Skip to content

Reference for ultralytics/nn/modules/conv.py

Note

This file is available at https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/modules/conv.py. If you spot a problem please help fix it by contributing a Pull Request ūüõ†ÔłŹ. Thank you ūüôŹ!


ultralytics.nn.modules.conv.Conv

Conv(c1, c2, k=1, s=1, p=None, g=1, d=1, act=True)

Bases: Module

Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation).

Source code in ultralytics/nn/modules/conv.py
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()

forward

forward(x)

Apply convolution, batch normalization and activation to input tensor.

Source code in ultralytics/nn/modules/conv.py
def forward(self, x):
    """Apply convolution, batch normalization and activation to input tensor."""
    return self.act(self.bn(self.conv(x)))

forward_fuse

forward_fuse(x)

Perform transposed convolution of 2D data.

Source code in ultralytics/nn/modules/conv.py
def forward_fuse(self, x):
    """Perform transposed convolution of 2D data."""
    return self.act(self.conv(x))





ultralytics.nn.modules.conv.Conv2

Conv2(c1, c2, k=3, s=1, p=None, g=1, d=1, act=True)

Bases: Conv

Simplified RepConv module with Conv fusing.

Source code in ultralytics/nn/modules/conv.py
def __init__(self, c1, c2, k=3, s=1, p=None, g=1, d=1, act=True):
    """Initialize Conv layer with given arguments including activation."""
    super().__init__(c1, c2, k, s, p, g=g, d=d, act=act)
    self.cv2 = nn.Conv2d(c1, c2, 1, s, autopad(1, p, d), groups=g, dilation=d, bias=False)  # add 1x1 conv

forward

forward(x)

Apply convolution, batch normalization and activation to input tensor.

Source code in ultralytics/nn/modules/conv.py
def forward(self, x):
    """Apply convolution, batch normalization and activation to input tensor."""
    return self.act(self.bn(self.conv(x) + self.cv2(x)))

forward_fuse

forward_fuse(x)

Apply fused convolution, batch normalization and activation to input tensor.

Source code in ultralytics/nn/modules/conv.py
def forward_fuse(self, x):
    """Apply fused convolution, batch normalization and activation to input tensor."""
    return self.act(self.bn(self.conv(x)))

fuse_convs

fuse_convs()

Fuse parallel convolutions.

Source code in ultralytics/nn/modules/conv.py
def fuse_convs(self):
    """Fuse parallel convolutions."""
    w = torch.zeros_like(self.conv.weight.data)
    i = [x // 2 for x in w.shape[2:]]
    w[:, :, i[0] : i[0] + 1, i[1] : i[1] + 1] = self.cv2.weight.data.clone()
    self.conv.weight.data += w
    self.__delattr__("cv2")
    self.forward = self.forward_fuse





ultralytics.nn.modules.conv.LightConv

LightConv(c1, c2, k=1, act=nn.ReLU())

Bases: Module

Light convolution with args(ch_in, ch_out, kernel).

https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/modeling/backbones/hgnet_v2.py

Source code in ultralytics/nn/modules/conv.py
def __init__(self, c1, c2, k=1, act=nn.ReLU()):
    """Initialize Conv layer with given arguments including activation."""
    super().__init__()
    self.conv1 = Conv(c1, c2, 1, act=False)
    self.conv2 = DWConv(c2, c2, k, act=act)

forward

forward(x)

Apply 2 convolutions to input tensor.

Source code in ultralytics/nn/modules/conv.py
def forward(self, x):
    """Apply 2 convolutions to input tensor."""
    return self.conv2(self.conv1(x))





ultralytics.nn.modules.conv.DWConv

DWConv(c1, c2, k=1, s=1, d=1, act=True)

Bases: Conv

Depth-wise convolution.

Source code in ultralytics/nn/modules/conv.py
def __init__(self, c1, c2, k=1, s=1, d=1, act=True):  # ch_in, ch_out, kernel, stride, dilation, activation
    """Initialize Depth-wise convolution with given parameters."""
    super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act)





ultralytics.nn.modules.conv.DWConvTranspose2d

DWConvTranspose2d(c1, c2, k=1, s=1, p1=0, p2=0)

Bases: ConvTranspose2d

Depth-wise transpose convolution.

Source code in ultralytics/nn/modules/conv.py
def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0):  # ch_in, ch_out, kernel, stride, padding, padding_out
    """Initialize DWConvTranspose2d class with given parameters."""
    super().__init__(c1, c2, k, s, p1, p2, groups=math.gcd(c1, c2))





ultralytics.nn.modules.conv.ConvTranspose

ConvTranspose(c1, c2, k=2, s=2, p=0, bn=True, act=True)

Bases: Module

Convolution transpose 2d layer.

Source code in ultralytics/nn/modules/conv.py
def __init__(self, c1, c2, k=2, s=2, p=0, bn=True, act=True):
    """Initialize ConvTranspose2d layer with batch normalization and activation function."""
    super().__init__()
    self.conv_transpose = nn.ConvTranspose2d(c1, c2, k, s, p, bias=not bn)
    self.bn = nn.BatchNorm2d(c2) if bn else nn.Identity()
    self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

forward

forward(x)

Applies transposed convolutions, batch normalization and activation to input.

Source code in ultralytics/nn/modules/conv.py
def forward(self, x):
    """Applies transposed convolutions, batch normalization and activation to input."""
    return self.act(self.bn(self.conv_transpose(x)))

forward_fuse

forward_fuse(x)

Applies activation and convolution transpose operation to input.

Source code in ultralytics/nn/modules/conv.py
def forward_fuse(self, x):
    """Applies activation and convolution transpose operation to input."""
    return self.act(self.conv_transpose(x))





ultralytics.nn.modules.conv.Focus

Focus(c1, c2, k=1, s=1, p=None, g=1, act=True)

Bases: Module

Focus wh information into c-space.

Source code in ultralytics/nn/modules/conv.py
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):
    """Initializes Focus object with user defined channel, convolution, padding, group and activation values."""
    super().__init__()
    self.conv = Conv(c1 * 4, c2, k, s, p, g, act=act)

forward

forward(x)

Applies convolution to concatenated tensor and returns the output.

Input shape is (b,c,w,h) and output shape is (b,4c,w/2,h/2).

Source code in ultralytics/nn/modules/conv.py
def forward(self, x):
    """
    Applies convolution to concatenated tensor and returns the output.

    Input shape is (b,c,w,h) and output shape is (b,4c,w/2,h/2).
    """
    return self.conv(torch.cat((x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]), 1))





ultralytics.nn.modules.conv.GhostConv

GhostConv(c1, c2, k=1, s=1, g=1, act=True)

Bases: Module

Ghost Convolution https://github.com/huawei-noah/ghostnet.

Source code in ultralytics/nn/modules/conv.py
def __init__(self, c1, c2, k=1, s=1, g=1, act=True):
    """Initializes the GhostConv object with input channels, output channels, kernel size, stride, groups and
    activation.
    """
    super().__init__()
    c_ = c2 // 2  # hidden channels
    self.cv1 = Conv(c1, c_, k, s, None, g, act=act)
    self.cv2 = Conv(c_, c_, 5, 1, None, c_, act=act)

forward

forward(x)

Forward propagation through a Ghost Bottleneck layer with skip connection.

Source code in ultralytics/nn/modules/conv.py
def forward(self, x):
    """Forward propagation through a Ghost Bottleneck layer with skip connection."""
    y = self.cv1(x)
    return torch.cat((y, self.cv2(y)), 1)





ultralytics.nn.modules.conv.RepConv

RepConv(c1, c2, k=3, s=1, p=1, g=1, d=1, act=True, bn=False, deploy=False)

Bases: Module

RepConv is a basic rep-style block, including training and deploy status.

This module is used in RT-DETR. Based on https://github.com/DingXiaoH/RepVGG/blob/main/repvgg.py

Source code in ultralytics/nn/modules/conv.py
def __init__(self, c1, c2, k=3, s=1, p=1, g=1, d=1, act=True, bn=False, deploy=False):
    """Initializes Light Convolution layer with inputs, outputs & optional activation function."""
    super().__init__()
    assert k == 3 and p == 1
    self.g = g
    self.c1 = c1
    self.c2 = c2
    self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

    self.bn = nn.BatchNorm2d(num_features=c1) if bn and c2 == c1 and s == 1 else None
    self.conv1 = Conv(c1, c2, k, s, p=p, g=g, act=False)
    self.conv2 = Conv(c1, c2, 1, s, p=(p - k // 2), g=g, act=False)

forward

forward(x)

Forward process.

Source code in ultralytics/nn/modules/conv.py
def forward(self, x):
    """Forward process."""
    id_out = 0 if self.bn is None else self.bn(x)
    return self.act(self.conv1(x) + self.conv2(x) + id_out)

forward_fuse

forward_fuse(x)

Forward process.

Source code in ultralytics/nn/modules/conv.py
def forward_fuse(self, x):
    """Forward process."""
    return self.act(self.conv(x))

fuse_convs

fuse_convs()

Combines two convolution layers into a single layer and removes unused attributes from the class.

Source code in ultralytics/nn/modules/conv.py
def fuse_convs(self):
    """Combines two convolution layers into a single layer and removes unused attributes from the class."""
    if hasattr(self, "conv"):
        return
    kernel, bias = self.get_equivalent_kernel_bias()
    self.conv = nn.Conv2d(
        in_channels=self.conv1.conv.in_channels,
        out_channels=self.conv1.conv.out_channels,
        kernel_size=self.conv1.conv.kernel_size,
        stride=self.conv1.conv.stride,
        padding=self.conv1.conv.padding,
        dilation=self.conv1.conv.dilation,
        groups=self.conv1.conv.groups,
        bias=True,
    ).requires_grad_(False)
    self.conv.weight.data = kernel
    self.conv.bias.data = bias
    for para in self.parameters():
        para.detach_()
    self.__delattr__("conv1")
    self.__delattr__("conv2")
    if hasattr(self, "nm"):
        self.__delattr__("nm")
    if hasattr(self, "bn"):
        self.__delattr__("bn")
    if hasattr(self, "id_tensor"):
        self.__delattr__("id_tensor")

get_equivalent_kernel_bias

get_equivalent_kernel_bias()

Returns equivalent kernel and bias by adding 3x3 kernel, 1x1 kernel and identity kernel with their biases.

Source code in ultralytics/nn/modules/conv.py
def get_equivalent_kernel_bias(self):
    """Returns equivalent kernel and bias by adding 3x3 kernel, 1x1 kernel and identity kernel with their biases."""
    kernel3x3, bias3x3 = self._fuse_bn_tensor(self.conv1)
    kernel1x1, bias1x1 = self._fuse_bn_tensor(self.conv2)
    kernelid, biasid = self._fuse_bn_tensor(self.bn)
    return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid





ultralytics.nn.modules.conv.ChannelAttention

ChannelAttention(channels: int)

Bases: Module

Channel-attention module https://github.com/open-mmlab/mmdetection/tree/v3.0.0rc1/configs/rtmdet.

Source code in ultralytics/nn/modules/conv.py
def __init__(self, channels: int) -> None:
    """Initializes the class and sets the basic configurations and instance variables required."""
    super().__init__()
    self.pool = nn.AdaptiveAvgPool2d(1)
    self.fc = nn.Conv2d(channels, channels, 1, 1, 0, bias=True)
    self.act = nn.Sigmoid()

forward

forward(x: torch.Tensor) -> torch.Tensor

Applies forward pass using activation on convolutions of the input, optionally using batch normalization.

Source code in ultralytics/nn/modules/conv.py
def forward(self, x: torch.Tensor) -> torch.Tensor:
    """Applies forward pass using activation on convolutions of the input, optionally using batch normalization."""
    return x * self.act(self.fc(self.pool(x)))





ultralytics.nn.modules.conv.SpatialAttention

SpatialAttention(kernel_size=7)

Bases: Module

Spatial-attention module.

Source code in ultralytics/nn/modules/conv.py
def __init__(self, kernel_size=7):
    """Initialize Spatial-attention module with kernel size argument."""
    super().__init__()
    assert kernel_size in {3, 7}, "kernel size must be 3 or 7"
    padding = 3 if kernel_size == 7 else 1
    self.cv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
    self.act = nn.Sigmoid()

forward

forward(x)

Apply channel and spatial attention on input for feature recalibration.

Source code in ultralytics/nn/modules/conv.py
def forward(self, x):
    """Apply channel and spatial attention on input for feature recalibration."""
    return x * self.act(self.cv1(torch.cat([torch.mean(x, 1, keepdim=True), torch.max(x, 1, keepdim=True)[0]], 1)))





ultralytics.nn.modules.conv.CBAM

CBAM(c1, kernel_size=7)

Bases: Module

Convolutional Block Attention Module.

Source code in ultralytics/nn/modules/conv.py
def __init__(self, c1, kernel_size=7):
    """Initialize CBAM with given input channel (c1) and kernel size."""
    super().__init__()
    self.channel_attention = ChannelAttention(c1)
    self.spatial_attention = SpatialAttention(kernel_size)

forward

forward(x)

Applies the forward pass through C1 module.

Source code in ultralytics/nn/modules/conv.py
def forward(self, x):
    """Applies the forward pass through C1 module."""
    return self.spatial_attention(self.channel_attention(x))





ultralytics.nn.modules.conv.Concat

Concat(dimension=1)

Bases: Module

Concatenate a list of tensors along dimension.

Source code in ultralytics/nn/modules/conv.py
def __init__(self, dimension=1):
    """Concatenates a list of tensors along a specified dimension."""
    super().__init__()
    self.d = dimension

forward

forward(x)

Forward pass for the YOLOv8 mask Proto module.

Source code in ultralytics/nn/modules/conv.py
def forward(self, x):
    """Forward pass for the YOLOv8 mask Proto module."""
    return torch.cat(x, self.d)





ultralytics.nn.modules.conv.autopad

autopad(k, p=None, d=1)

Pad to 'same' shape outputs.

Source code in ultralytics/nn/modules/conv.py
def autopad(k, p=None, d=1):  # kernel, padding, dilation
    """Pad to 'same' shape outputs."""
    if d > 1:
        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]  # actual kernel-size
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
    return p





Created 2023-11-12, Updated 2024-07-21
Authors: glenn-jocher (6), Burhan-Q (1)