.9 GFLOPs
  s: [0.33, 0.50, 1024]  # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPs
  m: [0.67, 0.75, 768]   # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPs
  l: [1.00, 1.00, 512]   # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
  x: [1.00, 1.25, 512]   # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs

# YOLOv8.0n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
  - [-1, 3, C2f, [128, True]]
  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
  - [-1, 6, C2f, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
  - [-1, 6, C2f, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
  - [-1, 3, C2f, [1024, True]]
  - [-1, 1, SPPF_UniRepLK, [1024, 5]]  # 9

# YOLOv8.0n head
head:
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
  - [-1, 3, C2f, [512]]  # 12

  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 12], 1, Concat, [1]]  # cat head P4
  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 9], 1, Concat, [1]]  # cat head P5
  - [-1, 3, C2f, [1024]]  # 21 (P5/32-large)

  - [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)