YOLOv8改进之C2f-DySnakeConv（动态蛇形卷积Dynamic Snake Convolution）

一、动态蛇形卷积Dynamic Snake Convolution论文

论文地址：2307.08388.pdf (arxiv.org)

二、动态蛇形卷积的简要介绍

   动态蛇形卷积（Dynamic Snake Convolution）的设计灵感来源于蛇形的形状，用于改善对目标形状和边界的敏感性。能够帮助神经网络更好地捕捉目标的形状信息，特别是对于复杂的或不规则形状的目标。通过引入动态的、可变形的卷积核来实现这一目标。这种可变形的卷积核能够根据目标的形状和边界信息进行调整，从而更好地适应目标的特定形状。

   传统的卷积操作在处理目标形状变化较大的情况下可能存在一定的局限性，而动态蛇形卷积则能够通过自适应性地调整卷积核的形状和大小，更有效地捕获目标的特征。

    这种模块的应用通常能够增强目标检测模型对不同尺度、形状和姿态的目标的感知能力，从而提高目标检测的准确性和鲁棒性。虽然这只是目标检测中的一种模块，但它代表了在深度学习领域中不断创新和改进的努力，以提高模型对复杂场景的理解能力。

三、算法实现

 1、在官方的yolov8包中ultralytics\ultralytics\nn的目录下新创建一个文件夹other_modules，用于存放额外添加的改进模块。

在other_modules文件夹下创建dynamic_snake_conv.py文件，存放dynamic_snake_conv动态蛇形卷积代码：

import torch
import torch.nn as nn
from ..modules.conv import Conv

__all__ = ['DySnakeConv']

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

在 ultralytics\ultralytics\nn\other_modules\block.py文件中开头声明动态蛇卷积：

from ultralytics.nn.modules import Conv
from .dynamic_snake_conv import DySnakeConv

并在__all__中添加：

然后还是在这个block文件中添加C2f DySnakeConv代码：

#######      添加 C2f DySnakeConv       ##########
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_DySnakeConv(C2f):
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
        super().__init__(c1, c2, n, shortcut, g, e)
        self.m = nn.ModuleList(Bottleneck_DySnakeConv(self.c, self.c, shortcut, g, k=(3, 3), e=1.0) for _ in range(n))

2、在ultralytics\ultralytics\nn\tasks.py文件里修改

首先在该文件开头引入上一步创建的文件夹other_modules：

from ultralytics.nn.other_modules.block import C2f_DySnakeConv
from ultralytics.nn.other_modules import *

然后在下边的然后def parse_model模块中添加warehouse_manager：在括号里面添加一个参数warehouse_manager：

def parse_model(d, ch, verbose=True, warehouse_manager=None):

 然后在该模块的下边加入C2f_DySnakeConv的运行算法，将原来程序中的685-694行中的内容：

修改为加入C2f_DySnakeConv的运行算法：

        if m in (Classify, Conv, ConvTranspose, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, Focus,
                 BottleneckCSP, C1, C2, C2f, C3, C3TR, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x, RepC3,
                 C2f_DBB,C2f_DySnakeConv):
            if args[0] == 'head_channel':
                args[0] = d[args[0]]
            c1, c2 = ch[f], args[0]
            if c2 != nc:  # if c2 not equal to number of classes (i.e. for Classify() output)
                c2 = make_divisible(min(c2, max_channels) * width, 8)

            args = [c1, c2, *args[1:]]


            if m in (
            BottleneckCSP, C1, C2, C2f, C3, C3TR, C3Ghost, C3x, RepC3, C2f_DBB,C2f_DySnakeConv):
                args.insert(2, n)  # number of repeats
                n = 1

3、创建YOLOv8+C2f-DySnakeConv的yaml文件 ：

# 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: 2  # 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_DySnakeConv, [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, [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)

四、运行测试

可以看出模型结构中已将yolov8原始结构已经包含C2f-DySnakeConv模块。