YOLOv8改进-添加YOLOv10的C2fCIB模块

添加C2fCIB注意力机制到block模块。

class RepVGGDW(torch.nn.Module):
    def __init__(self, ed) -> None:
        super().__init__()
        self.conv = Conv(ed, ed, 7, 1, 3, g=ed, act=False)
        self.conv1 = Conv(ed, ed, 3, 1, 1, g=ed, act=False)
        self.dim = ed
        self.act = nn.SiLU()
    
    def forward(self, x):
        return self.act(self.conv(x) + self.conv1(x))
    
    def forward_fuse(self, x):
        return self.act(self.conv(x))

    @torch.no_grad()
    def fuse(self):
        conv = fuse_conv_and_bn(self.conv.conv, self.conv.bn)
        conv1 = fuse_conv_and_bn(self.conv1.conv, self.conv1.bn)
        
        conv_w = conv.weight
        conv_b = conv.bias
        conv1_w = conv1.weight
        conv1_b = conv1.bias
        
        conv1_w = torch.nn.functional.pad(conv1_w, [2,2,2,2])

        final_conv_w = conv_w + conv1_w
        final_conv_b = conv_b + conv1_b

        conv.weight.data.copy_(final_conv_w)
        conv.bias.data.copy_(final_conv_b)

        self.conv = conv
        del self.conv1

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

    def __init__(self, c1, c2, shortcut=True, e=0.5, lk=False):
        """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 = nn.Sequential(
            Conv(c1, c1, 3, g=c1),
            Conv(c1, 2 * c_, 1),
            Conv(2 * c_, 2 * c_, 3, g=2 * c_) if not lk else RepVGGDW(2 * c_),
            Conv(2 * c_, c2, 1),
            Conv(c2, c2, 3, g=c2),
        )

        self.add = shortcut and c1 == c2

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

class C2fCIB(C2f):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""

    def __init__(self, c1, c2, n=1, shortcut=False, lk=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__(c1, c2, n, shortcut, g, e)
        self.m = nn.ModuleList(CIB(self.c, self.c, shortcut, e=1.0, lk=lk) for _ in range(n))

将该代码放ultralytics/nn/modules/block.py中。

再将模块添加到block.py的__all__中。 

 到ultralytics/nn/modules/__init__.py中添加C2fCIB模块。 

分别在.block导入C2fCIB和在__all__添加C2fCIB。 

 

然后，需要在 ultralytics/nn/tasks.py中加入C2fCIB。

在这个里面直接导入C2fCIB即可。

 然后再到parse_model函数中加入C2fCIB即可。

 

 然后，就可以再yaml文件里里面添加该模块了。

  # 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, [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, [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, C2fCIB, [1024, True, True]] # 22 (P5/32-large)

  - [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)