YOLOP2层改进

原创已于 2025-07-09 22:35:37 修改 · 682 阅读

6 ·

CC 4.0 BY-SA版权

文章标签：

#目标跟踪 #人工智能 #算法

于 2025-07-02 02:36:50 首次发布

YOLO学习笔记同时被 2 个专栏收录

14 篇文章

订阅专栏

CV改进模块

6 篇文章

订阅专栏

部署运行你感兴趣的模型镜像

核心目标：

在目标检测任务中，P2 层（分辨率为输入图像 1/4 的特征层）主要负责捕获小目标细节特征。原始 YOLOv11 模型仅使用 P3-P5 三层特征金字塔（分辨率 1/8、1/16、1/32），改进后的版本新增 P2 层（1/4 分辨率），主要优势在于：

增强小目标检测能力：更高分辨率的特征图保留更多空间细节，解决小目标特征缺失问题
丰富特征层次：形成 P2-P5 四级特征金字塔，覆盖从像素级细节到语义级全局的全尺度特征

如何改进呢，仅需修改原yolo11.yaml配置文件，即可修改网络结构。

YOLOv12

官方yolov12.yaml文件内容，

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license

# YOLO12 object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo12
# Task docs: https://docs.ultralytics.com/tasks/detect

# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo12n.yaml' will call yolo12.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 272 layers, 2,602,288 parameters, 2,602,272 gradients, 6.7 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 272 layers, 9,284,096 parameters, 9,284,080 gradients, 21.7 GFLOPs
  m: [0.50, 1.00, 512] # summary: 292 layers, 20,199,168 parameters, 20,199,152 gradients, 68.1 GFLOPs
  l: [1.00, 1.00, 512] # summary: 488 layers, 26,450,784 parameters, 26,450,768 gradients, 89.7 GFLOPs
  x: [1.00, 1.50, 512] # summary: 488 layers, 59,210,784 parameters, 59,210,768 gradients, 200.3 GFLOPs

# YOLO12n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv,  [64, 3, 2]] # 0-P1/2
  - [-1, 1, Conv,  [128, 3, 2, 1, 2]] # 1-P2/4
  - [-1, 2, C3k2,  [256, False, 0.25]]
  - [-1, 1, Conv,  [256, 3, 2, 1, 4]] # 3-P3/8
  - [-1, 2, C3k2,  [512, False, 0.25]]
  - [-1, 1, Conv,  [512, 3, 2]] # 5-P4/16
  - [-1, 4, A2C2f, [512, True, 4]]
  - [-1, 1, Conv,  [1024, 3, 2]] # 7-P5/32
  - [-1, 4, A2C2f, [1024, True, 1]] # 8

# YOLO12n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, A2C2f, [512, False, -1]] # 11

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, A2C2f, [256, False, -1]] # 14

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 11], 1, Concat, [1]] # cat head P4
  - [-1, 2, A2C2f, [512, False, -1]] # 17

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 8], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 20 (P5/32-large)

  - [[14, 17, 20], 1, Detect, [nc]] # Detect(P3, P4, P5)

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license

# YOLO12 object detection model with P2/4 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo12
# Task docs: https://docs.ultralytics.com/tasks/detect

# Parameters
nc: 80 # number of classes
scales:
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024]
  s: [0.50, 0.50, 1024]
  m: [0.50, 1.00, 512]
  l: [1.00, 1.00, 512]
  x: [1.00, 1.50, 512]

# YOLO12 backbone (保持不变)
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 (关键层：4倍下采样)
  - [-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, 4, A2C2f, [512, True, 4]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 4, A2C2f, [1024, True, 1]] # 8

# YOLO12 head (新增P2层检测头)
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, A2C2f, [512, False, -1]] # 11 (P4/16-medium)

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, A2C2f, [256, False, -1]] # 14 (P3/8-small)

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 1], 1, Concat, [1]] # cat backbone P2 (新增：融合4倍下采样特征)
  - [-1, 2, A2C2f, [128, False, -1]] # 17 (P2/4-xsmall)

  - [-1, 1, Conv, [128, 3, 2]] # P2上采样到P3
  - [[-1, 14], 1, Concat, [1]] # cat head P3
  - [-1, 2, A2C2f, [256, False, -1]] # 20 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]] # P3上采样到P4
  - [[-1, 11], 1, Concat, [1]] # cat head P4
  - [-1, 2, A2C2f, [512, False, -1]] # 23 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]] # P4上采样到P5
  - [[-1, 8], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 26 (P5/32-large)

  - [[17, 20, 23, 26], 1, Detect, [nc]] # Detect(P2, P3, P4, P5)

YOLOv11

yolov11原yaml文件：yolo11.yaml

# 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, 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)

p2改进后的，yolo11-p2.yaml

# 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, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 2], 1, Concat, [1]] # cat backbone P2
  - [-1, 2, C3k2, [128, False]] # 19 (P2/4-xsmall)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 16], 1, Concat, [1]] # cat head P3
  - [-1, 2, C3k2, [256, False]] # 22 (P3/8-medium)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 25 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 28 (P5/32-large)

  - [[19, 22, 25, 28], 1, Detect, [nc]] # Detect(P3, P4, P5)