当前位置：首页 > article >正文

YOLOv11融合针对小目标FFCA-YOPLO中的FEM模块及相关改进思路

article 2024/11/19 10:01:59

YOLOv11v10v8使用教程： YOLOv11入门到入土使用教程

YOLOv11改进汇总贴：YOLOv11及自研模型更新汇总

《FFCA-YOLO for Small Object Detection in Remote Sensing Images》

一、模块介绍

论文链接：https://ieeexplore.ieee.org/document/10423050

代码链接：yemu1138178251/FFCA-YOLO (github.com)

论文速览：

特征表示不足、背景混淆等问题使得遥感中小目标的探测任务变得艰巨。特别是当算法将部署在机上进行实时处理时，这需要在有限的计算资源下对准确性和速度进行广泛的优化。为了解决这些问题，本文提出了一种称为特征增强、融合和上下文感知 YOLO （FFCA-YOLO）的高效检测器。FFCA-YOLO 包括三个创新的轻量级和即插即用模块：功能增强模块（FEM）、功能融合模块（FFM）和空间上下文感知模块（SCAM）。这三个模块分别提高了局域网感知、多尺度特征融合和全局关联跨信道和空间的网络能力，同时尽可能避免增加复杂性。因此，小物体的弱特征表示得到了增强，并且抑制了可能混淆的背景。此外，为了在保证效率的同时进一步减少计算资源消耗，通过基于部分卷积（PConv）重建 FFCA-YOLO 的主干和颈部，优化了 FFCA-YOLO （L-FFCA-YOLO）的精简版。

总结：文章提出几个针对小目标的特征提取模块，有一定效果。

二、加入到YOLO中

2.1 创建脚本文件

首先在ultralytics->nn路径下创建blocks.py脚本，用于存放模块代码。

2.2 复制代码

复制代码粘到刚刚创建的blocks.py脚本中，如下图所示：

import torch
import torch.nn as nn
from ultralytics.nn.modules.conv import Conv


class BasicConv_FFCA(nn.Module):
    def __init__(self, in_planes, out_planes, kernel_size, stride=1, padding=0, dilation=1, groups=1, relu=True,
                 bn=True, bias=False):
        super(BasicConv_FFCA, self).__init__()
        self.out_channels = out_planes
        self.conv = nn.Conv2d(in_planes, out_planes, kernel_size=kernel_size, stride=stride, padding=padding,
                              dilation=dilation, groups=groups, bias=bias)
        self.bn = nn.BatchNorm2d(out_planes, eps=1e-5, momentum=0.01, affine=True) if bn else None
        self.relu = nn.ReLU(inplace=True) if relu else None

    def forward(self, x):
        x = self.conv(x)
        if self.bn is not None:
            x = self.bn(x)
        if self.relu is not None:
            x = self.relu(x)
        return x


class FEM(nn.Module):
    def __init__(self, in_planes, out_planes, stride=1, scale=0.1, map_reduce=8):
        super(FEM, self).__init__()
        self.scale = scale
        self.out_channels = out_planes
        inter_planes = in_planes // map_reduce
        self.branch0 = nn.Sequential(
            BasicConv_FFCA(in_planes, 2 * inter_planes, kernel_size=1, stride=stride),
            BasicConv_FFCA(2 * inter_planes, 2 * inter_planes, kernel_size=3, stride=1, padding=1, relu=False)
        )
        self.branch1 = nn.Sequential(
            BasicConv_FFCA(in_planes, inter_planes, kernel_size=1, stride=1),
            BasicConv_FFCA(inter_planes, (inter_planes // 2) * 3, kernel_size=(1, 3), stride=stride, padding=(0, 1)),
            BasicConv_FFCA((inter_planes // 2) * 3, 2 * inter_planes, kernel_size=(3, 1), stride=stride, padding=(1, 0)),
            BasicConv_FFCA(2 * inter_planes, 2 * inter_planes, kernel_size=3, stride=1, padding=5, dilation=5, relu=False)
        )
        self.branch2 = nn.Sequential(
            BasicConv_FFCA(in_planes, inter_planes, kernel_size=1, stride=1),
            BasicConv_FFCA(inter_planes, (inter_planes // 2) * 3, kernel_size=(3, 1), stride=stride, padding=(1, 0)),
            BasicConv_FFCA((inter_planes // 2) * 3, 2 * inter_planes, kernel_size=(1, 3), stride=stride, padding=(0, 1)),
            BasicConv_FFCA(2 * inter_planes, 2 * inter_planes, kernel_size=3, stride=1, padding=5, dilation=5, relu=False)
        )

        self.ConvLinear = BasicConv_FFCA(6 * inter_planes, out_planes, kernel_size=1, stride=1, relu=False)
        self.shortcut = BasicConv_FFCA(in_planes, out_planes, kernel_size=1, stride=stride, relu=False)
        self.relu = nn.ReLU(inplace=False)

    def forward(self, x):
        x0 = self.branch0(x)
        x1 = self.branch1(x)
        x2 = self.branch2(x)

        out = torch.cat((x0, x1, x2), 1)
        out = self.ConvLinear(out)
        short = self.shortcut(x)
        out = out * self.scale + short
        out = self.relu(out)

        return out

2.3 更改task.py文件

打开ultralytics->nn->modules->task.py，在脚本空白处导入函数。

from ultralytics.nn.blocks import *

之后找到模型解析函数parse_model（约在tasks.py脚本中940行左右位置，可能因代码版本不同变动），在该函数的最后一个else分支上面增加相关解析代码。

        elif m is FEM:
            c2 = args[0]
            args = [ch[f], *args]

2.4 更改yaml文件

yam文件解读：YOLO系列 “.yaml“文件解读_yolo yaml文件-CSDN博客

打开更改ultralytics/cfg/models/11路径下的YOLOv11.yaml文件，替换原有模块。（放在该位置仅能插入该模块，具体效果未知。博主精力有限，仅完成与其他模块二次创新融合的测试，结构图见文末，代码见群文件更新。）

# 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, FEM, [512]]
  - [-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)

2.5 修改train.py文件

创建Train脚本用于训练。

from ultralytics.models import YOLO
import os
os.environ['KMP_DUPLICATE_LIB_OK'] = 'True'

if __name__ == '__main__':
    model = YOLO(model='ultralytics/cfg/models/11/yolo11.yaml')
    # model.load('yolov8n.pt')
    model.train(data='./data.yaml', epochs=2, batch=1, device='0', imgsz=640, workers=2, cache=False,
                amp=True, mosaic=False, project='runs/train', name='exp')