深入理解 YOLOv11 算法核心模块与结构

2. 标准卷积层

这是最基础的构建块，包含卷积、批归一化和激活函数。

class Conv(nn.Module):
    """卷积层，包含卷积、批归一化和激活函数"""
    def __init__(self, in_channels, out_channels, kernel_size=3, stride=1, padding=None, groups=1, act=True):
        super(Conv, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, autopad(kernel_size, padding), groups=groups, bias=False)
        self.bn = nn.BatchNorm2d(out_channels)
        self.act = nn.SiLU() if act else nn.Identity()
    def forward(self, x):
        return self.act(self.bn(self.conv(x)))

3. Bottleneck 结构

瓶颈模块通过压缩通道再扩展的方式，在减少计算量的同时保留信息。

class Bottleneck(nn.Module):
    """标准瓶颈模块，包含两个卷积层"""
    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
        super(Bottleneck, self).__init__()
        c_ = int(c2 * e)
        self.cv1 = Conv(c1, c_, k[0], 1)
        self.cv2 = Conv(c_, c2, k[1], 1)
        self.add = shortcut and c1 == c2
    def forward(self, x):
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))

4. C2f 层

C2f 结合了多个 Bottleneck 模块，在小网络中表现优异，有助于加速处理。

class C2f(nn.Module):
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
        super().__init__()
        self.c = int(c2 * e)
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv((2 + n) * self.c, c2, 1)
        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):
        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):
        y = self.cv1(x).split((self.c, self.c), 1)
        y = [y[0], y[1]]
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))

5. C3k 层

C3k 是 C3 系列的改进版，通常用于平衡速度与精度。

class C3k(nn.Module):
    """C3k 模块，包含多个瓶颈模块"""
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5, k=3):
        super(C3k, self).__init__()
        c_ = int(c2 * e)
        self.m = nn.Sequential(*(Bottleneck(c1, c2, shortcut, g, k=(k, k), e=e) for _ in range(n)))
    def forward(self, x):
        return self.m(x)

6. C3k2 层

在大网络中，C3k2 往往替代 C3k，进一步增强了特征融合能力。

class C3k2(C2f):
    def __init__(self, c1, c2, n=1, c3k=False, e=0.5, g=1, shortcut=True):
        super().__init__(c1, c2, n, shortcut, g, e)
        self.m = nn.ModuleList(
            C3k(self.c, self.c, 2, shortcut, g) if c3k else Bottleneck(self.c, self.c, shortcut, g) for _ in range(n)
        )

7. C3k 动态卷积

将动态卷积引入 C3k 结构，旨在进一步提升模型的适应性。

class C3k_DynamicConv(C3k):
    """C3k 模块，使用动态卷积"""
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5, k=3):
        super().__init__(c1, c2, n, shortcut, g, e, k)
        c_ = int(c2 * e)
        self.m = nn.Sequential(*(Bottleneck_DynamicConv(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))

class C3k2_DynamicConv(C3k2):
    """C3k2 模块，使用动态卷积"""
    def __init__(self, c1, c2, n=1, c3k=False, e=0.5, g=1, shortcut=True):
        super().__init__(c1, c2, n, c3k, e, g, shortcut)
        self.m = nn.ModuleList(C3k_DynamicConv(self.c, self.c, 2, shortcut, g) if c3k else Bottleneck_DynamicConv(self.c, self.c, shortcut, g, k=(3, 3), e=1.0) for _ in range(n))

8. FFN 层

前馈神经网络层负责非线性变换，增强特征表达能力。

9. PSA 层

位置敏感注意力（PSA）模块引入了自注意力机制，帮助模型关注关键区域。

class PSABlock(nn.Module):
    def __init__(self, c, attn_ratio=0.5, num_heads=4, shortcut=True) -> None:
        super().__init__()
        self.attn = Attention(c, attn_ratio=attn_ratio, num_heads=num_heads)
        self.ffn = nn.Sequential(Conv(c, c * 2, 1), Conv(c * 2, c, 1, act=False))
        self.add = shortcut
    def forward(self, x):
        x = x + self.attn(x) if self.add else self.attn(x)
        x = x + self.ffn(x) if self.add else self.ffn(x)
        return x

10. C2PSA 层

结合卷积与注意力机制的混合模块，进一步优化特征提取效果。

注意力机制的卷积块：

class C2PSA(nn.Module):
    def __init__(self, c1, c2, n=1, e=0.5):
        super().__init__()
        assert c1 == c2
        self.c = int(c1 * e)
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv(2 * self.c, c1, 1)
        self.m = nn.Sequential(*(PSABlock(self.c, attn_ratio=0.5, num_heads=self.c // 64) for _ in range(n)))
    def forward(self, x):
        a, b = self.cv1(x).split((self.c, self.c), dim=1)
        b = self.m(b)
        return self.cv2(torch.cat((a, b), 1))