在深度学习中，特征提取是关键环节。传统的卷积神经网络（CNN）通过卷积层提取图像特征，但在处理复杂图像时，单一的频域信息可能不足以捕获所有重要细节。为了解决这个问题，我们可以结合小波变换（DWT）和卷积操作，使用Down_wt卷积提高YOLOv11模型的精度。
1. Down_wt卷积概述
下图展示了Down_wt卷积的结构。通过Haar小波变换，该卷积模块实现了高效的特征提取和降采样。
Down_wt 模块的设计
Down_wt 模块的核心功能是执行小波变换，并将变换后的结果与卷积层结合。下面是模块的关键组成部分：
小波变换：使用 DWTForward 类进行小波变换，提取低频和高频成分。
特征拼接：将低频成分和三个高频成分（水平、垂直和对角）拼接在一起，形成新的输入。
卷积层：通过1x1卷积、批量归一化和ReLU激活函数处理拼接后的特征。
2. 安装Down_wt环境
第一：下载代码，并将其解压https://github.com/fbcotter/pytorch_wavelets
第二： 找到其路径pytorch_wavelets路径下使用 pip install . 安装包
第三：安装 PyWavelets pip install PyWavelets
3. Down_wt代码部分
import torch
import torch.nn as nn
from pytorch_wavelets import DWTForwardclass Down_wt(nn.Module):def __init__(self, in_ch, out_ch):super(Down_wt, self).__init__()self.wt = DWTForward(J=1, mode='zero', wave='haar')self.conv_bn_relu = nn.Sequential(nn.Conv2d(in_ch*4, out_ch, kernel_size=1, stride=1),nn.BatchNorm2d(out_ch),nn.ReLU(inplace=True),)def forward(self, x):yL, yH = self.wt(x)y_HL = yH[0][:,:,0,::]y_LH = yH[0][:,:,1,::]y_HH = yH[0][:,:,2,::]x = torch.cat([yL, y_HL, y_LH, y_HH], dim=1)x = self.conv_bn_relu(x)return xif __name__ =='__main__':Down_WT = Down_wt(256,256)#创建一个输入张量batch_size = 8input_tensor=torch.randn(batch_size, 256, 64, 64 )#运行模型并打印输入和输出的形状output_tensor =Down_WT(input_tensor)print("Input shape:",input_tensor.shape)print("0utput shape:",output_tensor.shape)4. 将Down_wt卷积引入到YOLOv11中
第一: 将下面的核心代码复制到D:\bilibili\model\YOLO11\ultralytics-main\ultralytics\nn路径下，如下图所示。
第二：在task.py中导入Down_wt包
第三：在task.py中的模型配置部分下面代码
elif m is Down_wt:args = [ch[f], c2]
第四：将模型配置文件复制到YOLOV11.YAMY文件中
# 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, Down_wt, [256, 3, 2]] # 3-P3/8- [-1, 2, C3k2, [512, False, 0.25]]- [-1, 1, Down_wt, [512, 3, 2]] # 5-P4/16- [-1, 2, C3k2, [512, True]]- [-1, 1, Down_wt, [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)
第五：运行成功，这里记住要把混合精度关了 amp=False
from ultralytics.models import NAS, RTDETR, SAM, YOLO, FastSAM, YOLOWorldif __name__=="__main__":# 使用自己的YOLOv11.yamy文件搭建模型并加载预训练权重训练模型model = YOLO(r"D:\bilibili\model\YOLO11\ultralytics-main\ultralytics\cfg\models\11\yolo11_HWG.yaml")\.load(r'D:\bilibili\model\YOLO11\ultralytics-main\yolo11n.pt') # build from YAML and transfer weightsresults = model.train(data=r'D:\bilibili\model\ultralytics-main\ultralytics\cfg\datasets\VOC_my.yaml',epochs=100, imgsz=640, batch=8, amp=False) 
