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💡💡💡
本文给大家带来的教程是将YOLO11的Conv替换为WTConv结构来融合特征。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：YOLO11入门 + 改进涨点——点击即可跳转 欢迎订阅
目录
1.论文
2. WTConv代码实现
2.1 将WTConv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：Wavelet Convolutions for Large Receptive Fields
官方代码：官方代码仓库点击——即可跳转
2. WTConv代码实现
2.1 将WTConv添加到YOLO11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WTConv.py，粘贴下面代码
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Function
import pywt
import pywt.data
def create_wavelet_filter(wave, in_size, out_size, type=torch.float):
w = pywt.Wavelet(wave)
dec_hi = torch.tensor(w.dec_hi[::-1], dtype=type)
dec_lo = torch.tensor(w.dec_lo[::-1], dtype=type)
dec_filters = torch.stack([dec_lo.unsqueeze(0) * dec_lo.unsqueeze(1),
dec_lo.unsqueeze(0) * dec_hi.unsqueeze(1),
dec_hi.unsqueeze(0) * dec_lo.unsqueeze(1),
dec_hi.unsqueeze(0) * dec_hi.unsqueeze(1)], dim=0)
dec_filters = dec_filters[:, None].repeat(in_size, 1, 1, 1)
rec_hi = torch.tensor(w.rec_hi[::-1], dtype=type).flip(dims=[0])
rec_lo = torch.tensor(w.rec_lo[::-1], dtype=type).flip(dims=[0])
rec_filters = torch.stack([rec_lo.unsqueeze(0) * rec_lo.unsqueeze(1),
rec_lo.unsqueeze(0) * rec_hi.unsqueeze(1),
rec_hi.unsqueeze(0) * rec_lo.unsqueeze(1),
rec_hi.unsqueeze(0) * rec_hi.unsqueeze(1)], dim=0)
rec_filters = rec_filters[:, None].repeat(out_size, 1, 1, 1)
return dec_filters, rec_filters
def wavelet_transform(x, filters):
b, c, h, w = x.shape
pad = (filters.shape[2] // 2 - 1, filters.shape[3] // 2 - 1)
x = F.conv2d(x, filters.to(x.dtype).to(x.device), stride=2, groups=c, padding=pad)
x = x.reshape(b, c, 4, h // 2, w // 2)
return x
def inverse_wavelet_transform(x, filters):
b, c, _, h_half, w_half = x.shape
pad = (filters.shape[2] // 2 - 1, filters.shape[3] // 2 - 1)
x = x.reshape(b, c * 4, h_half, w_half)
x = F.conv_transpose2d(x, filters.to(x.dtype).to(x.device), stride=2, groups=c, padding=pad)
return x
# Define the WaveletTransform class
class WaveletTransform(Function):
@staticmethod
def forward(ctx, input, filters):
ctx.filters = filters
with torch.no_grad():
x = wavelet_transform(input, filters)
return x
@staticmethod
def backward(ctx, grad_output):
grad = inverse_wavelet_transform(grad_output, ctx.filters)
return grad, None
# Define the InverseWaveletTransform class
class InverseWaveletTransform(Function):
@staticmethod
def forward(ctx, input, filters):
ctx.filters = filters
with torch.no_grad():
x = inverse_wavelet_transform(input, filters)
return x
@staticmethod
def backward(ctx, grad_output):
grad = wavelet_transform(grad_output, ctx.filters)
return grad, None
# Initialize the WaveletTransform
def wavelet_transform_init(filters):
def apply(input):
return WaveletTransform.apply(input, filters)
return apply
# Initialize the InverseWaveletTransform
def inverse_wavelet_transform_init(filters):
def apply(input):
return InverseWaveletTransform.apply(input, filters)
return apply
class WTConv2d(nn.Module):
def __init__(self, in_channels, out_channels, kernel_size=5, stride=1, bias=True, wt_levels=1, wt_type='db1'):
super(WTConv2d, self).__init__()
assert in_channels == out_channels
self.in_channels = in_channels
self.wt_levels = wt_levels
self.stride = stride
self.dilation = 1
self.wt_filter, self.iwt_filter = create_wavelet_filter(wt_type, in_channels, in_channels, torch.float)
self.wt_filter = nn.Parameter(self.wt_filter, requires_grad=False)
self.iwt_filter = nn.Parameter(self.iwt_filter, requires_grad=False)
self.wt_function = wavelet_transform_init(self.wt_filter)
self.iwt_function = inverse_wavelet_transform_init(self.iwt_filter)
self.base_conv = nn.Conv2d(in_channels, in_channels, kernel_size, padding='same', stride=1, dilation=1, groups=in_channels, bias=bias)
self.base_scale = _ScaleModule([1,in_channels,1,1])
self.wavelet_convs = nn.ModuleList(
[nn.Conv2d(in_channels*4, in_channels*4, kernel_size, padding='same', stride=1, dilation=1, groups=in_channels*4, bias=False) for _ in range(self.wt_levels)]
)
self.wavelet_scale = nn.ModuleList(
[_ScaleModule([1,in_channels*4,1,1], init_scale=0.1) for _ in range(self.wt_levels)]
)
if self.stride > 1:
self.stride_filter = nn.Parameter(torch.ones(in_channels, 1, 1, 1), requires_grad=False)
self.do_stride = lambda x_in: F.conv2d(x_in, self.stride_filter.to(x_in.dtype).to(x_in.device), bias=None, stride=self.stride, groups=in_channels)
else:
self.do_stride = None
def forward(self, x):
x_ll_in_levels = []
x_h_in_levels = []
shapes_in_levels = []
curr_x_ll = x
for i in range(self.wt_levels):
curr_shape = curr_x_ll.shape
shapes_in_levels.append(curr_shape)
if (curr_shape[2] % 2 > 0) or (curr_shape[3] % 2 > 0):
curr_pads = (0, curr_shape[3] % 2, 0, curr_shape[2] % 2)
curr_x_ll = F.pad(curr_x_ll, curr_pads)
curr_x = self.wt_function(curr_x_ll)
curr_x_ll = curr_x[:,:,0,:,:]
shape_x = curr_x.shape
curr_x_tag = curr_x.reshape(shape_x[0], shape_x[1] * 4, shape_x[3], shape_x[4])
curr_x_tag = self.wavelet_scale[i](self.wavelet_convs[i](curr_x_tag))
curr_x_tag = curr_x_tag.reshape(shape_x)
x_ll_in_levels.append(curr_x_tag[:,:,0,:,:])
x_h_in_levels.append(curr_x_tag[:,:,1:4,:,:])
next_x_ll = 0
for i in range(self.wt_levels-1, -1, -1):
curr_x_ll = x_ll_in_levels.pop()
curr_x_h = x_h_in_levels.pop()
curr_shape = shapes_in_levels.pop()
curr_x_ll = curr_x_ll + next_x_ll
curr_x = torch.cat([curr_x_ll.unsqueeze(2), curr_x_h], dim=2)
next_x_ll = self.iwt_function(curr_x)
next_x_ll = next_x_ll[:, :, :curr_shape[2], :curr_shape[3]]
x_tag = next_x_ll
assert len(x_ll_in_levels) == 0
x = self.base_scale(self.base_conv(x))
x = x + x_tag
if self.do_stride is not None:
x = self.do_stride(x)
return x
class _ScaleModule(nn.Module):
def __init__(self, dims, init_scale=1.0, init_bias=0):
super(_ScaleModule, self).__init__()
self.dims = dims
self.weight = nn.Parameter(torch.ones(*dims) * init_scale)
self.bias = None
def forward(self, x):
return torch.mul(self.weight, 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
是上面的这个WTConv2d 框错了
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_WTConv.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
# 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, WTConv2d, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- [-1, 1, WTConv2d, [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
# 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, WTConv2d, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- [-1, 1, WTConv2d, [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]] # Detect(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
# 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, WTConv2d, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- [-1, 1, WTConv2d, [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：5122.4 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WTConv
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WTConv
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_WTConv.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/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 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
12 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1]
13 -1 1 111296 ultralytics.nn.modules.block.C3k2 [384, 128, 1, False]
14 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
15 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1]
16 -1 1 32096 ultralytics.nn.modules.block.C3k2 [256, 64, 1, False]
17 -1 1 5376 ultralytics.nn.modules.models.WTConv.WTConv2d [64, 64, 3, 2]
18 [-1, 13] 1 0 ultralytics.nn.modules.conv.Concat [1]
19 -1 1 86720 ultralytics.nn.modules.block.C3k2 [192, 128, 1, False]
20 -1 1 10752 ultralytics.nn.modules.models.WTConv.WTConv2d [128, 128, 3, 2]
21 [-1, 10] 1 0 ultralytics.nn.modules.conv.Concat [1]
22 -1 1 378880 ultralytics.nn.modules.block.C3k2 [384, 256, 1, True]
23 [16, 19, 22] 1 464912 ultralytics.nn.modules.head.Detect [80, [64, 128, 256]]
YOLO11_WTConv summary: 327 layers, 2,455,504 parameters, 2,449,152 gradients, 6.4 GFLOPs3.修改后的网络结构图
4. 完整代码分享
主页侧边
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——<专栏地址：YOLO11入门 + 改进涨点——点击即可跳转 欢迎订阅>。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。
为什么订阅我的专栏？ ——专栏地址：YOLO11入门 + 改进涨点——点击即可跳转 欢迎订阅
-
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。
-
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。
-
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。
-
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
