當前位置：首頁 > news >正文

河南省網(wǎng)站建設最新最好的磁力搜索

news 2025/7/4 6:10:13

河南省網(wǎng)站建設,最新最好的磁力搜索,網(wǎng)站建設 php,深圳南山網(wǎng)站建設YOLOv11v10v8使用教程： YOLOv11入門到入土使用教程 YOLOv11改進匯總貼：YOLOv11及自研模型更新匯總《FFCA-YOLO for Small Object Detection in Remote Sensing Images》一、模塊介紹論文鏈接：https://ieeexplore.ieee.org/document/10…

YOLOv11v10v8使用教程：??YOLOv11入門到入土使用教程

YOLOv11改進匯總貼：YOLOv11及自研模型更新匯總?

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

一、模塊介紹

? ? ? ? 論文鏈接：https://ieeexplore.ieee.org/document/10423050

? ? ? ? 代碼鏈接：yemu1138178251/FFCA-YOLO (github.com)

論文速覽：

????????特征表示不足、背景混淆等問題使得遙感中小目標的探測任務變得艱巨。特別是當算法將部署在機上進行實時處理時，這需要在有限的計算資源下對準確性和速度進行廣泛的優(yōu)化。為了解決這些問題，本文提出了一種稱為特征增強、融合和上下文感知 YOLO （FFCA-YOLO）的高效檢測器。FFCA-YOLO 包括三個創(chuàng)新的輕量級和即插即用模塊：功能增強模塊（FEM）、功能融合模塊（FFM）和空間上下文感知模塊（SCAM）。這三個模塊分別提高了局域網(wǎng)感知、多尺度特征融合和全局關聯(lián)跨信道和空間的網(wǎng)絡能力，同時盡可能避免增加復雜性。因此，小物體的弱特征表示得到了增強，并且抑制了可能混淆的背景。此外，為了在保證效率的同時進一步減少計算資源消耗，通過基于部分卷積（PConv）重建 FFCA-YOLO 的主干和頸部，優(yōu)化了 FFCA-YOLO （L-FFCA-YOLO）的精簡版。

總結：?文章提出幾個針對小目標的特征提取模塊，有一定效果。

二、加入到YOLO中

2.1 創(chuàng)建腳本文件

? ? ? ? 首先在ultralytics->nn路徑下創(chuàng)建blocks.py腳本，用于存放模塊代碼。

2.2 復制代碼? ? ? ??

????????復制代碼粘到剛剛創(chuàng)建的blocks.py腳本中，如下圖所示：

import torch
import torch.nn as nn
from ultralytics.nn.modules.conv import Convclass 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_planesself.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 Noneself.relu = nn.ReLU(inplace=True) if relu else Nonedef 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 xclass FEM(nn.Module):def __init__(self, in_planes, out_planes, stride=1, scale=0.1, map_reduce=8):super(FEM, self).__init__()self.scale = scaleself.out_channels = out_planesinter_planes = in_planes // map_reduceself.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 + shortout = self.relu(out)return out

2.3?更改task.py文件?

? ? ? ?打開ultralytics->nn->modules->task.py，在腳本空白處導入函數(shù)。

from ultralytics.nn.blocks import *

? ? ? ? 之后找到模型解析函數(shù)parse_model（約在tasks.py腳本中940行左右位置，可能因代碼版本不同變動），在該函數(shù)的最后一個else分支上面增加相關解析代碼。

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

2.4 更改yaml文件?

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

? ? ? ?打開更改ultralytics/cfg/models/11路徑下的YOLOv11.yaml文件，替換原有模塊。（放在該位置僅能插入該模塊，具體效果未知。博主精力有限，僅完成與其他模塊二次創(chuàng)新融合的測試，結構圖見文末，代碼見群文件更新。）

# 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 GFLOPss: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPsm: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPsl: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPsx: [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

? ? ? ?創(chuàng)建Train腳本用于訓練。

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')