Yolo11网络结构详解与对比

时隔一年半，u版yolo再次推出新版，它是基于u版前一代yolov8的基础上改进的，本贴讨论一下改进的地方，直接看网络结构：

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLO11 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=yolo11n.yaml' will call yolo11.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
  m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
  l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
  x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs

# YOLO11n 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, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]] # 9
  - [-1, 2, C2PSA, [1024]] # 10

# YOLO11n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, C3k2, [512, False]] # 13

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)

  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

可以看到首先在backbone部分增加了一个C2PSA模块，并且将C2f替换为了C3k2
先看一下C3k2：

class C3k2(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(self.c, self.c, 2, shortcut, g) if c3k else Bottleneck(self.c, self.c, shortcut, g) for _ in range(n)
        )


class C3k(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(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))

可以看到，相比于C2f，当超参数c3k=True时，瓶颈块替换为 C3k，否则还是C2f,而C3k相比于C3则是可以让使用者自定义卷积块大小，更加灵活。

重头戏在C2PSA上，直接看代码：

class C2PSA(nn.Module):
    """
    C2PSA module with attention mechanism for enhanced feature extraction and processing.

    This module implements a convolutional block with attention mechanisms to enhance feature extraction and processing
    capabilities. It includes a series of PSABlock modules for self-attention and feed-forward operations.

    Attributes:
        c (int): Number of hidden channels.
        cv1 (Conv): 1x1 convolution layer to reduce the number of input channels to 2*c.
        cv2 (Conv): 1x1 convolution layer to reduce the number of output channels to c.
        m (nn.Sequential): Sequential container of PSABlock modules for attention and feed-forward operations.

    Methods:
        forward: Performs a forward pass through the C2PSA module, applying attention and feed-forward operations.

    Notes:
        This module essentially is the same as PSA module, but refactored to allow stacking more PSABlock modules.

    Examples:
        >>> c2psa = C2PSA(c1=256, c2=256, n=3, e=0.5)
        >>> input_tensor = torch.randn(1, 256, 64, 64)
        >>> output_tensor = c2psa(input_tensor)
    """

    def __init__(self, c1, c2, n=1, e=0.5):
        """Initializes the C2PSA module with specified input/output channels, number of layers, and expansion ratio."""
        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):
        """Processes the input tensor 'x' through a series of PSA blocks and returns the transformed tensor."""
        a, b = self.cv1(x).split((self.c, self.c), dim=1)
        b = self.m(b)
        return self.cv2(torch.cat((a, b), 1))

class PSABlock(nn.Module):
    """
    PSABlock class implementing a Position-Sensitive Attention block for neural networks.

    This class encapsulates the functionality for applying multi-head attention and feed-forward neural network layers
    with optional shortcut connections.

    Attributes:
        attn (Attention): Multi-head attention module.
        ffn (nn.Sequential): Feed-forward neural network module.
        add (bool): Flag indicating whether to add shortcut connections.

    Methods:
        forward: Performs a forward pass through the PSABlock, applying attention and feed-forward layers.

    Examples:
        Create a PSABlock and perform a forward pass
        >>> psablock = PSABlock(c=128, attn_ratio=0.5, num_heads=4, shortcut=True)
        >>> input_tensor = torch.randn(1, 128, 32, 32)
        >>> output_tensor = psablock(input_tensor)
    """

    def __init__(self, c, attn_ratio=0.5, num_heads=4, shortcut=True) -> None:
        """Initializes the PSABlock with attention and feed-forward layers for enhanced feature extraction."""
        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):
        """Executes a forward pass through PSABlock, applying attention and feed-forward layers to the input tensor."""
        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


class Attention(nn.Module):
    """
    Attention module that performs self-attention on the input tensor.

    Args:
        dim (int): The input tensor dimension.
        num_heads (int): The number of attention heads.
        attn_ratio (float): The ratio of the attention key dimension to the head dimension.

    Attributes:
        num_heads (int): The number of attention heads.
        head_dim (int): The dimension of each attention head.
        key_dim (int): The dimension of the attention key.
        scale (float): The scaling factor for the attention scores.
        qkv (Conv): Convolutional layer for computing the query, key, and value.
        proj (Conv): Convolutional layer for projecting the attended values.
        pe (Conv): Convolutional layer for positional encoding.
    """

    def __init__(self, dim, num_heads=8, attn_ratio=0.5):
        """Initializes multi-head attention module with query, key, and value convolutions and positional encoding."""
        super().__init__()
        self.num_heads = num_heads
        self.head_dim = dim // num_heads
        self.key_dim = int(self.head_dim * attn_ratio)
        self.scale = self.key_dim**-0.5
        nh_kd = self.key_dim * num_heads
        h = dim + nh_kd * 2
        self.qkv = Conv(dim, h, 1, act=False)
        self.proj = Conv(dim, dim, 1, act=False)
        self.pe = Conv(dim, dim, 3, 1, g=dim, act=False)

    def forward(self, x):
        """
        Forward pass of the Attention module.

        Args:
            x (torch.Tensor): The input tensor.

        Returns:
            (torch.Tensor): The output tensor after self-attention.
        """
        B, C, H, W = x.shape
        N = H * W
        qkv = self.qkv(x)
        q, k, v = qkv.view(B, self.num_heads, self.key_dim * 2 + self.head_dim, N).split(
            [self.key_dim, self.key_dim, self.head_dim], dim=2
        )

        attn = (q.transpose(-2, -1) @ k) * self.scale
        attn = attn.softmax(dim=-1)
        x = (v @ attn.transpose(-2, -1)).view(B, C, H, W) + self.pe(v.reshape(B, C, H, W))
        x = self.proj(x)
        return x

可以发现，引入了自注意力机制，首先使用了卷积块提取特征，并分为两部分a,b,其中b会通过PSAblock进行注意力计算，最后再通过cat与a连接，并用一个卷积进一步提取特征。

而在PSAblock中，则是使用了多头注意力和一个前馈神经网络ffn，ffn是通过两个1*1的卷积层实现的最后通过超参数判断是否残差连接，最后返回结果。

总结：
相比于yolov8，主要将C2f改进为C3k2,并添加了一个注意力模块C2PSA