YOLO11改进 | 注意力机制 | 对密集和小目标友好的EVAblock 【完整代码】

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💡💡💡

本文介绍了一种基于全局显式集中式特征规则的集中式特征金字塔(CFP)检测方法。具体而言，我们首先提出了一种空间显式视觉中心方案，其中使用轻量级MLP来捕捉全局长距离依赖关系，并使用并行可学习视觉中心机制来捕捉输入图像的局部角区域。在此基础上，我们以自顶向下的方式对常用的特征金字塔提出了一个全局集中的规则，其中使用从最深层内特征获得的显式视觉中心信息。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. 将EVC添加到YOLO11中

2.1 EVC代码实现

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：Centralized Feature Pyramid for Object Detection——点击即可跳转

官方代码：官方代码仓库——点击即可跳转

2. 将EVC添加到YOLO11中

2.1 EVC代码实现

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

class Encoding(nn.Module):def __init__(self, in_channels, num_codes):super(Encoding, self).__init__()# init codewords and smoothing factorself.in_channels, self.num_codes = in_channels, num_codesnum_codes = 64std = 1. / ((num_codes * in_channels) ** 0.5)# [num_codes, channels]self.codewords = nn.Parameter(torch.empty(num_codes, in_channels, dtype=torch.float).uniform_(-std, std), requires_grad=True)# [num_codes]self.scale = nn.Parameter(torch.empty(num_codes, dtype=torch.float).uniform_(-1, 0), requires_grad=True)@staticmethoddef scaled_l2(x, codewords, scale):num_codes, in_channels = codewords.size()b = x.size(0)expanded_x = x.unsqueeze(2).expand((b, x.size(1), num_codes, in_channels))# ---处理codebook (num_code, c1)reshaped_codewords = codewords.view((1, 1, num_codes, in_channels))# 把scale从1, num_code变成   batch, c2, N, num_codesreshaped_scale = scale.view((1, 1, num_codes))  # N, num_codes# ---计算rik = z1 - d  # b, N, num_codesscaled_l2_norm = reshaped_scale * (expanded_x - reshaped_codewords).pow(2).sum(dim=3)return scaled_l2_norm@staticmethoddef aggregate(assignment_weights, x, codewords):num_codes, in_channels = codewords.size()# ---处理codebookreshaped_codewords = codewords.view((1, 1, num_codes, in_channels))b = x.size(0)# ---处理特征向量x b, c1, Nexpanded_x = x.unsqueeze(2).expand((b, x.size(1), num_codes, in_channels))# 变换rei  b, N, num_codes,-assignment_weights = assignment_weights.unsqueeze(3)  # b, N, num_codes,# ---开始计算eik,必须在Rei计算完之后encoded_feat = (assignment_weights * (expanded_x - reshaped_codewords)).sum(1)return encoded_featdef forward(self, x):assert x.dim() == 4 and x.size(1) == self.in_channelsb, in_channels, w, h = x.size()# [batch_size, height x width, channels]x = x.view(b, self.in_channels, -1).transpose(1, 2).contiguous()# assignment_weights: [batch_size, channels, num_codes]assignment_weights = torch.softmax(self.scaled_l2(x, self.codewords, self.scale), dim=2)# aggregateencoded_feat = self.aggregate(assignment_weights, x, self.codewords)return encoded_featclass Mlp(nn.Module):"""Implementation of MLP with 1*1 convolutions. Input: tensor with shape [B, C, H, W]"""def __init__(self, in_features, hidden_features=None,out_features=None, act_layer=nn.GELU, drop=0.):super().__init__()out_features = out_features or in_featureshidden_features = hidden_features or in_featuresself.fc1 = nn.Conv2d(in_features, hidden_features, 1)self.act = act_layer()self.fc2 = nn.Conv2d(hidden_features, out_features, 1)self.drop = nn.Dropout(drop)self.apply(self._init_weights)def _init_weights(self, m):if isinstance(m, nn.Conv2d):trunc_normal_(m.weight, std=.02)if m.bias is not None:nn.init.constant_(m.bias, 0)def forward(self, x):x = self.fc1(x)x = self.act(x)x = self.drop(x)x = self.fc2(x)x = self.drop(x)return x#  1*1 3*3 1*1
class ConvBlock(nn.Module):def __init__(self, in_channels, out_channels, stride=1, res_conv=False, act_layer=nn.SiLU, groups=1,norm_layer=partial(nn.BatchNorm2d, eps=1e-6)):super(ConvBlock, self).__init__()self.in_channels = in_channelsexpansion = 4c = out_channels // expansionself.conv1 = Conv(in_channels, c, act=nn.SiLU())self.conv2 = Conv(c, c, k=3, s=stride, g=groups, act=nn.SiLU())self.conv3 = Conv(c, out_channels, 1, act=False)self.act3 = act_layer(inplace=True)if res_conv:self.residual_conv = nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=1, padding=0, bias=False)self.residual_bn = norm_layer(out_channels)self.res_conv = res_convdef zero_init_last_bn(self):nn.init.zeros_(self.bn3.weight)def forward(self, x, return_x_2=True):residual = xx = self.conv1(x)x2 = self.conv2(x)  # if x_t_r is None else self.conv2(x + x_t_r)x = self.conv3(x2)if self.res_conv:residual = self.residual_conv(residual)residual = self.residual_bn(residual)x += residualx = self.act3(x)if return_x_2:return x, x2else:return xclass Mean(nn.Module):def __init__(self, dim, keep_dim=False):super(Mean, self).__init__()self.dim = dimself.keep_dim = keep_dimdef forward(self, input):return input.mean(self.dim, self.keep_dim)class LVCBlock(nn.Module):def __init__(self, in_channels, out_channels, num_codes, channel_ratio=0.25, base_channel=64):super(LVCBlock, self).__init__()self.out_channels = out_channelsself.num_codes = num_codesnum_codes = 64self.conv_1 = ConvBlock(in_channels=in_channels, out_channels=in_channels, res_conv=True, stride=1)self.LVC = nn.Sequential(Conv(in_channels, in_channels, 1, act=nn.SiLU()),Encoding(in_channels=in_channels, num_codes=num_codes),nn.BatchNorm1d(num_codes),nn.SiLU(inplace=True),Mean(dim=1))self.fc = nn.Sequential(nn.Linear(in_channels, in_channels), nn.Sigmoid())def forward(self, x):x = self.conv_1(x, return_x_2=False)en = self.LVC(x)gam = self.fc(en)b, in_channels, _, _ = x.size()y = gam.view(b, in_channels, 1, 1)x = F.relu_(x + x * y)return xclass GroupNorm(nn.GroupNorm):"""Group Normalization with 1 group.Input: tensor in shape [B, C, H, W]"""def __init__(self, num_channels, **kwargs):super().__init__(1, num_channels, **kwargs)class DWConv_LMLP(nn.Module):"""Depthwise Conv + Conv"""def __init__(self, in_channels, out_channels, ksize, stride=1, act="silu"):super().__init__()self.dconv = Conv(in_channels,in_channels,k=ksize,s=stride,g=in_channels,)self.pconv = Conv(in_channels, out_channels, k=1, s=1, g=1)def forward(self, x):x = self.dconv(x)return self.pconv(x)# LightMLPBlock
class LightMLPBlock(nn.Module):def __init__(self, in_channels, out_channels, ksize=1, stride=1, act="silu",mlp_ratio=4., drop=0., act_layer=nn.GELU,use_layer_scale=True, layer_scale_init_value=1e-5, drop_path=0.,norm_layer=GroupNorm):  # act_layer=nn.GELU,super().__init__()self.dw = DWConv_LMLP(in_channels, out_channels, ksize=1, stride=1, act="silu")self.linear = nn.Linear(out_channels, out_channels)  # learnable position embeddingself.out_channels = out_channelsself.norm1 = norm_layer(in_channels)self.norm2 = norm_layer(in_channels)mlp_hidden_dim = int(in_channels * mlp_ratio)self.mlp = Mlp(in_features=in_channels, hidden_features=mlp_hidden_dim, act_layer=nn.GELU,drop=drop)self.drop_path = DropPath(drop_path) if drop_path > 0. \else nn.Identity()self.use_layer_scale = use_layer_scaleif use_layer_scale:self.layer_scale_1 = nn.Parameter(layer_scale_init_value * torch.ones(out_channels), requires_grad=True)self.layer_scale_2 = nn.Parameter(layer_scale_init_value * torch.ones(out_channels), requires_grad=True)def forward(self, x):if self.use_layer_scale:x = x + self.drop_path(self.layer_scale_1.unsqueeze(-1).unsqueeze(-1) * self.dw(self.norm1(x)))x = x + self.drop_path(self.layer_scale_2.unsqueeze(-1).unsqueeze(-1) * self.mlp(self.norm2(x)))else:x = x + self.drop_path(self.dw(self.norm1(x)))x = x + self.drop_path(self.mlp(self.norm2(x)))return x# EVCBlock
class EVCBlock(nn.Module):def __init__(self, in_channels, out_channels, channel_ratio=4, base_channel=16):super().__init__()expansion = 2ch = out_channels * expansion# Stem stage: get the feature maps by conv block (copied form resnet.py) 进入conformer框架之前的处理self.conv1 = Conv(in_channels, in_channels, k=3, act=nn.SiLU())self.maxpool = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)  # 1 / 4 [56, 56]# LVCself.lvc = LVCBlock(in_channels=in_channels, out_channels=out_channels, num_codes=64)  # c1值暂时未定# LightMLPBlockself.l_MLP = LightMLPBlock(in_channels, out_channels, ksize=3, stride=1, act="silu", act_layer=nn.GELU,mlp_ratio=4., drop=0.,use_layer_scale=True, layer_scale_init_value=1e-5, drop_path=0.,norm_layer=GroupNorm)self.cnv1 = nn.Conv2d(ch, out_channels, kernel_size=1, stride=1, padding=0)def forward(self, x):x1 = self.maxpool((self.conv1(x)))# LVCBlockx_lvc = self.lvc(x1)# LightMLPBlockx_lmlp = self.l_MLP(x1)# concatx = torch.cat((x_lvc, x_lmlp), dim=1)x = self.cnv1(x)return x

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

关键步骤三：在/ultralytics/ultralytics/cfg/models/11下面新建文件yolo11_EVC.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 GFLOPss: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPsm: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPsl: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPsx: [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, 1, EVCBlock, [ 1024 ] ]- [[-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, 14], 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)- [[17, 20, 23], 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 GFLOPss: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPsm: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPsl: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPsx: [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, 1, EVCBlock, [ 1024 ] ]- [[-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, 14], 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)- [[17, 20, 23], 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 GFLOPss: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPsm: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPsl: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPsx: [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, 1, EVCBlock, [ 1024 ] ]- [[-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, 14], 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)- [[17, 20, 23], 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task.py的parse_model函数中进行注册，

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 EVCBlock,

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_EVC.yaml的路径即可

from ultralytics import YOLO
import warnings
warnings.filterwarnings('ignore')
from pathlib import Pathif __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 modelresults = 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                                       arguments0                  -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         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']12                  -1  1   1666240  ultralytics.nn.modules.block.EVCBlock        [256, 256]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, 14]  1         0  ultralytics.nn.modules.conv.Concat           [1]20                  -1  1     86720  ultralytics.nn.modules.block.C3k2            [192, 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        [17, 20, 23]  1    464912  ultralytics.nn.modules.head.Detect           [80, [64, 128, 256]]
YOLO11_EVCBlock summary: 372 layers, 4,290,320 parameters, 4,290,304 gradients, 11.6 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。