企业官网建设流程全解析

💡💡💡本专栏所有程序均经过测试，可成功执行💡💡💡

本文给大家带来的教程是将YOLO26的特征融合替换为LCA来提取特征。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：YOLO26改进-论文涨点——点击跳转看所有内容，关注不迷路！

目录

1.论文

2. LCA代码实现

2.1 将LCA添加到YOLO26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. 完整代码分享

4. GFLOPs

5. 进阶

6.总结

1.论文

论文地址：HVI: ANewColor Space for Low-light Image Enhancement

官方代码：官方代码仓库点击即可跳转

2.LCA代码实现

2.1 将LCA添加到YOLO26中

关键步骤一：在ultralytics\ultralytics\nn\modules下面新建文件夹models，在文件夹下新建LCA.py，粘贴下面代码

import torch import torch.nn as nn import torch.functional as F from einops import rearrange from ultralytics.nn.modules.conv import Conv class LayerNorm(nn.Module): r""" LayerNorm that supports two data formats: channels_last (default) or channels_first. The ordering of the dimensions in the inputs. channels_last corresponds to inputs with shape (batch_size, height, width, channels) while channels_first corresponds to inputs with shape (batch_size, channels, height, width). """ def __init__(self, normalized_shape, eps=1e-6, data_format="channels_first"): super().__init__() self.weight = nn.Parameter(torch.ones(normalized_shape)) self.bias = nn.Parameter(torch.zeros(normalized_shape)) self.eps = eps self.data_format = data_format if self.data_format not in ["channels_last", "channels_first"]: raise NotImplementedError self.normalized_shape = (normalized_shape, ) def forward(self, x): if self.data_format == "channels_last": return F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps) elif self.data_format == "channels_first": u = x.mean(1, keepdim=True) s = (x - u).pow(2).mean(1, keepdim=True) x = (x - u) / torch.sqrt(s + self.eps) x = self.weight[:, None, None] * x + self.bias[:, None, None] return x class CAB(nn.Module): def __init__(self, dim, num_heads, bias): super(CAB, self).__init__() self.num_heads = num_heads self.temperature = nn.Parameter(torch.ones(num_heads, 1, 1)) self.q = nn.Conv2d(dim, dim, kernel_size=1, bias=bias) self.q_dwconv = nn.Conv2d(dim, dim, kernel_size=3, stride=1, padding=1, groups=dim, bias=bias) self.kv = nn.Conv2d(dim, dim*2, kernel_size=1, bias=bias) self.kv_dwconv = nn.Conv2d(dim*2, dim*2, kernel_size=3, stride=1, padding=1, groups=dim*2, bias=bias) self.project_out = nn.Conv2d(dim, dim, kernel_size=1, bias=bias) def forward(self, x, y): b, c, h, w = x.shape q = self.q_dwconv(self.q(x)) kv = self.kv_dwconv(self.kv(y)) k, v = kv.chunk(2, dim=1) q = rearrange(q, 'b (head c) h w -> b head c (h w)', head=self.num_heads) k = rearrange(k, 'b (head c) h w -> b head c (h w)', head=self.num_heads) v = rearrange(v, 'b (head c) h w -> b head c (h w)', head=self.num_heads) q = torch.nn.functional.normalize(q, dim=-1) k = torch.nn.functional.normalize(k, dim=-1) attn = (q @ k.transpose(-2, -1)) * self.temperature attn = nn.functional.softmax(attn,dim=-1) out = (attn @ v) out = rearrange(out, 'b head c (h w) -> b (head c) h w', head=self.num_heads, h=h, w=w) out = self.project_out(out) return out class IEL(nn.Module): def __init__(self, dim, ffn_expansion_factor=2.66, bias=False): super(IEL, self).__init__() hidden_features = int(dim*ffn_expansion_factor) self.project_in = nn.Conv2d(dim, hidden_features*2, kernel_size=1, bias=bias) self.dwconv = nn.Conv2d(hidden_features*2, hidden_features*2, kernel_size=3, stride=1, padding=1, groups=hidden_features*2, bias=bias) self.dwconv1 = nn.Conv2d(hidden_features, hidden_features, kernel_size=3, stride=1, padding=1, groups=hidden_features, bias=bias) self.dwconv2 = nn.Conv2d(hidden_features, hidden_features, kernel_size=3, stride=1, padding=1, groups=hidden_features, bias=bias) self.project_out = nn.Conv2d(hidden_features, dim, kernel_size=1, bias=bias) self.Tanh = nn.Tanh() def forward(self, x): x = self.project_in(x) x1, x2 = self.dwconv(x).chunk(2, dim=1) x1 = self.Tanh(self.dwconv1(x1)) + x1 x2 = self.Tanh(self.dwconv2(x2)) + x2 x = x1 * x2 x = self.project_out(x) return x class LCA(nn.Module): def __init__(self, in_dim, out_dim, num_heads=8, bias=False): super(LCA, self).__init__() self.norm = LayerNorm(out_dim) self.gdfn = IEL(out_dim) self.ffn = CAB(out_dim, num_heads, bias=bias) self.conv1x1 = nn.ModuleList([]) for i in in_dim: if i != out_dim: self.conv1x1.append(Conv(i, out_dim, 1)) else: self.conv1x1.append(nn.Identity()) def forward(self, inputs): x, y = inputs x = self.conv1x1[0](x) y = self.conv1x1[1](y) x = x + self.ffn(self.norm(x),self.norm(y)) x = x + self.gdfn(self.norm(x)) return x

2.2 更改init.py文件

关键步骤二：在文件ultralytics\ultralytics\nn\modules\models文件夹下新建__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/26下面新建文件yolo26_LCA.yaml文件，粘贴下面的内容

• 目标检测

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license # Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs # Model docs: https://docs.ultralytics.com/models/yolo26 # Task docs: https://docs.ultralytics.com/tasks/detect # Parameters nc: 80 # number of classes end2end: True # whether to use end-to-end mode reg_max: 1 # DFL bins scales: # model compound scaling constants, i.e. 'model=yolo26n.yaml' will call yolo26.yaml with scale 'n' # [depth, width, max_channels] n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs # YOLO26n 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]] # 2-P2/4 - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - [-1, 2, C3k2, [512, False, 0.25]] # 4-P3/8 - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - [-1, 2, C3k2, [512, True]] # 6-P4/16 - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - [-1, 2, C3k2, [1024, True]] # 8-P5/32 - [-1, 1, SPPF, [1024, 5, 3, True]] # 9-P5/32 - [-1, 2, C2PSA, [1024]] # 10-P5/32 # YOLO26n head head: - [-1, 1, nn.Upsample, [None, 2, "nearest"]] # 11-P4/16 - [[-1, 6], 1, LCA, [512]] # 12-P4/16 - [-1, 2, C3k2, [512, True]] # 13-P4/16 - [-1, 1, nn.Upsample, [None, 2, "nearest"]] # 14-P3/8 - [[-1, 4], 1, LCA, [256]] # 15-P3/8 - [-1, 2, C3k2, [256, True]] # 16-P3/8 - [-1, 1, Conv, [256, 3, 2]] # 17-P4/16 - [[-1, 13], 1, LCA, [512]] # 18-P4/16 - [-1, 2, C3k2, [512, True]] # 19-P4/16 - [-1, 1, Conv, [512, 3, 2]] # 20-P5/32 - [[-1, 10], 1, LCA, [1024]] # 21-P5/32 - [-1, 1, C3k2, [1024, True, 0.5, True]] # 22-P5/32 - [[16, 19, 22], 1, Detect, [nc]] # 23-P3/8,P4/16,P5/32

• 语义分割

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license # Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs # Model docs: https://docs.ultralytics.com/models/yolo26 # Task docs: https://docs.ultralytics.com/tasks/detect # Parameters nc: 80 # number of classes end2end: True # whether to use end-to-end mode reg_max: 1 # DFL bins scales: # model compound scaling constants, i.e. 'model=yolo26n.yaml' will call yolo26.yaml with scale 'n' # [depth, width, max_channels] n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs # YOLO26n 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]] # 2-P2/4 - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - [-1, 2, C3k2, [512, False, 0.25]] # 4-P3/8 - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - [-1, 2, C3k2, [512, True]] # 6-P4/16 - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - [-1, 2, C3k2, [1024, True]] # 8-P5/32 - [-1, 1, SPPF, [1024, 5, 3, True]] # 9-P5/32 - [-1, 2, C2PSA, [1024]] # 10-P5/32 # YOLO26n head head: - [-1, 1, nn.Upsample, [None, 2, "nearest"]] # 11-P4/16 - [[-1, 6], 1, LCA, [512]] # 12-P4/16 - [-1, 2, C3k2, [512, True]] # 13-P4/16 - [-1, 1, nn.Upsample, [None, 2, "nearest"]] # 14-P3/8 - [[-1, 4], 1, LCA, [256]] # 15-P3/8 - [-1, 2, C3k2, [256, True]] # 16-P3/8 - [-1, 1, Conv, [256, 3, 2]] # 17-P4/16 - [[-1, 13], 1, LCA, [512]] # 18-P4/16 - [-1, 2, C3k2, [512, True]] # 19-P4/16 - [-1, 1, Conv, [512, 3, 2]] # 20-P5/32 - [[-1, 10], 1, LCA, [1024]] # 21-P5/32 - [-1, 1, C3k2, [1024, True, 0.5, True]] # 22-P5/32 - [[16, 19, 22], 1, Segment, [nc, 32, 256]]

• 旋转目标检测

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license # Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs # Model docs: https://docs.ultralytics.com/models/yolo26 # Task docs: https://docs.ultralytics.com/tasks/detect # Parameters nc: 80 # number of classes end2end: True # whether to use end-to-end mode reg_max: 1 # DFL bins scales: # model compound scaling constants, i.e. 'model=yolo26n.yaml' will call yolo26.yaml with scale 'n' # [depth, width, max_channels] n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs # YOLO26n 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]] # 2-P2/4 - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - [-1, 2, C3k2, [512, False, 0.25]] # 4-P3/8 - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - [-1, 2, C3k2, [512, True]] # 6-P4/16 - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - [-1, 2, C3k2, [1024, True]] # 8-P5/32 - [-1, 1, SPPF, [1024, 5, 3, True]] # 9-P5/32 - [-1, 2, C2PSA, [1024]] # 10-P5/32 # YOLO26n head head: - [-1, 1, nn.Upsample, [None, 2, "nearest"]] # 11-P4/16 - [[-1, 6], 1, LCA, [512]] # 12-P4/16 - [-1, 2, C3k2, [512, True]] # 13-P4/16 - [-1, 1, nn.Upsample, [None, 2, "nearest"]] # 14-P3/8 - [[-1, 4], 1, LCA, [256]] # 15-P3/8 - [-1, 2, C3k2, [256, True]] # 16-P3/8 - [-1, 1, Conv, [256, 3, 2]] # 17-P4/16 - [[-1, 13], 1, LCA, [512]] # 18-P4/16 - [-1, 2, C3k2, [512, True]] # 19-P4/16 - [-1, 1, Conv, [512, 3, 2]] # 20-P5/32 - [[-1, 10], 1, LCA, [1024]] # 21-P5/32 - [-1, 1, C3k2, [1024, True, 0.5, True]] # 22-P5/32 - [[16, 19, 22], 1, OBB, [nc, 1]]

温馨提示：本文只是对yolo26基础上添加模块，如果要对yolo26 n/l/m/x进行添加则只需要指定对应的depth_multiple 和 width_multiple

end2end: True # whether to use end-to-end mode reg_max: 1 # DFL bins scales: # model compound scaling constants, i.e. 'model=yolo26n.yaml' will call yolo26.yaml with scale 'n' # [depth, width, max_channels] n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs

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LCA

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LCA

elif m in frozenset({LCA}): c1, c2 = [ch[fi] for fi in f], args[0] c2 = make_divisible(min(c2, max_channels) * width, 8) args = [c1, c2, *args[1:]]

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yolo26_LCA.yaml的路径即可 【注意是在外边的Ultralytics下新建train.py】

from ultralytics import YOLO import warnings warnings.filterwarnings('ignore') from pathlib import Path if __name__ == '__main__': # 加载模型 model = YOLO("ultralytics/cfg/26/yolo26.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, 3, True] 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, 6] 1 245080 ultralytics.nn.models.LCA.LCA [[256, 128], 128] 13 -1 1 87040 ultralytics.nn.modules.block.C3k2 [128, 128, 1, True] 14 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 15 [-1, 4] 1 73648 ultralytics.nn.models.LCA.LCA [[128, 128], 64] 16 -1 1 22016 ultralytics.nn.modules.block.C3k2 [64, 64, 1, True] 17 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2] 18 [-1, 13] 1 220504 ultralytics.nn.models.LCA.LCA [[64, 128], 128] 19 -1 1 87040 ultralytics.nn.modules.block.C3k2 [128, 128, 1, True] 20 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2] 21 [-1, 10] 1 849576 ultralytics.nn.models.LCA.LCA [[128, 256], 256] 22 -1 1 430336 ultralytics.nn.modules.block.C3k2 [256, 256, 1, True, 0.5, True] 23 [16, 19, 22] 1 309656 ultralytics.nn.modules.head.Detect [80, 1, True, [64, 128, 256]] YOLO26_LCA summary: 317 layers, 3,875,072 parameters, 3,875,072 gradients, 8.9 GFLOPs

3. 完整代码分享

主页侧边

4. 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YOLO26n GFLOPs

​改进后的GFLOPs

5. 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

6.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——<专栏地址：YOLO26改进-论文涨点——点击跳转看所有内容，关注不迷路！>。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YOLO26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。

为什么订阅我的专栏？——专栏地址：YOLO26改进-论文涨点——点击跳转看所有内容，关注不迷路！

1. 前沿技术解读：专栏不仅限于YOLO系列的改进，还会涵盖各类主流与新兴网络的最新研究成果，帮助你紧跟技术潮流。

2. 详尽的实践分享：所有内容实践性也极强。每次更新都会附带代码和具体的改进步骤，保证每位读者都能迅速上手。

3. 问题互动与答疑：订阅我的专栏后，你将可以随时向我提问，获取及时的答疑。

4. 实时更新，紧跟行业动态：不定期发布来自全球顶会的最新研究方向和复现实验报告，让你时刻走在技术前沿。

专栏适合人群：

• 对目标检测、YOLO系列网络有深厚兴趣的同学

• 希望在用YOLO算法写论文的同学

• 对YOLO算法感兴趣的同学等

​