YOLO11改进 | 注意力机制 | 用于增强小目标感受野的RFEM

秋招面试专栏推荐 ：深度学习算法工程师面试问题总结【百面算法工程师】——点击即可跳转

💡💡💡本专栏所有程序均经过测试，可成功执行💡💡💡

近年来，基于深度学习的人脸检测算法取得了很大进步。这些算法大致可以分为两类，即类似于Faster R-CNN的两阶段检测器和类似于YOLO的一阶段检测器。由于在一阶段检测器中准确性和速度之间有更好的平衡，因此它们被广泛应用于许多应用中。本文介绍了一个名为RFE的感受野增强模块，用于增强小目标的感受野。文章在介绍主要的原理后，将手把手教学如何进行模块的代码添加和修改，并将修改后的完整代码放在文章的最后，方便大家一键运行，小白也可轻松上手实践。以帮助您更好地学习深度学习目标检测YOLO系列的挑战。

专栏地址：YOLO11入门 + 改进涨点——点击即可跳转欢迎订阅

1. 论文

2. RFEM的代码实现

2.1 将RFEM添加到YOLO11中

2.2 更改init.py文件

2.3 添加yaml文件

2.4 在task.py中进行注册

2.5 执行程序

3.修改后的网络结构图

4. 完整代码分享

5. GFLOPs

6. 进阶

7.总结

1. 论文

论文地址：YOLO-FaceV2: A Scale and Occlusion Aware Face Detector——点击即可跳转

官方代码：官方代码仓库——点击即可跳转

2. RFEM的代码实现

2.1 将RFEM添加到YOLO11中

关键步骤一: 将下面代码粘贴到在/ultralytics/ultralytics/nn/modules/block.py中


class CBLinear(nn.Module):
    """CBLinear."""

    def __init__(self, c1, c2s, k=1, s=1, p=None, g=1):
        """Initializes the CBLinear module, passing inputs unchanged."""
        super(CBLinear, self).__init__()
        self.c2s = c2s
        self.conv = nn.Conv2d(c1, sum(c2s), k, s, autopad(k, p), groups=g, bias=True)

    def forward(self, x):
        """Forward pass through CBLinear layer."""
        outs = self.conv(x).split(self.c2s, dim=1)
        return outs


class CBFuse(nn.Module):
    """CBFuse."""

    def __init__(self, idx):
        """Initializes CBFuse module with layer index for selective feature fusion."""
        super(CBFuse, self).__init__()
        self.idx = idx

    def forward(self, xs):
        """Forward pass through CBFuse layer."""
        target_size = xs[-1].shape[2:]
        res = [F.interpolate(x[self.idx[i]], size=target_size, mode="nearest") for i, x in enumerate(xs[:-1])]
        out = torch.sum(torch.stack(res + xs[-1:]), dim=0)
        return out

class TridentBlock(nn.Module):
    def __init__(self, c1, c2, stride=1, c=False, e=0.5, padding=None, dilate=None, bias=False):
        super(TridentBlock, self).__init__()
        if padding is None:
            padding = [1, 2, 3]
        if dilate is None:
            dilate = [1, 2, 3]
        self.stride = stride
        self.c = c
        c_ = int(c2 * e)
        self.padding = padding
        self.dilate = dilate
        self.share_weightconv1 = nn.Parameter(torch.Tensor(c_, c1, 1, 1))
        self.share_weightconv2 = nn.Parameter(torch.Tensor(c2, c_, 3, 3))

        self.bn1 = nn.BatchNorm2d(c_)
        self.bn2 = nn.BatchNorm2d(c2)

        self.act = nn.SiLU()

        nn.init.kaiming_uniform_(self.share_weightconv1, nonlinearity="relu")
        nn.init.kaiming_uniform_(self.share_weightconv2, nonlinearity="relu")

        if bias:
            self.bias = nn.Parameter(torch.Tensor(c2))
        else:
            self.bias = None

        if self.bias is not None:
            nn.init.constant_(self.bias, 0)

    def forward_for_small(self, x):
        residual = x
        out = nn.functional.conv2d(x, self.share_weightconv1, bias=self.bias)
        out = self.bn1(out)
        out = self.act(out)

        out = nn.functional.conv2d(out, self.share_weightconv2, bias=self.bias, stride=self.stride,
                                   padding=self.padding[0],
                                   dilation=self.dilate[0])
        out = self.bn2(out)
        out += residual
        out = self.act(out)

        return out

    def forward_for_middle(self, x):
        residual = x
        out = nn.functional.conv2d(x, self.share_weightconv1, bias=self.bias)
        out = self.bn1(out)
        out = self.act(out)

        out = nn.functional.conv2d(out, self.share_weightconv2, bias=self.bias, stride=self.stride,
                                   padding=self.padding[1],
                                   dilation=self.dilate[1])
        out = self.bn2(out)
        out += residual
        out = self.act(out)

        return out

    def forward_for_big(self, x):
        residual = x
        out = nn.functional.conv2d(x, self.share_weightconv1, bias=self.bias)
        out = self.bn1(out)
        out = self.act(out)

        out = nn.functional.conv2d(out, self.share_weightconv2, bias=self.bias, stride=self.stride,
                                   padding=self.padding[2],
                                   dilation=self.dilate[2])
        out = self.bn2(out)
        out += residual
        out = self.act(out)

        return out

    def forward(self, x):
        xm = x
        base_feat = []
        if self.c is not False:
            x1 = self.forward_for_small(x)
            x2 = self.forward_for_middle(x)
            x3 = self.forward_for_big(x)
        else:
            x1 = self.forward_for_small(xm[0])
            x2 = self.forward_for_middle(xm[1])
            x3 = self.forward_for_big(xm[2])

        base_feat.append(x1)
        base_feat.append(x2)
        base_feat.append(x3)

        return base_feat


class RFEM(nn.Module):
    def __init__(self, c1, c2, n=1, e=0.5, stride=1):
        super(RFEM, self).__init__()
        c = True
        layers = [TridentBlock(c1, c2, stride=stride, c=c, e=e)]
        c1 = c2
        for i in range(1, n):
            layers.append(TridentBlock(c1, c2))
        self.layer = nn.Sequential(*layers)
        self.bn = nn.BatchNorm2d(c2)
        self.act = nn.SiLU()

    def forward(self, x):
        out = self.layer(x)
        out = out[0] + out[1] + out[2] + x
        out = self.act(self.bn(out))
        return out

2.2 更改init.py文件

关键步骤二：修改modules文件夹下的__init__.py文件，先导入函数

然后在下面的__all__中声明函数

2.3 添加yaml文件

关键步骤四：在/ultralytics/ultralytics/cfg/models/11下面新建文件yolo11_RFEM.yaml文件，粘贴下面的内容

目标检测

# 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
  - [-1, 1, RFEM, [1024]]

# 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)

语义分割

# 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
  - [-1, 1, RFEM, [1024]]

# 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, Segment, [nc, 32, 256]] # Segment(P3, P4, P5)

旋转目标检测

# 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
  - [-1, 1, RFEM, [1024]]

# 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, OBB, [nc, 1]] # Detect(P3, P4, P5)

温馨提示：本文只是对yolo11基础上添加模块，如果要对yolo11n/l/m/x进行添加则只需要指定对应的depth_multiple 和 width_multiple。

# YOLO11n
depth_multiple: 0.50  # model depth multiple
width_multiple: 0.25  # layer channel multiple
max_channel：1024
 
# YOLO11s
depth_multiple: 0.50  # model depth multiple
width_multiple: 0.50  # layer channel multiple
max_channel：1024
 
# YOLO11m
depth_multiple: 0.50  # model depth multiple
width_multiple: 1.00  # layer channel multiple
max_channel：512
 
# YOLO11l 
depth_multiple: 1.00  # model depth multiple
width_multiple: 1.00  # layer channel multiple
max_channel：512 
 
# YOLO11x
depth_multiple: 1.00  # model depth multiple
width_multiple: 1.50 # layer channel multiple
max_channel：512

2.4 在task.py中进行注册

关键步骤四：在parse_model函数中进行注册，添加RFEM,

先在task.py导入函数

然后在task.py文件下找到parse_model这个函数，如下图，添加RFEM,

2.5 执行程序

关键步骤五：在ultralytics文件中新建train.py，将model的参数路径设置为yolo11_RFEM.yaml的路径即可

建议大家写绝对路径，确保一定能找到

from ultralytics import YOLO
import warnings
warnings.filterwarnings('ignore')
from pathlib import Path
 
if __name__ == '__main__':
 
 
    # 加载模型
    model = YOLO("ultralytics/cfg/11/yolo11.yaml")  # 你要选择的模型yaml文件地址
    # Use the model
    results = model.train(data=r"你的数据集的yaml文件地址",
                          epochs=100, batch=16, imgsz=640, workers=4, name=Path(model.cfg).stem)  # 训练模型

🚀运行程序，如果出现下面的内容则说明添加成功🚀

                   from  n    params  module                                       arguments
  0                  -1  1       464  ultralytics.nn.modules.conv.Conv             [3, 16, 3, 2]
  1                  -1  1      4672  ultralytics.nn.modules.conv.Conv             [16, 32, 3, 2]
  2                  -1  1      6640  ultralytics.nn.modules.block.C3k2            [32, 64, 1, False, 0.25]
  3                  -1  1     36992  ultralytics.nn.modules.conv.Conv             [64, 64, 3, 2]
  4                  -1  1     26080  ultralytics.nn.modules.block.C3k2            [64, 128, 1, False, 0.25]
  5                  -1  1    147712  ultralytics.nn.modules.conv.Conv             [128, 128, 3, 2]
  6                  -1  1     87040  ultralytics.nn.modules.block.C3k2            [128, 128, 1, True]
  7                  -1  1    295424  ultralytics.nn.modules.conv.Conv             [128, 256, 3, 2]
  8                  -1  1    346112  ultralytics.nn.modules.block.C3k2            [256, 256, 1, True]
  9                  -1  1    164608  ultralytics.nn.modules.block.SPPF            [256, 256, 5]
 10                  -1  1    249728  ultralytics.nn.modules.block.C2PSA           [256, 256, 1]
 11                  -1  1    328960  ultralytics.nn.modules.block.RFEM            [256, 256]
 12                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']
 13             [-1, 6]  1         0  ultralytics.nn.modules.conv.Concat           [1]
 14                  -1  1    111296  ultralytics.nn.modules.block.C3k2            [384, 128, 1, False]
 15                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']
 16             [-1, 4]  1         0  ultralytics.nn.modules.conv.Concat           [1]
 17                  -1  1     32096  ultralytics.nn.modules.block.C3k2            [256, 64, 1, False]
 18                  -1  1     36992  ultralytics.nn.modules.conv.Conv             [64, 64, 3, 2]
 19            [-1, 13]  1         0  ultralytics.nn.modules.conv.Concat           [1]
 20                  -1  1    119488  ultralytics.nn.modules.block.C3k2            [448, 128, 1, False]
 21                  -1  1    147712  ultralytics.nn.modules.conv.Conv             [128, 128, 3, 2]
 22            [-1, 10]  1         0  ultralytics.nn.modules.conv.Concat           [1]
 23                  -1  1    378880  ultralytics.nn.modules.block.C3k2            [384, 256, 1, True]
 24        [16, 19, 22]  1   1310848  ultralytics.nn.modules.head.Detect           [80, [256, 448, 384]]
YOLO11_RFEM summary: 327 layers, 3,831,744 parameters, 3,831,728 gradients, 11.3 GFLOPs

3.修改后的网络结构图

4. 完整代码分享

这个后期补充吧~，先按照步骤来即可

5. GFLOPs

关于GFLOPs的计算方式可以查看：百面算法工程师 | 卷积基础知识——Convolution

未改进的YOLO11n GFLOPs

改进后的GFLOPs

6. 进阶

可以与其他的注意力机制或者损失函数等结合，进一步提升检测效果

7.总结

通过以上的改进方法，我们成功提升了模型的表现。这只是一个开始，未来还有更多优化和技术深挖的空间。在这里，我想隆重向大家推荐我的专栏——《YOLO11改进有效涨点》。这个专栏专注于前沿的深度学习技术，特别是目标检测领域的最新进展，不仅包含对YOLO11的深入解析和改进策略，还会定期更新来自各大顶会（如CVPR、NeurIPS等）的论文复现和实战分享。