yolov26改进 | 细节创新篇 | iAFF迭代注意力特征融合改进C3k2助力yolov26有效涨点（附独家网络结构图
·
开始讲解之前推荐一下我的专栏，本专栏的内容支持(分类、检测、分割、追踪、关键点检测),专栏目前为限时折扣，欢迎大家订阅本专栏，本专栏每周更新5-7篇最新机制，更有包含我所有改进的文件和交流群提供给大家，本人定期在群内分享发表论文方法和经验。
一、本文介绍
本文给大家带来的最新改进机制是iAFF（迭代注意力特征融合），其主要思想是通过改善特征融合过程来提高检测精度。传统的特征融合方法如加法或串联简单，未考虑到特定对象的融合适用性。iAFF通过引入多尺度通道注意力模块(我个人觉得这个改进机制就算融合了注意力机制的求和操作)，更好地整合不同尺度和语义不一致的特征。该方法属于细节上的改进，并不影响任何其它的模块，非常适合大家进行融合改进，单独使用也是有一定的涨点效果。
欢迎大家订阅我的专栏一起学习YOLO！
专栏链接：YOLOv26有效涨点专栏包含：Conv、注意力机制、主干/Backbone、损失函数、优化器、后处理等改进机制
目录
二、iAFF的基本框架原理
官方论文地址： 官方论文地址点击即可跳转
官方代码地址： 官方代码地址点击即可跳转
iAFF的主要思想在于通过更精细的注意力机制来改善特征融合，从而增强卷积神经网络。它不仅处理了由于尺度和语义不一致而引起的特征融合问题，还引入了多尺度通道注意力模块，提供了一种统一且通用的特征融合方案。此外，iAFF通过迭代注意力特征融合来解决特征图初始整合可能成为的瓶颈。这种方法使得模型即使在层数或参数较少的情况下，也能取得到较好的效果。
iAFF的创新点主要包括：
1. 注意力特征融合：提出了一种新的特征融合方式，利用注意力机制来改善传统的简单特征融合方法（如加和或串联）。
2. 多尺度通道注意力模块：解决了在不同尺度上融合特征时出现的问题，特别是语义和尺度不一致的特征融合问题。
3. 迭代注意力特征融合（iAFF）：通过迭代地应用注意力机制来改善特征图的初步整合，克服了初步整合可能成为性能瓶颈的问题。
这张图片是关于所提出的AFF（注意力特征融合）和iAFF（迭代注意力特征融合）的示意图。图中展示了两种结构：
(a) AFF: 展示了一个通过多尺度通道注意力模块（MS-CAM）来融合不同特征的基本框架。特征图X和Y通过MS-CAM和其他操作融合，产生输出Z。
(b) iAFF: 与AFF类似，但添加了迭代结构。在这里，输出Z回馈到输入，与X和Y一起再次经过MS-CAM和融合操作，以进一步细化特征融合过程。
(这两种方法都是文章中提出的我仅使用了iAFF也就是更复杂的版本，大家对于AFF有兴趣的可以按照我的该法进行相似添加即可)
三、iAFF的核心代码
使用方式看章节四！
import torch
import torch.nn as nn
__all__ = ['C3k2_iAFF']
def autopad(k, p=None, d=1): # kernel, padding, dilation
"""Pad to 'same' shape outputs."""
if d > 1:
k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k] # actual kernel-size
if p is None:
p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
return p
class Conv(nn.Module):
"""Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""
default_act = nn.SiLU() # default activation
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
"""Initialize Conv layer with given arguments including activation."""
super().__init__()
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
self.bn = nn.BatchNorm2d(c2)
self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()
def forward(self, x):
"""Apply convolution, batch normalization and activation to input tensor."""
return self.act(self.bn(self.conv(x)))
def forward_fuse(self, x):
"""Perform transposed convolution of 2D data."""
return self.act(self.conv(x))
class iAFF(nn.Module):
'''
多特征融合 iAFF
'''
def __init__(self, channels=64, r=2):
super(iAFF, self).__init__()
inter_channels = int(channels // r)
# 本地注意力
self.local_att = nn.Sequential(
nn.Conv2d(channels, inter_channels, kernel_size=1, stride=1, padding=0),
nn.BatchNorm2d(inter_channels),
nn.ReLU(inplace=True),
nn.Conv2d(inter_channels, channels, kernel_size=1, stride=1, padding=0),
nn.BatchNorm2d(channels),
)
# 全局注意力
self.global_att = nn.Sequential(
nn.AdaptiveAvgPool2d(1),
nn.Conv2d(channels, inter_channels, kernel_size=1, stride=1, padding=0),
nn.ReLU(inplace=True),
nn.Conv2d(inter_channels, channels, kernel_size=1, stride=1, padding=0),
)
# 第二次本地注意力
self.local_att2 = nn.Sequential(
nn.Conv2d(channels, inter_channels, kernel_size=1, stride=1, padding=0),
nn.BatchNorm2d(inter_channels),
nn.ReLU(inplace=True),
nn.Conv2d(inter_channels, channels, kernel_size=1, stride=1, padding=0),
nn.BatchNorm2d(channels),
)
# 第二次全局注意力
self.global_att2 = nn.Sequential(
nn.AdaptiveAvgPool2d(1),
nn.Conv2d(channels, inter_channels, kernel_size=1, stride=1, padding=0),
nn.BatchNorm2d(inter_channels),
nn.ReLU(inplace=True),
nn.Conv2d(inter_channels, channels, kernel_size=1, stride=1, padding=0),
nn.BatchNorm2d(channels),
)
self.sigmoid = nn.Sigmoid()
def forward(self, x, residual):
xa = x + residual
xl = self.local_att(xa)
xg = self.global_att(xa)
xlg = xl + xg
wei = self.sigmoid(xlg)
xi = x * wei + residual * (1 - wei)
xl2 = self.local_att2(xi)
xg2 = self.global_att(xi)
xlg2 = xl2 + xg2
wei2 = self.sigmoid(xlg2)
xo = x * wei2 + residual * (1 - wei2)
return xo
class AFF(nn.Module):
'''
多特征融合 AFF
'''
def __init__(self, channels=64, r=4):
super(AFF, self).__init__()
inter_channels = int(channels // r)
self.local_att = nn.Sequential(
nn.Conv2d(channels, inter_channels, kernel_size=1, stride=1, padding=0),
nn.BatchNorm2d(inter_channels),
nn.ReLU(inplace=True),
nn.Conv2d(inter_channels, channels, kernel_size=1, stride=1, padding=0),
nn.BatchNorm2d(channels),
)
self.global_att = nn.Sequential(
nn.AdaptiveAvgPool2d(1),
nn.Conv2d(channels, inter_channels, kernel_size=1, stride=1, padding=0),
nn.BatchNorm2d(inter_channels),
nn.ReLU(inplace=True),
nn.Conv2d(inter_channels, channels, kernel_size=1, stride=1, padding=0),
nn.BatchNorm2d(channels),
)
self.sigmoid = nn.Sigmoid()
def forward(self, x, residual):
xa = x + residual
xl = self.local_att(xa)
xg = self.global_att(xa)
xlg = xl + xg
wei = self.sigmoid(xlg)
xo = 2 * x * wei + 2 * residual * (1 - wei)
return xo
class Bottleneck_iAFF(nn.Module):
"""Standard bottleneck."""
def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
"""Initializes a bottleneck module with given input/output channels, shortcut option, group, kernels, and
expansion.
"""
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, k[0], 1)
self.cv2 = Conv(c_, c2, k[1], 1, g=g)
self.add = shortcut and c1 == c2
self.iAFF = iAFF(c2)
def forward(self, x):
"""'forward()' applies the YOLO FPN to input data."""
if self.add:
results = self.iAFF(x , self.cv2(self.cv1(x)))
else:
results = self.cv2(self.cv1(x))
return results
class Bottleneck_AFF(nn.Module):
"""Standard bottleneck."""
def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
"""Initializes a bottleneck module with given input/output channels, shortcut option, group, kernels, and
expansion.
"""
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, k[0], 1)
self.cv2 = Conv(c_, c2, k[1], 1, g=g)
self.add = shortcut and c1 == c2
self.AFF = AFF(c2)
def forward(self, x):
"""'forward()' applies the YOLO FPN to input data."""
if self.add:
results = self.AFF(x, self.cv2(self.cv1(x)))
else:
results = self.cv2(self.cv1(x))
return results
class Bottleneck(nn.Module):
"""Standard bottleneck."""
def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
"""Initializes a standard bottleneck module with optional shortcut connection and configurable parameters."""
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, k[0], 1)
self.cv2 = Conv(c_, c2, k[1], 1, g=g)
self.add = shortcut and c1 == c2
def forward(self, x):
"""Applies the YOLO FPN to input data."""
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
class C2f(nn.Module):
"""Faster Implementation of CSP Bottleneck with 2 convolutions."""
def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
"""Initializes a CSP bottleneck with 2 convolutions and n Bottleneck blocks for faster processing."""
super().__init__()
self.c = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, 2 * self.c, 1, 1)
self.cv2 = Conv((2 + n) * self.c, c2, 1) # optional act=FReLU(c2)
self.m = nn.ModuleList(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n))
def forward(self, x):
"""Forward pass through C2f layer."""
y = list(self.cv1(x).chunk(2, 1))
y.extend(m(y[-1]) for m in self.m)
return self.cv2(torch.cat(y, 1))
def forward_split(self, x):
"""Forward pass using split() instead of chunk()."""
y = list(self.cv1(x).split((self.c, self.c), 1))
y.extend(m(y[-1]) for m in self.m)
return self.cv2(torch.cat(y, 1))
class C3(nn.Module):
"""CSP Bottleneck with 3 convolutions."""
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
"""Initialize the CSP Bottleneck with given channels, number, shortcut, groups, and expansion values."""
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c1, c_, 1, 1)
self.cv3 = Conv(2 * c_, c2, 1) # optional act=FReLU(c2)
self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, k=((1, 1), (3, 3)), e=1.0) for _ in range(n)))
def forward(self, x):
"""Forward pass through the CSP bottleneck with 2 convolutions."""
return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))
class C3k(C3):
"""C3k is a CSP bottleneck module with customizable kernel sizes for feature extraction in neural networks."""
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, k=3):
"""Initializes the C3k module with specified channels, number of layers, and configurations."""
super().__init__(c1, c2, n, shortcut, g, e)
c_ = int(c2 * e) # hidden channels
# self.m = nn.Sequential(*(RepBottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
class Attention_YOLOv26(nn.Module):
"""Attention module that performs self-attention on the input tensor.
Args:
dim (int): The input tensor dimension.
num_heads (int): The number of attention heads.
attn_ratio (float): The ratio of the attention key dimension to the head dimension.
Attributes:
num_heads (int): The number of attention heads.
head_dim (int): The dimension of each attention head.
key_dim (int): The dimension of the attention key.
scale (float): The scaling factor for the attention scores.
qkv (Conv): Convolutional layer for computing the query, key, and value.
proj (Conv): Convolutional layer for projecting the attended values.
pe (Conv): Convolutional layer for positional encoding.
"""
def __init__(self, dim: int, num_heads: int = 8, attn_ratio: float = 0.5):
"""Initialize multi-head attention module.
Args:
dim (int): Input dimension.
num_heads (int): Number of attention heads.
attn_ratio (float): Attention ratio for key dimension.
"""
super().__init__()
self.num_heads = num_heads
self.head_dim = dim // num_heads
self.key_dim = int(self.head_dim * attn_ratio)
self.scale = self.key_dim**-0.5
nh_kd = self.key_dim * num_heads
h = dim + nh_kd * 2
self.qkv = Conv(dim, h, 1, act=False)
self.proj = Conv(dim, dim, 1, act=False)
self.pe = Conv(dim, dim, 3, 1, g=dim, act=False)
def forward(self, x: torch.Tensor) -> torch.Tensor:
"""Forward pass of the Attention module.
Args:
x (torch.Tensor): The input tensor.
Returns:
(torch.Tensor): The output tensor after self-attention.
"""
B, C, H, W = x.shape
N = H * W
qkv = self.qkv(x)
q, k, v = qkv.view(B, self.num_heads, self.key_dim * 2 + self.head_dim, N).split(
[self.key_dim, self.key_dim, self.head_dim], dim=2
)
attn = (q.transpose(-2, -1) @ k) * self.scale
attn = attn.softmax(dim=-1)
x = (v @ attn.transpose(-2, -1)).view(B, C, H, W) + self.pe(v.reshape(B, C, H, W))
x = self.proj(x)
return x
class PSABlock(nn.Module):
"""PSABlock class implementing a Position-Sensitive Attention block for neural networks.
This class encapsulates the functionality for applying multi-head attention and feed-forward neural network layers
with optional shortcut connections.
Attributes:
attn (Attention): Multi-head attention module.
ffn (nn.Sequential): Feed-forward neural network module.
add (bool): Flag indicating whether to add shortcut connections.
Methods:
forward: Performs a forward pass through the PSABlock, applying attention and feed-forward layers.
"""
def __init__(self, c: int, attn_ratio: float = 0.5, num_heads: int = 4, shortcut: bool = True) -> None:
"""Initialize the PSABlock.
Args:
c (int): Input and output channels.
attn_ratio (float): Attention ratio for key dimension.
num_heads (int): Number of attention heads.
shortcut (bool): Whether to use shortcut connections.
"""
super().__init__()
self.attn = Attention_YOLOv26(c, attn_ratio=attn_ratio, num_heads=num_heads)
self.ffn = nn.Sequential(Conv(c, c * 2, 1), Conv(c * 2, c, 1, act=False))
self.add = shortcut
def forward(self, x: torch.Tensor) -> torch.Tensor:
"""Execute a forward pass through PSABlock.
Args:
x (torch.Tensor): Input tensor.
Returns:
(torch.Tensor): Output tensor after attention and feed-forward processing.
"""
x = x + self.attn(x) if self.add else self.attn(x)
x = x + self.ffn(x) if self.add else self.ffn(x)
return x
class C3k(C3):
"""C3k is a CSP bottleneck module with customizable kernel sizes for feature extraction in neural networks."""
def __init__(self, c1: int, c2: int, n: int = 1, shortcut: bool = True, g: int = 1, e: float = 0.5, k: int = 3):
"""Initialize C3k module.
Args:
c1 (int): Input channels.
c2 (int): Output channels.
n (int): Number of Bottleneck blocks.
shortcut (bool): Whether to use shortcut connections.
g (int): Groups for convolutions.
e (float): Expansion ratio.
k (int): Kernel size.
"""
super().__init__(c1, c2, n, shortcut, g, e)
c_ = int(c2 * e) # hidden channels
# self.m = nn.Sequential(*(RepBottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
class C3k_iAFF(C3):
"""C3k is a CSP bottleneck module with customizable kernel sizes for feature extraction in neural networks."""
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, k=3):
"""Initializes the C3k module with specified channels, number of layers, and configurations."""
super().__init__(c1, c2, n, shortcut, g, e)
c_ = int(c2 * e) # hidden channels
# self.m = nn.Sequential(*(RepBottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
self.m = nn.Sequential(*(Bottleneck_iAFF(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
class C3k2_iAFF(C2f):
"""Faster Implementation of CSP Bottleneck with 2 convolutions."""
def __init__(
self,
c1: int,
c2: int,
n: int = 1,
c3k: bool = False,
e: float = 0.5,
attn: bool = False,
g: int = 1,
shortcut: bool = True,
):
"""Initialize C3k2 modu
Args:
c1 (int): Input channels.
c2 (int): Output channels.
n (int): Number of blocks.
c3k (bool): Whether to use C3k blocks.
e (float): Expansion ratio.
attn (bool): Whether to use attention blocks.
g (int): Groups for convolutions.
shortcut (bool): Whether to use shortcut connections.
"""
super().__init__(c1, c2, n, shortcut, g, e)
self.m = nn.ModuleList(
nn.Sequential(
Bottleneck_iAFF(self.c, self.c, shortcut, g),
PSABlock(self.c, attn_ratio=0.5, num_heads=max(self.c // 64, 1)),
)
if attn
else C3k_iAFF(self.c, self.c, 2, shortcut, g)
if c3k
else Bottleneck_iAFF(self.c, self.c, shortcut, g)
for _ in range(n)
)
if __name__ == '__main__':
from thop import profile, clever_format
inp1= torch.rand(1,48,256,256)
model = C3k2_iAFF(48,48)
out = model(inp1)
print(out.shape)四、手把手教你添加C3k2iAFF
下面的步骤如果你不会或者不想麻烦操作，可以联系作者获得本专栏添加所有项目文件的源代码，可直接训练.
4.1 修改一
第一还是建立文件，我们找到如下ultralytics/nn文件夹下建立一个目录名字呢就是'Addmodules'文件夹！
4.2 修改二
然后在Addmodules文件夹内建立一个新的py文件，将本文章节三中的“核心代码"复制粘贴进去。
4.3 修改三
第二步我们在该目录下创建一个新的py文件名字为'__init__.py'，然后在其内部导入我们的文件，如下图所示。
4.4 修改四
第三步我门中到如下文件'ultralytics/nn/tasks.py'进行导入和注册我们的模块(此处只需要添加一次即可，如果你用我其它的改进机制这里的步骤只需要添加一次)！
4.5 修改五
在'ultralytics/nn/tasks.py'文件内的parse_model方法函数内（位置大概在1500+行左右），按照图示位置添加即可（此处需要自己有一定的判别能力，如果不会可联系作者获得视频教程）。
4.6 修改六
在'ultralytics/nn/tasks.py'文件内的parse_model方法函数内（位置大概在1600+行左右），按照图示位置进行代码的替换即可（此处不改如果你yaml文件中的所有C3k2都被改名了，则检测头会使用老版本的v8检测头参数量会大幅度增加，但不影响运行很多人都忽略了这一步）。
if "C3k2" in getattr(m, "__name__", str(m)):
legacy = False
if scale in "mlx":
args[3] = True到此就修改完成了，大家可以复制下面的yaml文件运行，更多使用方式可以联系作者获得使用视频，本文仅列出常见的使用方式。
五、正式训练
5.1 yaml文件
5.1.1 yaml文件1
训练信息：YOLO26-C3k2-iAFF-1 summary: 387 layers, 2,555,820 parameters, 2,555,820 gradients, 5.9 GFLOPs
# 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_iAFF, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2_iAFF, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2_iAFF, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2_iAFF, [1024, True]]
- [-1, 1, SPPF, [1024, 5, 3, True]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO26n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, True]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)
5.1.2 yaml文件2
训练信息：YOLO26-C3k2-iAFF-2 summary: 366 layers, 2,585,276 parameters, 2,585,276 gradients, 5.8 GFLOPs
# 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]]
- [-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, 3, True]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO26n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2_iAFF, [256, True]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2_iAFF, [512, True]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 1, C3k2_iAFF, [1024, True, 0.5, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)
5.1.3 yaml文件3
训练信息：YOLO26-C3k2-iAFF-3 summary: 534 layers, 2,644,108 parameters, 2,644,108 gradients, 6.0 GFLOPs
# 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_iAFF, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2_iAFF, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2_iAFF, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2_iAFF, [1024, True]]
- [-1, 1, SPPF, [1024, 5, 3, True]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO26n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2_iAFF, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2_iAFF, [256, True]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2_iAFF, [512, True]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 1, C3k2_iAFF, [1024, True, 0.5, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)
5.2 训练代码
大家可以创建一个py文件将我给的代码复制粘贴进去，配置好自己的文件路径即可运行。
import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLO
if __name__ == '__main__':
model = YOLO('模型配置文件地址,也就是5.1你保存到本地文件的地址')
# 如何切换模型版本, 上面的ymal文件可以改为 yolo26s.yaml就是使用的26s,
# 类似某个改进的yaml文件名称为yolo26-XXX.yaml那么如果想使用其它版本就把上面的名称改为yolo26l-XXX.yaml即可（改的是上面YOLO中间的名字不是配置文件的）！
# model.load('yolo26n.pt') # 是否加载预训练权重,科研不建议大家加载否则很难提升精度
model.train(
data=r"数据集文件地址",
# 如果大家任务是其它的'ultralytics/cfg/default.yaml'找到这里修改task可以改成detect, segment, classify, pose
cache=False,
imgsz=640,
epochs=20,
single_cls=False, # 是否是单类别检测
batch=16,
close_mosaic=0,
workers=0,
device='0',
optimizer='MuSGD', # using SGD/MuSGD
# resume=, # 这里是填写last.pt地址
amp=True, # 如果出现训练损失为Nan可以关闭amp
project='runs/train',
name='exp',
)
5.3 训练过程截图
五、本文总结
到此本文的正式分享内容就结束了，在这里给大家推荐我的YOLOv26改进有效涨点专栏，本专栏目前为新开的平均质量分98分，后期我会根据各种最新的前沿顶会进行论文复现，也会对一些老的改进机制进行补充，如果大家觉得本文帮助到你了，订阅本专栏，关注后续更多的更新~
专栏链接：