class Bottleneck(nn.Module):
    """Standard bottleneck."""

    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
        """Initializes a standard bottleneck module with optional shortcut connection and configurable parameters."""
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, k[0], 1)
        self.cv2 = Conv(c_, c2, k[1], 1, g=g)
        self.add = shortcut and c1 == c2

    def forward(self, x):
        """Applies the YOLO FPN to input data."""
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))

class Conv(nn.Module):
    """Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""

    default_act = nn.SiLU()  # default activation

    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
        """Initialize Conv layer with given arguments including activation."""
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

    def forward(self, x):
        """Apply convolution, batch normalization and activation to input tensor."""
        return self.act(self.bn(self.conv(x)))

    def forward_fuse(self, x):
        """Apply convolution and activation without batch normalization."""
        return self.act(self.conv(x))

class C3(nn.Module):
    """CSP Bottleneck with 3 convolutions."""

    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        """Initialize the CSP Bottleneck with given channels, number, shortcut, groups, and expansion values."""
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(2 * c_, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, k=((1, 1), (3, 3)), e=1.0) for _ in range(n)))

    def forward(self, x):
        """Forward pass through the CSP bottleneck with 2 convolutions."""
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))

class C3k(C3):
    """C3k is a CSP bottleneck module with customizable kernel sizes for feature extraction in neural networks."""

    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, k=3):
        """Initializes the C3k module with specified channels, number of layers, and configurations."""
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)  # hidden channels
        # self.m = nn.Sequential(*(RepBottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))

class C2f(nn.Module):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""

    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
        """Initialize CSP bottleneck layer with two convolutions with arguments ch_in, ch_out, number, shortcut, groups,
        expansion.
        """
        super().__init__()
        self.c = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv((2 + n) * self.c, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.ModuleList(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n))

    def forward(self, x):
        """Forward pass through C2f layer."""
        y = list(self.cv1(x).chunk(2, 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))

    def forward_split(self, x):
        """Forward pass using split() instead of chunk()."""
        y = list(self.cv1(x).split((self.c, self.c), 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))

class C3k2(C2f):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""

    def __init__(self, c1, c2, n=1, c3k=False, e=0.5, g=1, shortcut=True):
        """Initializes the C3k2 module, a faster CSP Bottleneck with 2 convolutions and optional C3k blocks."""
        super().__init__(c1, c2, n, shortcut, g, e)
        self.m = nn.ModuleList(
            C3k(self.c, self.c, 2, shortcut, g) if c3k else Bottleneck(self.c, self.c, shortcut, g) for _ in range(n)
        )


class C3k(C3):
    """C3k is a CSP bottleneck module with customizable kernel sizes for feature extraction in neural networks."""

    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, k=3):
        """Initializes the C3k module with specified channels, number of layers, and configurations."""
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)  # hidden channels
        # self.m = nn.Sequential(*(RepBottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))

class SPP(nn.Module):
    """Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729."""

    def __init__(self, c1, c2, k=(5, 9, 13)):
        """Initialize the SPP layer with input/output channels and pooling kernel sizes."""
        super().__init__()
        c_ = c1 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])

    def forward(self, x):
        """Forward pass of the SPP layer, performing spatial pyramid pooling."""
        x = self.cv1(x)
        return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))

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

    def __init__(self, c1, c2, k=5):
        """
        Initializes the SPPF layer with given input/output channels and kernel size.

        This module is 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)

    def forward(self, x):
        """Forward pass through Ghost Convolution block."""
        y = [self.cv1(x)]
        y.extend(self.m(y[-1]) for _ in range(3))
        return self.cv2(torch.cat(y, 1))

class C2PSA(nn.Module):

    def __init__(self, c1, c2, n=1, e=0.5):
        """Initializes the C2PSA module with specified input/output channels, number of layers, and expansion ratio."""
        super().__init__()
        assert c1 == c2
        self.c = int(c1 * e)
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv(2 * self.c, c1, 1)

        self.m = nn.Sequential(*(PSABlock(self.c, attn_ratio=0.5, num_heads=self.c // 64) for _ in range(n)))

    def forward(self, x):
        """Processes the input tensor 'x' through a series of PSA blocks and returns the transformed tensor."""
        a, b = self.cv1(x).split((self.c, self.c), dim=1)
        b = self.m(b)
        return self.cv2(torch.cat((a, b), 1))

class AAttn(nn.Module):
    """
    Area-attention module for YOLO models, providing efficient attention mechanisms.

    This module implements an area-based attention mechanism that processes input features in a spatially-aware manner,
    making it particularly effective for object detection tasks.

    Attributes:
        area (int): Number of areas the feature map is divided.
        num_heads (int): Number of heads into which the attention mechanism is divided.
        head_dim (int): Dimension of each attention head.
        qkv (Conv): Convolution layer for computing query, key and value tensors.
        proj (Conv): Projection convolution layer.
        pe (Conv): Position encoding convolution layer.

    Methods:
        forward: Applies area-attention to input tensor.

    Examples:
        >>> attn = AAttn(dim=256, num_heads=8, area=4)
        >>> x = torch.randn(1, 256, 32, 32)
        >>> output = attn(x)
        >>> print(output.shape)
        torch.Size([1, 256, 32, 32])
    """

    def __init__(self, dim, num_heads, area=1):
        """
        Initializes an Area-attention module for YOLO models.

        Args:
            dim (int): Number of hidden channels.
            num_heads (int): Number of heads into which the attention mechanism is divided.
            area (int): Number of areas the feature map is divided, default is 1.
        """
        super().__init__()
        self.area = area

        self.num_heads = num_heads
        self.head_dim = head_dim = dim // num_heads
        all_head_dim = head_dim * self.num_heads

        self.qkv = Conv(dim, all_head_dim * 3, 1, act=False)
        self.proj = Conv(all_head_dim, dim, 1, act=False)
        self.pe = Conv(all_head_dim, dim, 7, 1, 3, g=dim, act=False)

    def forward(self, x):
        """Processes the input tensor 'x' through the area-attention."""
        B, C, H, W = x.shape
        N = H * W

        qkv = self.qkv(x).flatten(2).transpose(1, 2)
        if self.area > 1:
            qkv = qkv.reshape(B * self.area, N // self.area, C * 3)
            B, N, _ = qkv.shape
        q, k, v = (
            qkv.view(B, N, self.num_heads, self.head_dim * 3)
            .permute(0, 2, 3, 1)
            .split([self.head_dim, self.head_dim, self.head_dim], dim=2)
        )
        attn = (q.transpose(-2, -1) @ k) * (self.head_dim**-0.5)
        attn = attn.softmax(dim=-1)
        x = v @ attn.transpose(-2, -1)
        x = x.permute(0, 3, 1, 2)
        v = v.permute(0, 3, 1, 2)

        if self.area > 1:
            x = x.reshape(B // self.area, N * self.area, C)
            v = v.reshape(B // self.area, N * self.area, C)
            B, N, _ = x.shape

        x = x.reshape(B, H, W, C).permute(0, 3, 1, 2).contiguous()
        v = v.reshape(B, H, W, C).permute(0, 3, 1, 2).contiguous()

        x = x + self.pe(v)
        return self.proj(x)