Reference for ultralytics/nn/modules/block.py

def __init__(self, c1: int = 16):
    """Initialize a convolutional layer with a given number of input channels.

    Args:
        c1 (int): Number of input channels.
    """
    super().__init__()
    self.conv = nn.Conv2d(c1, 1, 1, bias=False).requires_grad_(False)
    x = torch.arange(c1, dtype=torch.float)
    self.conv.weight.data[:] = nn.Parameter(x.view(1, c1, 1, 1))
    self.c1 = c1

def __init__(self, c1: int, c_: int = 256, c2: int = 32):
    """Initialize the Ultralytics YOLO models mask Proto module with specified number of protos and masks.

    Args:
        c1 (int): Input channels.
        c_ (int): Intermediate channels.
        c2 (int): Output channels (number of protos).
    """
    super().__init__()
    self.cv1 = Conv(c1, c_, k=3)
    self.upsample = nn.ConvTranspose2d(c_, c_, 2, 2, 0, bias=True)  # nn.Upsample(scale_factor=2, mode='nearest')
    self.cv2 = Conv(c_, c_, k=3)
    self.cv3 = Conv(c_, c2)

def __init__(self, c1: int, cm: int, c2: int):
    """Initialize the StemBlock of PPHGNetV2.

    Args:
        c1 (int): Input channels.
        cm (int): Middle channels.
        c2 (int): Output channels.
    """
    super().__init__()
    self.stem1 = Conv(c1, cm, 3, 2, act=nn.ReLU())
    self.stem2a = Conv(cm, cm // 2, 2, 1, 0, act=nn.ReLU())
    self.stem2b = Conv(cm // 2, cm, 2, 1, 0, act=nn.ReLU())
    self.stem3 = Conv(cm * 2, cm, 3, 2, act=nn.ReLU())
    self.stem4 = Conv(cm, c2, 1, 1, act=nn.ReLU())
    self.pool = nn.MaxPool2d(kernel_size=2, stride=1, padding=0, ceil_mode=True)

def __init__(
    self,
    c1: int,
    cm: int,
    c2: int,
    k: int = 3,
    n: int = 6,
    lightconv: bool = False,
    shortcut: bool = False,
    act: nn.Module = nn.ReLU(),
):
    """Initialize HGBlock with specified parameters.

    Args:
        c1 (int): Input channels.
        cm (int): Middle channels.
        c2 (int): Output channels.
        k (int): Kernel size.
        n (int): Number of LightConv or Conv blocks.
        lightconv (bool): Whether to use LightConv.
        shortcut (bool): Whether to use shortcut connection.
        act (nn.Module): Activation function.
    """
    super().__init__()
    block = LightConv if lightconv else Conv
    self.m = nn.ModuleList(block(c1 if i == 0 else cm, cm, k=k, act=act) for i in range(n))
    self.sc = Conv(c1 + n * cm, c2 // 2, 1, 1, act=act)  # squeeze conv
    self.ec = Conv(c2 // 2, c2, 1, 1, act=act)  # excitation conv
    self.add = shortcut and c1 == c2

def __init__(self, c1: int, c2: int, k: tuple[int, ...] = (5, 9, 13)):
    """Initialize the SPP layer with input/output channels and pooling kernel sizes.

    Args:
        c1 (int): Input channels.
        c2 (int): Output channels.
        k (tuple): Kernel sizes for max pooling.
    """
    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 __init__(self, c1: int, c2: int, k: int = 5):
    """Initialize the SPPF layer with given input/output channels and kernel size.

    Args:
        c1 (int): Input channels.
        c2 (int): Output channels.
        k (int): Kernel size.

    Notes:
        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 __init__(self, c1: int, c2: int, n: int = 1):
    """Initialize the CSP Bottleneck with 1 convolution.

    Args:
        c1 (int): Input channels.
        c2 (int): Output channels.
        n (int): Number of convolutions.
    """
    super().__init__()
    self.cv1 = Conv(c1, c2, 1, 1)
    self.m = nn.Sequential(*(Conv(c2, c2, 3) for _ in range(n)))

def __init__(self, c1: int, c2: int, n: int = 1, shortcut: bool = True, g: int = 1, e: float = 0.5):
    """Initialize a CSP Bottleneck with 2 convolutions.

    Args:
        c1 (int): Input channels.
        c2 (int): Output channels.
        n (int): Number of Bottleneck blocks.
        shortcut (bool): Whether to use shortcut connections.
        g (int): Groups for convolutions.
        e (float): Expansion ratio.
    """
    super().__init__()
    self.c = int(c2 * e)  # hidden channels
    self.cv1 = Conv(c1, 2 * self.c, 1, 1)
    self.cv2 = Conv(2 * self.c, c2, 1)  # optional act=FReLU(c2)
    # self.attention = ChannelAttention(2 * self.c)  # or SpatialAttention()
    self.m = nn.Sequential(*(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n)))

def __init__(self, c1: int, c2: int, n: int = 1, shortcut: bool = False, g: int = 1, e: float = 0.5):
    """Initialize a CSP bottleneck with 2 convolutions.

    Args:
        c1 (int): Input channels.
        c2 (int): Output channels.
        n (int): Number of Bottleneck blocks.
        shortcut (bool): Whether to use shortcut connections.
        g (int): Groups for convolutions.
        e (float): Expansion ratio.
    """
    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 __init__(self, c1: int, c2: int, n: int = 1, shortcut: bool = True, g: int = 1, e: float = 0.5):
    """Initialize the CSP Bottleneck with 3 convolutions.

    Args:
        c1 (int): Input channels.
        c2 (int): Output channels.
        n (int): Number of Bottleneck blocks.
        shortcut (bool): Whether to use shortcut connections.
        g (int): Groups for convolutions.
        e (float): Expansion ratio.
    """
    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 __init__(self, c1: int, c2: int, n: int = 1, shortcut: bool = True, g: int = 1, e: float = 0.5):
    """Initialize C3 module with cross-convolutions.

    Args:
        c1 (int): Input channels.
        c2 (int): Output channels.
        n (int): Number of Bottleneck blocks.
        shortcut (bool): Whether to use shortcut connections.
        g (int): Groups for convolutions.
        e (float): Expansion ratio.
    """
    super().__init__(c1, c2, n, shortcut, g, e)
    self.c_ = int(c2 * e)
    self.m = nn.Sequential(*(Bottleneck(self.c_, self.c_, shortcut, g, k=((1, 3), (3, 1)), e=1) for _ in range(n)))

def __init__(self, c1: int, c2: int, n: int = 3, e: float = 1.0):
    """Initialize CSP Bottleneck with a single convolution.

    Args:
        c1 (int): Input channels.
        c2 (int): Output channels.
        n (int): Number of RepConv blocks.
        e (float): Expansion ratio.
    """
    super().__init__()
    c_ = int(c2 * e)  # hidden channels
    self.cv1 = Conv(c1, c_, 1, 1)
    self.cv2 = Conv(c1, c_, 1, 1)
    self.m = nn.Sequential(*[RepConv(c_, c_) for _ in range(n)])
    self.cv3 = Conv(c_, c2, 1, 1) if c_ != c2 else nn.Identity()

def __init__(self, c1: int, c2: int, n: int = 1, shortcut: bool = True, g: int = 1, e: float = 0.5):
    """Initialize C3 module with TransformerBlock.

    Args:
        c1 (int): Input channels.
        c2 (int): Output channels.
        n (int): Number of Transformer blocks.
        shortcut (bool): Whether to use shortcut connections.
        g (int): Groups for convolutions.
        e (float): Expansion ratio.
    """
    super().__init__(c1, c2, n, shortcut, g, e)
    c_ = int(c2 * e)
    self.m = TransformerBlock(c_, c_, 4, n)

def __init__(self, c1: int, c2: int, n: int = 1, shortcut: bool = True, g: int = 1, e: float = 0.5):
    """Initialize C3 module with GhostBottleneck.

    Args:
        c1 (int): Input channels.
        c2 (int): Output channels.
        n (int): Number of Ghost bottleneck blocks.
        shortcut (bool): Whether to use shortcut connections.
        g (int): Groups for convolutions.
        e (float): Expansion ratio.
    """
    super().__init__(c1, c2, n, shortcut, g, e)
    c_ = int(c2 * e)  # hidden channels
    self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n)))

def __init__(self, c1: int, c2: int, k: int = 3, s: int = 1):
    """Initialize Ghost Bottleneck module.

    Args:
        c1 (int): Input channels.
        c2 (int): Output channels.
        k (int): Kernel size.
        s (int): Stride.
    """
    super().__init__()
    c_ = c2 // 2
    self.conv = nn.Sequential(
        GhostConv(c1, c_, 1, 1),  # pw
        DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(),  # dw
        GhostConv(c_, c2, 1, 1, act=False),  # pw-linear
    )
    self.shortcut = (
        nn.Sequential(DWConv(c1, c1, k, s, act=False), Conv(c1, c2, 1, 1, act=False)) if s == 2 else nn.Identity()
    )

def __init__(
    self, c1: int, c2: int, shortcut: bool = True, g: int = 1, k: tuple[int, int] = (3, 3), e: float = 0.5
):
    """Initialize a standard bottleneck module.

    Args:
        c1 (int): Input channels.
        c2 (int): Output channels.
        shortcut (bool): Whether to use shortcut connection.
        g (int): Groups for convolutions.
        k (tuple): Kernel sizes for convolutions.
        e (float): Expansion ratio.
    """
    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 __init__(self, c1: int, c2: int, n: int = 1, shortcut: bool = True, g: int = 1, e: float = 0.5):
    """Initialize CSP Bottleneck.

    Args:
        c1 (int): Input channels.
        c2 (int): Output channels.
        n (int): Number of Bottleneck blocks.
        shortcut (bool): Whether to use shortcut connections.
        g (int): Groups for convolutions.
        e (float): Expansion ratio.
    """
    super().__init__()
    c_ = int(c2 * e)  # hidden channels
    self.cv1 = Conv(c1, c_, 1, 1)
    self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
    self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
    self.cv4 = Conv(2 * c_, c2, 1, 1)
    self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)
    self.act = nn.SiLU()
    self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))

def __init__(self, c1: int, c2: int, s: int = 1, e: int = 4):
    """Initialize ResNet block.

    Args:
        c1 (int): Input channels.
        c2 (int): Output channels.
        s (int): Stride.
        e (int): Expansion ratio.
    """
    super().__init__()
    c3 = e * c2
    self.cv1 = Conv(c1, c2, k=1, s=1, act=True)
    self.cv2 = Conv(c2, c2, k=3, s=s, p=1, act=True)
    self.cv3 = Conv(c2, c3, k=1, act=False)
    self.shortcut = nn.Sequential(Conv(c1, c3, k=1, s=s, act=False)) if s != 1 or c1 != c3 else nn.Identity()

def __init__(self, c1: int, c2: int, s: int = 1, is_first: bool = False, n: int = 1, e: int = 4):
    """Initialize ResNet layer.

    Args:
        c1 (int): Input channels.
        c2 (int): Output channels.
        s (int): Stride.
        is_first (bool): Whether this is the first layer.
        n (int): Number of ResNet blocks.
        e (int): Expansion ratio.
    """
    super().__init__()
    self.is_first = is_first

    if self.is_first:
        self.layer = nn.Sequential(
            Conv(c1, c2, k=7, s=2, p=3, act=True), nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        )
    else:
        blocks = [ResNetBlock(c1, c2, s, e=e)]
        blocks.extend([ResNetBlock(e * c2, c2, 1, e=e) for _ in range(n - 1)])
        self.layer = nn.Sequential(*blocks)

def __init__(self, c1: int, c2: int, nh: int = 1, ec: int = 128, gc: int = 512, scale: bool = False):
    """Initialize MaxSigmoidAttnBlock.

    Args:
        c1 (int): Input channels.
        c2 (int): Output channels.
        nh (int): Number of heads.
        ec (int): Embedding channels.
        gc (int): Guide channels.
        scale (bool): Whether to use learnable scale parameter.
    """
    super().__init__()
    self.nh = nh
    self.hc = c2 // nh
    self.ec = Conv(c1, ec, k=1, act=False) if c1 != ec else None
    self.gl = nn.Linear(gc, ec)
    self.bias = nn.Parameter(torch.zeros(nh))
    self.proj_conv = Conv(c1, c2, k=3, s=1, act=False)
    self.scale = nn.Parameter(torch.ones(1, nh, 1, 1)) if scale else 1.0