【YOLOv11单模态融合改进】普通数据集的双模型融合改进，涉及中期、中后期、后期融合方式的完整配置步骤以及二次改进方案
前言
主题： YOLOv11的单模态融合改进，普通数据集的双模型融合改进（双模型同步提升）
方式： 中期融合、中-后期融合、后期融合。
内容： 包含融合方式详解和完整配置步骤以及二次改进建议，通过融合多个模型的优势实现精度提升。
一、融合方式
输入的是一个模态的数据，所以没有早期的融合。
1.1 中期融合方法及结构图
定义： 在网络中间层（骨干网络与颈部网络之间）对多模态特征进行融合。
实现方式： 每个模态通过独立的骨干网络提取特征，融合时采用Concat操作合并特征图，送入颈部网络。
结构示意图：
1.2 中-后期融合方法及结构图
定义： 在颈部网络的上采样之后对多模态特征进行融合。
实现方式： 每个模态通过独立的骨干网络和颈部的FPN网络提取特征，融合时采用Concat操作合并特征图，送入检测头。
结构示意图：
1.3 后期融合方法及结构图
定义： 在网络输出阶段（如检测头或分类器前）对多模态特征进行融合。
实现方式： 每个模态通过独立的骨干网络和颈部网络提取特征，融合时采用Concat操作合并特征图，送入检测头。
结构示意图：
二、完整配置步骤
相关的配置只涉及单模态，只需在原本的项目包中配置运行即可，不需要使用我提供的多模态项目包。
①：在
ultralytics/nn/modules/block.py
中添加如下代码，并在
__all__
中添加
“IN”
class IN(nn.Module):
def __init__(self):
super().__init__()
def forward(self, x):
return x
②：在
ultralytics/nn/modules/__init__.py
中的
from .block import (...）
添加
IN
③：在
ultralytics/nn/tasks.py
中的
from ultralytics.nn.modules import (...)
中添加
IN
至此，添加完成。
三、YAML模型结构
此处以
ultralytics/cfg/models/11/yolo11.yaml
为例，在同目录下创建一个用于自己数据集训练的双模型融合文件，并粘贴下方的模型训练即可。
3.1 中期融合
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO11 object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo11
# Task docs: 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, IN, []] # 0
- [0, 1, Conv, [64, 3, 2]] # 1-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 2-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 4-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 6-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 8-P5/32
- [-1, 2, C3k2, [1024, True]]
- [0, 1, Conv, [64, 3, 2]] # 10-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 11-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 13-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 15-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 17-P5/32
- [-1, 2, C3k2, [1024, True]]
- [[5, 14], 1, Concat, [1]] # 19 cat backbone P3
- [[7, 16], 1, Concat, [1]] # 20 cat backbone P4
- [[9, 18], 1, Concat, [1]] # 21 cat backbone P5
- [-1, 1, SPPF, [1024, 5]] # 22
- [-1, 2, C2PSA, [1024]] # 23
# YOLO11n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 20], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 26
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 19], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, False]] # 29 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 26], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 32 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 23], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 35 (P5/32-large)
- [[29, 32, 35], 1, Detect, [nc]] # Detect(P3, P4, P5)
3.2 中-后期融合
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO11 object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo11
# Task docs: 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, IN, []] # 0
- [0, 1, Conv, [64, 3, 2]] # 1-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 2-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 4-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 6-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 8-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 10
- [-1, 2, C2PSA, [1024]] # 11
- [0, 1, Conv, [64, 3, 2]] # 12-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 13-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 15-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 17-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 19-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 21
- [-1, 2, C2PSA, [1024]] # 22
# YOLO11n head
head:
- [11, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 7], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 25
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 5], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, False]] # 28 (P3/8-small)
- [22, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 18], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 31
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 16], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, False]] # 34 (P3/8-small)
- [[11, 22], 1, Concat, [1]] # 35 cat backbone P3
- [[25, 31], 1, Concat, [1]] # 36 cat backbone P4
- [[28, 34], 1, Concat, [1]] # 37 cat backbone P5
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 36], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 40 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 35], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 43 (P5/32-large)
- [[37, 40, 43], 1, Detect, [nc]] # Detect(P3, P4, P5)
3.3 后期融合
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO11 object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo11
# Task docs: 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, IN, []] # 0
- [0, 1, Conv, [64, 3, 2]] # 1-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 2-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 4-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 6-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 8-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 10
- [-1, 2, C2PSA, [1024]] # 11
- [0, 1, Conv, [64, 3, 2]] # 12-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 13-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 15-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 17-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 19-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 21
- [-1, 2, C2PSA, [1024]] # 22
# YOLO11n head
head:
- [11, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 7], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 25
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 5], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, False]] # 28 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 25], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 31 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 34 (P5/32-large)
- [22, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 18], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 37
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 16], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, False]] # 40 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 37], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 43 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 22], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 46 (P5/32-large)
- [[11, 22], 1, Concat, [1]] # 47 cat backbone P3
- [[31, 43], 1, Concat, [1]] # 48 cat backbone P4
- [[34, 46], 1, Concat, [1]] # 49 cat backbone P5
- [[47, 48, 49], 1, Detect, [nc]] # Detect(P3, P4, P5)
四、成功运行结果
中期融合结果：
YOLO11-BiModel summary: 434 layers, 3,795,379 parameters, 3,795,363 gradients, 9.6 GFLOPs
from n params module arguments
0 -1 1 0 ultralytics.nn.modules.block.IN []
1 0 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2]
2 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2]
3 -1 1 6640 ultralytics.nn.modules.block.C3k2 [32, 64, 1, False, 0.25]
4 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2]
5 -1 1 26080 ultralytics.nn.modules.block.C3k2 [64, 128, 1, False, 0.25]
6 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2]
7 -1 1 87040 ultralytics.nn.modules.block.C3k2 [128, 128, 1, True]
8 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2]
9 -1 1 346112 ultralytics.nn.modules.block.C3k2 [256, 256, 1, True]
10 0 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2]
11 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2]
12 -1 1 6640 ultralytics.nn.modules.block.C3k2 [32, 64, 1, False, 0.25]
13 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2]
14 -1 1 26080 ultralytics.nn.modules.block.C3k2 [64, 128, 1, False, 0.25]
15 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2]
16 -1 1 87040 ultralytics.nn.modules.block.C3k2 [128, 128, 1, True]
17 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2]
18 -1 1 346112 ultralytics.nn.modules.block.C3k2 [256, 256, 1, True]
19 [5, 14] 1 0 ultralytics.nn.modules.conv.Concat [1]
20 [7, 16] 1 0 ultralytics.nn.modules.conv.Concat [1]
21 [9, 18] 1 0 ultralytics.nn.modules.conv.Concat [1]
22 -1 1 394240 ultralytics.nn.modules.block.SPPF [512, 256, 5]
23 -1 1 249728 ultralytics.nn.modules.block.C2PSA [256, 256, 1]
24 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
25 [-1, 20] 1 0 ultralytics.nn.modules.conv.Concat [1]
26 -1 1 127680 ultralytics.nn.modules.block.C3k2 [512, 128, 1, False]
27 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
28 [-1, 19] 1 0 ultralytics.nn.modules.conv.Concat [1]
29 -1 1 40288 ultralytics.nn.modules.block.C3k2 [384, 64, 1, False]
30 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2]
31 [-1, 26] 1 0 ultralytics.nn.modules.conv.Concat [1]
32 -1 1 86720 ultralytics.nn.modules.block.C3k2 [192, 128, 1, False]
33 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2]
34 [-1, 23] 1 0 ultralytics.nn.modules.conv.Concat [1]
35 -1 1 378880 ultralytics.nn.modules.block.C3k2 [384, 256, 1, True]
36 [29, 32, 35] 1 430867 ultralytics.nn.modules.head.Detect [1, [64, 128, 256]]
YOLO11-BiModel summary: 434 layers, 3,795,379 parameters, 3,795,363 gradients, 9.6 GFLOPs
中-后期融合结果：
YOLO11-BiModel summary: 506 layers, 4,332,051 parameters, 4,332,035 gradients, 11.5 GFLOPs
from n params module arguments
0 -1 1 0 ultralytics.nn.modules.block.IN []
1 0 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2]
2 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2]
3 -1 1 6640 ultralytics.nn.modules.block.C3k2 [32, 64, 1, False, 0.25]
4 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2]
5 -1 1 26080 ultralytics.nn.modules.block.C3k2 [64, 128, 1, False, 0.25]
6 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2]
7 -1 1 87040 ultralytics.nn.modules.block.C3k2 [128, 128, 1, True]
8 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2]
9 -1 1 346112 ultralytics.nn.modules.block.C3k2 [256, 256, 1, True]
10 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5]
11 -1 1 249728 ultralytics.nn.modules.block.C2PSA [256, 256, 1]
12 0 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2]
13 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2]
14 -1 1 6640 ultralytics.nn.modules.block.C3k2 [32, 64, 1, False, 0.25]
15 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2]
16 -1 1 26080 ultralytics.nn.modules.block.C3k2 [64, 128, 1, False, 0.25]
17 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2]
18 -1 1 87040 ultralytics.nn.modules.block.C3k2 [128, 128, 1, True]
19 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2]
20 -1 1 346112 ultralytics.nn.modules.block.C3k2 [256, 256, 1, True]
21 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5]
22 -1 1 249728 ultralytics.nn.modules.block.C2PSA [256, 256, 1]
23 11 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
24 [-1, 7] 1 0 ultralytics.nn.modules.conv.Concat [1]
25 -1 1 111296 ultralytics.nn.modules.block.C3k2 [384, 128, 1, False]
26 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
27 [-1, 5] 1 0 ultralytics.nn.modules.conv.Concat [1]
28 -1 1 32096 ultralytics.nn.modules.block.C3k2 [256, 64, 1, False]
29 22 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
30 [-1, 18] 1 0 ultralytics.nn.modules.conv.Concat [1]
31 -1 1 111296 ultralytics.nn.modules.block.C3k2 [384, 128, 1, False]
32 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
33 [-1, 16] 1 0 ultralytics.nn.modules.conv.Concat [1]
34 -1 1 32096 ultralytics.nn.modules.block.C3k2 [256, 64, 1, False]
35 [11, 22] 1 0 ultralytics.nn.modules.conv.Concat [1]
36 [25, 31] 1 0 ultralytics.nn.modules.conv.Concat [1]
37 [28, 34] 1 0 ultralytics.nn.modules.conv.Concat [1]
38 -1 1 73856 ultralytics.nn.modules.conv.Conv [128, 64, 3, 2]
39 [-1, 36] 1 0 ultralytics.nn.modules.conv.Concat [1]
40 -1 1 103104 ultralytics.nn.modules.block.C3k2 [320, 128, 1, False]
41 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2]
42 [-1, 35] 1 0 ultralytics.nn.modules.conv.Concat [1]
43 -1 1 444416 ultralytics.nn.modules.block.C3k2 [640, 256, 1, True]
44 [37, 40, 43] 1 545235 ultralytics.nn.modules.head.Detect [1, [128, 128, 256]]
YOLO11-BiModel summary: 506 layers, 4,332,051 parameters, 4,332,035 gradients, 11.5 GFLOPs
后期融合结果：
YOLO11-BiModel summary: 562 layers, 7,742,035 parameters, 7,742,019 gradients, 14.2 GFLOPs
from n params module arguments
0 -1 1 0 ultralytics.nn.modules.block.IN []
1 0 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2]
2 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2]
3 -1 1 6640 ultralytics.nn.modules.block.C3k2 [32, 64, 1, False, 0.25]
4 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2]
5 -1 1 26080 ultralytics.nn.modules.block.C3k2 [64, 128, 1, False, 0.25]
6 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2]
7 -1 1 87040 ultralytics.nn.modules.block.C3k2 [128, 128, 1, True]
8 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2]
9 -1 1 346112 ultralytics.nn.modules.block.C3k2 [256, 256, 1, True]
10 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5]
11 -1 1 249728 ultralytics.nn.modules.block.C2PSA [256, 256, 1]
12 0 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2]
13 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2]
14 -1 1 6640 ultralytics.nn.modules.block.C3k2 [32, 64, 1, False, 0.25]
15 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2]
16 -1 1 26080 ultralytics.nn.modules.block.C3k2 [64, 128, 1, False, 0.25]
17 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2]
18 -1 1 87040 ultralytics.nn.modules.block.C3k2 [128, 128, 1, True]
19 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2]
20 -1 1 346112 ultralytics.nn.modules.block.C3k2 [256, 256, 1, True]
21 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5]
22 -1 1 249728 ultralytics.nn.modules.block.C2PSA [256, 256, 1]
23 11 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
24 [-1, 7] 1 0 ultralytics.nn.modules.conv.Concat [1]
25 -1 1 111296 ultralytics.nn.modules.block.C3k2 [384, 128, 1, False]
26 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
27 [-1, 5] 1 0 ultralytics.nn.modules.conv.Concat [1]
28 -1 1 32096 ultralytics.nn.modules.block.C3k2 [256, 64, 1, False]
29 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2]
30 [-1, 25] 1 0 ultralytics.nn.modules.conv.Concat [1]
31 -1 1 86720 ultralytics.nn.modules.block.C3k2 [192, 128, 1, False]
32 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2]
33 [-1, 11] 1 0 ultralytics.nn.modules.conv.Concat [1]
34 -1 1 378880 ultralytics.nn.modules.block.C3k2 [384, 256, 1, True]
35 22 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
36 [-1, 18] 1 0 ultralytics.nn.modules.conv.Concat [1]
37 -1 1 111296 ultralytics.nn.modules.block.C3k2 [384, 128, 1, False]
38 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
39 [-1, 16] 1 0 ultralytics.nn.modules.conv.Concat [1]
40 -1 1 32096 ultralytics.nn.modules.block.C3k2 [256, 64, 1, False]
41 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2]
42 [-1, 37] 1 0 ultralytics.nn.modules.conv.Concat [1]
43 -1 1 86720 ultralytics.nn.modules.block.C3k2 [192, 128, 1, False]
44 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2]
45 [-1, 22] 1 0 ultralytics.nn.modules.conv.Concat [1]
46 -1 1 378880 ultralytics.nn.modules.block.C3k2 [384, 256, 1, True]
47 [11, 22] 1 0 ultralytics.nn.modules.conv.Concat [1]
48 [31, 43] 1 0 ultralytics.nn.modules.conv.Concat [1]
49 [34, 46] 1 0 ultralytics.nn.modules.conv.Concat [1]
50 [47, 48, 49] 1 3423699 ultralytics.nn.modules.head.Detect [1, [512, 256, 512]]
YOLO11-BiModel summary: 562 layers, 7,742,035 parameters, 7,742,019 gradients, 14.2 GFLOPs
五、二次改进方案
-
双模型的二次改进和普通模型的改进一致，主要涉及到C3k2、颈部结构、上采样、下采样等，可以增加或替换成其它模块，可以换成其它的颈部结构在进行融合。
-
两个骨干中均可以再次添加其它模块，需要注意的是融合的时候特征图大小要一致。