YOLOv11改进 | Conv篇 |手把手教你添加动态蛇形卷积Dynamic Snake Convolution （辅助C3k2进行特征提取）

​

​

​

​

import torch
import torch.nn as nn
 
__all__ = ['C3k2_DSConv']
 
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
 
 
 
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):
        """Perform transposed convolution of 2D data."""
        return self.act(self.conv(x))
 
class DySnakeConv(nn.Module):
    def __init__(self, inc, ouc, k=3) -> None:
        super().__init__()
 
        self.conv_0 = Conv(inc, ouc, k)
        self.conv_x = DSConv(inc, ouc, 0, k)
        self.conv_y = DSConv(inc, ouc, 1, k)
 
    def forward(self, x):
        return torch.cat([self.conv_0(x), self.conv_x(x), self.conv_y(x)], dim=1)
 
 
class DSConv(nn.Module):
    def __init__(self, in_ch, out_ch, morph, kernel_size=3, if_offset=True, extend_scope=1):
        """
        The Dynamic Snake Convolution
        :param in_ch: input channel
        :param out_ch: output channel
        :param kernel_size: the size of kernel
        :param extend_scope: the range to expand (default 1 for this method)
        :param morph: the morphology of the convolution kernel is mainly divided into two types
                        along the x-axis (0) and the y-axis (1) (see the paper for details)
        :param if_offset: whether deformation is required, if it is False, it is the standard convolution kernel
        """
        super(DSConv, self).__init__()
        # use the <offset_conv> to learn the deformable offset
        self.offset_conv = nn.Conv2d(in_ch, 2 * kernel_size, 3, padding=1)
        self.bn = nn.BatchNorm2d(2 * kernel_size)
        self.kernel_size = kernel_size
 
        # two types of the DSConv (along x-axis and y-axis)
        self.dsc_conv_x = nn.Conv2d(
            in_ch,
            out_ch,
            kernel_size=(kernel_size, 1),
            stride=(kernel_size, 1),
            padding=0,
        )
        self.dsc_conv_y = nn.Conv2d(
            in_ch,
            out_ch,
            kernel_size=(1, kernel_size),
            stride=(1, kernel_size),
            padding=0,
        )
 
        self.gn = nn.GroupNorm(out_ch // 4, out_ch)
        self.act = Conv.default_act
 
        self.extend_scope = extend_scope
        self.morph = morph
        self.if_offset = if_offset
 
    def forward(self, f):
        offset = self.offset_conv(f)
        offset = self.bn(offset)
        # We need a range of deformation between -1 and 1 to mimic the snake's swing
        offset = torch.tanh(offset)
        input_shape = f.shape
        dsc = DSC(input_shape, self.kernel_size, self.extend_scope, self.morph)
        deformed_feature = dsc.deform_conv(f, offset, self.if_offset)
        if self.morph == 0:
            x = self.dsc_conv_x(deformed_feature.type(f.dtype))
            x = self.gn(x)
            x = self.act(x)
            return x
        else:
            x = self.dsc_conv_y(deformed_feature.type(f.dtype))
            x = self.gn(x)
            x = self.act(x)
            return x
 
 
# Core code, for ease of understanding, we mark the dimensions of input and output next to the code
class DSC(object):
    def __init__(self, input_shape, kernel_size, extend_scope, morph):
        self.num_points = kernel_size
        self.width = input_shape[2]
        self.height = input_shape[3]
        self.morph = morph
        self.extend_scope = extend_scope  # offset (-1 ~ 1) * extend_scope
 
        # define feature map shape
        """
        B: Batch size  C: Channel  W: Width  H: Height
        """
        self.num_batch = input_shape[0]
        self.num_channels = input_shape[1]
 
    """
    input: offset [B,2*K,W,H]  K: Kernel size (2*K: 2D image, deformation contains <x_offset> and <y_offset>)
    output_x: [B,1,W,K*H]   coordinate map
    output_y: [B,1,K*W,H]   coordinate map
    """
 
    def _coordinate_map_3D(self, offset, if_offset):
        device = offset.device
        # offset
        y_offset, x_offset = torch.split(offset, self.num_points, dim=1)
 
        y_center = torch.arange(0, self.width).repeat([self.height])
        y_center = y_center.reshape(self.height, self.width)
        y_center = y_center.permute(1, 0)
        y_center = y_center.reshape([-1, self.width, self.height])
        y_center = y_center.repeat([self.num_points, 1, 1]).float()
        y_center = y_center.unsqueeze(0)
 
        x_center = torch.arange(0, self.height).repeat([self.width])
        x_center = x_center.reshape(self.width, self.height)
        x_center = x_center.permute(0, 1)
        x_center = x_center.reshape([-1, self.width, self.height])
        x_center = x_center.repeat([self.num_points, 1, 1]).float()
        x_center = x_center.unsqueeze(0)
 
        if self.morph == 0:
            """
            Initialize the kernel and flatten the kernel
                y: only need 0
                x: -num_points//2 ~ num_points//2 (Determined by the kernel size)
                !!! The related PPT will be submitted later, and the PPT will contain the whole changes of each step
            """
            y = torch.linspace(0, 0, 1)
            x = torch.linspace(
                -int(self.num_points // 2),
                int(self.num_points // 2),
                int(self.num_points),
            )
 
            y, x = torch.meshgrid(y, x)
            y_spread = y.reshape(-1, 1)
            x_spread = x.reshape(-1, 1)
 
            y_grid = y_spread.repeat([1, self.width * self.height])
            y_grid = y_grid.reshape([self.num_points, self.width, self.height])
            y_grid = y_grid.unsqueeze(0)  # [B*K*K, W,H]
 
            x_grid = x_spread.repeat([1, self.width * self.height])
            x_grid = x_grid.reshape([self.num_points, self.width, self.height])
            x_grid = x_grid.unsqueeze(0)  # [B*K*K, W,H]
 
            y_new = y_center + y_grid
            x_new = x_center + x_grid
 
            y_new = y_new.repeat(self.num_batch, 1, 1, 1).to(device)
            x_new = x_new.repeat(self.num_batch, 1, 1, 1).to(device)
 
            y_offset_new = y_offset.detach().clone()
 
            if if_offset:
                y_offset = y_offset.permute(1, 0, 2, 3)
                y_offset_new = y_offset_new.permute(1, 0, 2, 3)
                center = int(self.num_points // 2)
 
                # The center position remains unchanged and the rest of the positions begin to swing
                # This part is quite simple. The main idea is that "offset is an iterative process"
                y_offset_new[center] = 0
                for index in range(1, center):
                    y_offset_new[center + index] = (y_offset_new[center + index - 1] + y_offset[center + index])
                    y_offset_new[center - index] = (y_offset_new[center - index + 1] + y_offset[center - index])
                y_offset_new = y_offset_new.permute(1, 0, 2, 3).to(device)
                y_new = y_new.add(y_offset_new.mul(self.extend_scope))
 
            y_new = y_new.reshape(
                [self.num_batch, self.num_points, 1, self.width, self.height])
            y_new = y_new.permute(0, 3, 1, 4, 2)
            y_new = y_new.reshape([
                self.num_batch, self.num_points * self.width, 1 * self.height
            ])
            x_new = x_new.reshape(
                [self.num_batch, self.num_points, 1, self.width, self.height])
            x_new = x_new.permute(0, 3, 1, 4, 2)
            x_new = x_new.reshape([
                self.num_batch, self.num_points * self.width, 1 * self.height
            ])
            return y_new, x_new
 
        else:
            """
            Initialize the kernel and flatten the kernel
                y: -num_points//2 ~ num_points//2 (Determined by the kernel size)
                x: only need 0
            """
            y = torch.linspace(
                -int(self.num_points // 2),
                int(self.num_points // 2),
                int(self.num_points),
            )
            x = torch.linspace(0, 0, 1)
 
            y, x = torch.meshgrid(y, x)
            y_spread = y.reshape(-1, 1)
            x_spread = x.reshape(-1, 1)
 
            y_grid = y_spread.repeat([1, self.width * self.height])
            y_grid = y_grid.reshape([self.num_points, self.width, self.height])
            y_grid = y_grid.unsqueeze(0)
 
            x_grid = x_spread.repeat([1, self.width * self.height])
            x_grid = x_grid.reshape([self.num_points, self.width, self.height])
            x_grid = x_grid.unsqueeze(0)
 
            y_new = y_center + y_grid
            x_new = x_center + x_grid
 
            y_new = y_new.repeat(self.num_batch, 1, 1, 1)
            x_new = x_new.repeat(self.num_batch, 1, 1, 1)
 
            y_new = y_new.to(device)
            x_new = x_new.to(device)
            x_offset_new = x_offset.detach().clone()
 
            if if_offset:
                x_offset = x_offset.permute(1, 0, 2, 3)
                x_offset_new = x_offset_new.permute(1, 0, 2, 3)
                center = int(self.num_points // 2)
                x_offset_new[center] = 0
                for index in range(1, center):
                    x_offset_new[center + index] = (x_offset_new[center + index - 1] + x_offset[center + index])
                    x_offset_new[center - index] = (x_offset_new[center - index + 1] + x_offset[center - index])
                x_offset_new = x_offset_new.permute(1, 0, 2, 3).to(device)
                x_new = x_new.add(x_offset_new.mul(self.extend_scope))
 
            y_new = y_new.reshape(
                [self.num_batch, 1, self.num_points, self.width, self.height])
            y_new = y_new.permute(0, 3, 1, 4, 2)
            y_new = y_new.reshape([
                self.num_batch, 1 * self.width, self.num_points * self.height
            ])
            x_new = x_new.reshape(
                [self.num_batch, 1, self.num_points, self.width, self.height])
            x_new = x_new.permute(0, 3, 1, 4, 2)
            x_new = x_new.reshape([
                self.num_batch, 1 * self.width, self.num_points * self.height
            ])
            return y_new, x_new
 
    """
    input: input feature map [N,C,D,W,H]；coordinate map [N,K*D,K*W,K*H] 
    output: [N,1,K*D,K*W,K*H]  deformed feature map
    """
 
    def _bilinear_interpolate_3D(self, input_feature, y, x):
        device = input_feature.device
        y = y.reshape([-1]).float()
        x = x.reshape([-1]).float()
 
        zero = torch.zeros([]).int()
        max_y = self.width - 1
        max_x = self.height - 1
 
        # find 8 grid locations
        y0 = torch.floor(y).int()
        y1 = y0 + 1
        x0 = torch.floor(x).int()
        x1 = x0 + 1
 
        # clip out coordinates exceeding feature map volume
        y0 = torch.clamp(y0, zero, max_y)
        y1 = torch.clamp(y1, zero, max_y)
        x0 = torch.clamp(x0, zero, max_x)
        x1 = torch.clamp(x1, zero, max_x)
 
        input_feature_flat = input_feature.flatten()
        input_feature_flat = input_feature_flat.reshape(
            self.num_batch, self.num_channels, self.width, self.height)
        input_feature_flat = input_feature_flat.permute(0, 2, 3, 1)
        input_feature_flat = input_feature_flat.reshape(-1, self.num_channels)
        dimension = self.height * self.width
 
        base = torch.arange(self.num_batch) * dimension
        base = base.reshape([-1, 1]).float()
 
        repeat = torch.ones([self.num_points * self.width * self.height
                             ]).unsqueeze(0)
        repeat = repeat.float()
 
        base = torch.matmul(base, repeat)
        base = base.reshape([-1])
 
        base = base.to(device)
 
        base_y0 = base + y0 * self.height
        base_y1 = base + y1 * self.height
 
        # top rectangle of the neighbourhood volume
        index_a0 = base_y0 - base + x0
        index_c0 = base_y0 - base + x1
 
        # bottom rectangle of the neighbourhood volume
        index_a1 = base_y1 - base + x0
        index_c1 = base_y1 - base + x1
 
        # get 8 grid values
        value_a0 = input_feature_flat[index_a0.type(torch.int64)].to(device)
        value_c0 = input_feature_flat[index_c0.type(torch.int64)].to(device)
        value_a1 = input_feature_flat[index_a1.type(torch.int64)].to(device)
        value_c1 = input_feature_flat[index_c1.type(torch.int64)].to(device)
 
        # find 8 grid locations
        y0 = torch.floor(y).int()
        y1 = y0 + 1
        x0 = torch.floor(x).int()
        x1 = x0 + 1
 
        # clip out coordinates exceeding feature map volume
        y0 = torch.clamp(y0, zero, max_y + 1)
        y1 = torch.clamp(y1, zero, max_y + 1)
        x0 = torch.clamp(x0, zero, max_x + 1)
        x1 = torch.clamp(x1, zero, max_x + 1)
 
        x0_float = x0.float()
        x1_float = x1.float()
        y0_float = y0.float()
        y1_float = y1.float()
 
        vol_a0 = ((y1_float - y) * (x1_float - x)).unsqueeze(-1).to(device)
        vol_c0 = ((y1_float - y) * (x - x0_float)).unsqueeze(-1).to(device)
        vol_a1 = ((y - y0_float) * (x1_float - x)).unsqueeze(-1).to(device)
        vol_c1 = ((y - y0_float) * (x - x0_float)).unsqueeze(-1).to(device)
 
        outputs = (value_a0 * vol_a0 + value_c0 * vol_c0 + value_a1 * vol_a1 +
                   value_c1 * vol_c1)
 
        if self.morph == 0:
            outputs = outputs.reshape([
                self.num_batch,
                self.num_points * self.width,
                1 * self.height,
                self.num_channels,
            ])
            outputs = outputs.permute(0, 3, 1, 2)
        else:
            outputs = outputs.reshape([
                self.num_batch,
                1 * self.width,
                self.num_points * self.height,
                self.num_channels,
            ])
            outputs = outputs.permute(0, 3, 1, 2)
        return outputs
 
    def deform_conv(self, input, offset, if_offset):
        y, x = self._coordinate_map_3D(offset, if_offset)
        deformed_feature = self._bilinear_interpolate_3D(input, y, x)
        return deformed_feature
 
 
class Bottleneck(nn.Module):
    """Standard bottleneck."""
 
    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
        """Initializes a bottleneck module with given input/output channels, shortcut option, group, kernels, and
        expansion.
        """
        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):
        """'forward()' applies the YOLO FPN to input data."""
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
 
 
class Bottleneck_DySnakeConv(Bottleneck):
    """Standard bottleneck with DySnakeConv."""
 
    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):  # ch_in, ch_out, shortcut, groups, kernels, expand
        super().__init__(c1, c2, shortcut, g, k, e)
        c_ = int(c2 * e)  # hidden channels
        self.cv2 = DySnakeConv(c_, c2, k[1])
        self.cv3 = Conv(c2 * 3, c2, k=1)
 
    def forward(self, x):
        """'forward()' applies the YOLOv5 FPN to input data."""
        return x + self.cv3(self.cv2(self.cv1(x))) if self.add else self.cv3(self.cv2(self.cv1(x)))
 
 
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):
        """Initializes a CSP bottleneck with 2 convolutions and n Bottleneck blocks for faster processing."""
        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 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_DSConv(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_DySnakeConv(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
 
class C3k2_DSConv(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_DSConv(self.c, self.c, 2, shortcut, g) if c3k else Bottleneck(self.c, self.c, shortcut, g) for _ in range(n)
        )
    # 在特征提取时用DSConv,在辅助特征融合时换回原先的Bottleneck
 
 
if __name__ == "__main__":
    # Generating Sample image
    image_size = (1, 64, 240, 240)
    image = torch.rand(*image_size)
 
    # Model
    mobilenet_v1 = C3k2_DSConv(64, 64, c3k=True)
 
    out = mobilenet_v1(image)
    print(out.size())
 

# 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_DSConv, [128, True]]
  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
  - [-1, 6, C2f_DSConv, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
  - [-1, 6, C2f_DSConv, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
  - [-1, 3, C2f_DSConv, [1024, True]]
  - [-1, 1, SPPF, [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_DSConv, [256]]  # 15 (P3/8-small)
 
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 12], 1, Concat, [1]]  # cat head P4
  - [-1, 3, C2f_DSConv, [512]]  # 18 (P4/16-medium)
 
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 9], 1, Concat, [1]]  # cat head P5
  - [-1, 3, C2f_DSConv, [1024]]  # 21 (P5/32-large)
 
  - [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)