yolov5口罩检测模型-编程知识

1 项目背景及意义

全球范围内的公共卫生安全和人脸识别技术的发展。在面对新型冠状病毒等传染病的爆发和传播风险时，佩戴口罩成为一种重要的防护措施。然而，现有的人脸识别系统在识别戴口罩的人脸时存在一定的困难。

通过口罩识别技术，可以更准确地辨别佩戴口罩的人员身份，有助于提高公共安全水平，减少犯罪行为和恶意攻击的风险，且传统的人脸识别技术在遇到戴口罩的情况下准确度较低。通过开发口罩识别的异构高性能项目，可以提高人脸识别系统在戴口罩情况下的准确性和可靠性。在口罩成为日常生活必备品的背景下，通过口罩识别技术可以实现更便捷的公共服务，如自助购物、自助取票等，提升人们的生活体验。

这一技术的应用有助于应对公共卫生安全挑战，并推动人脸识别技术的进一步发展与应用。

2 环境搭建

2.1 yolov5模型下载

从github将yolov5的模型下载下来，github中yolov5首页如下图所示，通过右上角code下载全部代码。yolov5模型地址github地址
github
可通过release下载不同版本，本项目使用的是yolov5-5.0版本，可自由选择最新版本.
在这里插入图片描述

2.2 下载依赖

在已经有python环境的情况下，可以选用conda来构建虚拟环境，设置一个新的pytorch环境。

下载的yolov5模型根目录下有一个requirement.txt，其中包含了yolo所需的依赖包，通过指令pip install –r requirement.txt快速下载。如下图所示，图中的“already satisfied”是由于依赖已安装
在这里插入图片描述

3 数据集处理

实验中初始数据集为jpg格式图片与对应的txt格式标签文件，需要转为yolo格式的标签文件，以及划分数据集。代码部分主要参考目标检测数据集划分

3.1 txt转为xml

对于没有标签文件的图片可以使用labelImg标注，保存为xml文件，则不需要中txt转为xml,本次实验中没有xml标签，所以需要先转为xml。

文件结构如下图所示，在项目根目录下创建VOCdevkit/VOC2007，分为三个文件夹，JPEGImages用以存放图片，YOLO存放待转txt标签文件，Annotaions目前为空，用以存放转化后的XML文件。
在这里插入图片描述
在根目录下创建txttoxml.py，用以执行代码转txt为xml，详细代码如下

from xml.dom.minidom import Document
import os
import cv2# def makexml(txtPath, xmlPath, picPath):  # txt所在文件夹路径，xml文件保存路径，图片所在文件夹路径
def makexml(picPath, txtPath, xmlPath):  # txt所在文件夹路径，xml文件保存路径，图片所在文件夹路径"""此函数用于将yolo格式txt标注文件转换为voc格式xml标注文件在自己的标注图片文件夹下建三个子文件夹，分别命名为picture、txt、xml"""dic = {'0': "face",  '1': "mask",}files = os.listdir(txtPath)for i, name in enumerate(files):xmlBuilder = Document()annotation = xmlBuilder.createElement("annotation")  # 创建annotation标签xmlBuilder.appendChild(annotation)txtFile = open(txtPath + name)txtList = txtFile.readlines()img = cv2.imread(picPath + name[0:-4] + ".jpg")Pheight, Pwidth, Pdepth = img.shapefolder = xmlBuilder.createElement("folder")  # folder标签foldercontent = xmlBuilder.createTextNode("driving_annotation_dataset")folder.appendChild(foldercontent)annotation.appendChild(folder)  # folder标签结束filename = xmlBuilder.createElement("filename")  # filename标签filenamecontent = xmlBuilder.createTextNode(name[0:-4] + ".jpg")filename.appendChild(filenamecontent)annotation.appendChild(filename)  # filename标签结束size = xmlBuilder.createElement("size")  # size标签width = xmlBuilder.createElement("width")  # size子标签widthwidthcontent = xmlBuilder.createTextNode(str(Pwidth))width.appendChild(widthcontent)size.appendChild(width)  # size子标签width结束height = xmlBuilder.createElement("height")  # size子标签heightheightcontent = xmlBuilder.createTextNode(str(Pheight))height.appendChild(heightcontent)size.appendChild(height)  # size子标签height结束depth = xmlBuilder.createElement("depth")  # size子标签depthdepthcontent = xmlBuilder.createTextNode(str(Pdepth))depth.appendChild(depthcontent)size.appendChild(depth)  # size子标签depth结束annotation.appendChild(size)  # size标签结束for j in txtList:oneline = j.strip().split(" ")object = xmlBuilder.createElement("object")  # object 标签picname = xmlBuilder.createElement("name")  # name标签namecontent = xmlBuilder.createTextNode(dic[oneline[0]])picname.appendChild(namecontent)object.appendChild(picname)  # name标签结束pose = xmlBuilder.createElement("pose")  # pose标签posecontent = xmlBuilder.createTextNode("Unspecified")pose.appendChild(posecontent)object.appendChild(pose)  # pose标签结束truncated = xmlBuilder.createElement("truncated")  # truncated标签truncatedContent = xmlBuilder.createTextNode("0")truncated.appendChild(truncatedContent)object.appendChild(truncated)  # truncated标签结束difficult = xmlBuilder.createElement("difficult")  # difficult标签difficultcontent = xmlBuilder.createTextNode("0")difficult.appendChild(difficultcontent)object.appendChild(difficult)  # difficult标签结束bndbox = xmlBuilder.createElement("bndbox")  # bndbox标签xmin = xmlBuilder.createElement("xmin")  # xmin标签mathData = int(((float(oneline[1])) * Pwidth + 1) - (float(oneline[3])) * 0.5 * Pwidth)xminContent = xmlBuilder.createTextNode(str(mathData))xmin.appendChild(xminContent)bndbox.appendChild(xmin)  # xmin标签结束ymin = xmlBuilder.createElement("ymin")  # ymin标签mathData = int(((float(oneline[2])) * Pheight + 1) - (float(oneline[4])) * 0.5 * Pheight)yminContent = xmlBuilder.createTextNode(str(mathData))ymin.appendChild(yminContent)bndbox.appendChild(ymin)  # ymin标签结束xmax = xmlBuilder.createElement("xmax")  # xmax标签mathData = int(((float(oneline[1])) * Pwidth + 1) + (float(oneline[3])) * 0.5 * Pwidth)xmaxContent = xmlBuilder.createTextNode(str(mathData))xmax.appendChild(xmaxContent)bndbox.appendChild(xmax)  # xmax标签结束ymax = xmlBuilder.createElement("ymax")  # ymax标签mathData = int(((float(oneline[2])) * Pheight + 1) + (float(oneline[4])) * 0.5 * Pheight)ymaxContent = xmlBuilder.createTextNode(str(mathData))ymax.appendChild(ymaxContent)bndbox.appendChild(ymax)  # ymax标签结束object.appendChild(bndbox)  # bndbox标签结束annotation.appendChild(object)  # object标签结束f = open(xmlPath + name[0:-4] + ".xml", 'w')xmlBuilder.writexml(f, indent='\t', newl='\n', addindent='\t', encoding='utf-8')f.close()if __name__ == "__main__":picPath = "VOCdevkit/VOC2007/JPEGImages/" txtPath = "VOCdevkit/VOC2007/YOLO/" xmlPath = "VOCdevkit/VOC2007/Annotations/"  makexml(picPath, txtPath, xmlPath)

3.2 xml转为yolo

yolo标签文件也是txt格式的，但要直接使用txt很可能会出错，所以需要先转xml再转yolo。

实验通过文件命名划分数据集，将test_00003到test_00004作为验证集，大约1000张图片。test_00004以后作为测试集，大约800张。余下作为训练集，大约6000张，如果需要修改这个，可用正则。

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
import random
import re
from shutil import copyfileclasses = ["face", "mask"]
#classes=["ball"]TRAIN_RATIO = 80def clear_hidden_files(path):dir_list = os.listdir(path)for i in dir_list:abspath = os.path.join(os.path.abspath(path), i)if os.path.isfile(abspath):if i.startswith("._"):os.remove(abspath)else:clear_hidden_files(abspath)def convert(size, box):dw = 1./size[0]dh = 1./size[1]x = (box[0] + box[1])/2.0y = (box[2] + box[3])/2.0w = box[1] - box[0]h = box[3] - box[2]x = x*dww = w*dwy = y*dhh = h*dhreturn (x,y,w,h)def convert_annotation(image_id):in_file = open('VOCdevkit/VOC2007/Annotations/%s.xml' %image_id)out_file = open('VOCdevkit/VOC2007/YOLO/%s.txt' %image_id, 'w')tree=ET.parse(in_file)root = tree.getroot()size = root.find('size')w = int(size.find('width').text)h = int(size.find('height').text)for obj in root.iter('object'):difficult = obj.find('difficult').textcls = obj.find('name').textif cls not in classes or int(difficult) == 1:continuecls_id = classes.index(cls)xmlbox = obj.find('bndbox')b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))bb = convert((w,h), b)out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')in_file.close()out_file.close()wd = os.getcwd()
wd = os.getcwd()
data_base_dir = os.path.join(wd, "VOCdevkit/")
if not os.path.isdir(data_base_dir):os.mkdir(data_base_dir)
work_sapce_dir = os.path.join(data_base_dir, "VOC2007/")
if not os.path.isdir(work_sapce_dir):os.mkdir(work_sapce_dir)
annotation_dir = os.path.join(work_sapce_dir, "Annotations/")
if not os.path.isdir(annotation_dir):os.mkdir(annotation_dir)
clear_hidden_files(annotation_dir)
image_dir = os.path.join(work_sapce_dir, "JPEGImages/")
if not os.path.isdir(image_dir):os.mkdir(image_dir)
clear_hidden_files(image_dir)
yolo_labels_dir = os.path.join(work_sapce_dir, "YOLO/")
if not os.path.isdir(yolo_labels_dir):os.mkdir(yolo_labels_dir)
clear_hidden_files(yolo_labels_dir)
yolov5_images_dir = os.path.join(data_base_dir, "images/")
if not os.path.isdir(yolov5_images_dir):os.mkdir(yolov5_images_dir)
clear_hidden_files(yolov5_images_dir)
yolov5_labels_dir = os.path.join(data_base_dir, "labels/")
if not os.path.isdir(yolov5_labels_dir):os.mkdir(yolov5_labels_dir)
clear_hidden_files(yolov5_labels_dir)
yolov5_images_train_dir = os.path.join(yolov5_images_dir, "train/")
if not os.path.isdir(yolov5_images_train_dir):os.mkdir(yolov5_images_train_dir)
clear_hidden_files(yolov5_images_train_dir)
yolov5_images_val_dir = os.path.join(yolov5_images_dir, "val/")
if not os.path.isdir(yolov5_images_val_dir):os.mkdir(yolov5_images_val_dir)
clear_hidden_files(yolov5_images_val_dir)
yolov5_images_test_dir = os.path.join(yolov5_images_dir, "test/")
if not os.path.isdir(yolov5_images_test_dir):os.mkdir(yolov5_images_test_dir)
clear_hidden_files(yolov5_images_test_dir)
yolov5_labels_train_dir = os.path.join(yolov5_labels_dir, "train/")
if not os.path.isdir(yolov5_labels_train_dir):os.mkdir(yolov5_labels_train_dir)
clear_hidden_files(yolov5_labels_train_dir)
yolov5_labels_val_dir = os.path.join(yolov5_labels_dir, "val/")
if not os.path.isdir(yolov5_labels_val_dir):os.mkdir(yolov5_labels_val_dir)
clear_hidden_files(yolov5_labels_val_dir)
yolov5_labels_test_dir = os.path.join(yolov5_labels_dir, "test/")
if not os.path.isdir(yolov5_labels_test_dir):os.mkdir(yolov5_labels_test_dir)
clear_hidden_files(yolov5_labels_test_dir)train_file = open(os.path.join(wd, "yolov5_train.txt"), 'w')
val_file = open(os.path.join(wd, "yolov5_val.txt"), 'w')
test_file = open(os.path.join(wd, "yolov5_test.txt"), 'w')
train_file.close()
val_file.close()
test_file.close()
train_file = open(os.path.join(wd, "yolov5_train.txt"), 'a')
val_file = open(os.path.join(wd, "yolov5_val.txt"), 'a')
test_file = open(os.path.join(wd, "yolov5_test.txt"), 'a')
list_imgs = os.listdir(image_dir) # list image files
for i in range(0,len(list_imgs)):path = os.path.join(image_dir,list_imgs[i])if os.path.isfile(path):image_path = image_dir + list_imgs[i]voc_path = list_imgs[i](nameWithoutExtention, extention) = os.path.splitext(os.path.basename(image_path))(voc_nameWithoutExtention, voc_extention) = os.path.splitext(os.path.basename(voc_path))annotation_name = nameWithoutExtention + '.xml'annotation_path = os.path.join(annotation_dir, annotation_name)label_name = nameWithoutExtention + '.txt'label_path = os.path.join(yolo_labels_dir, label_name)if(nameWithoutExtention.startswith("test_00003")): # test datasetif os.path.exists(annotation_path):val_file.write(image_path + '\n')convert_annotation(nameWithoutExtention) # convert labelcopyfile(image_path, yolov5_images_val_dir + voc_path)copyfile(label_path, yolov5_labels_val_dir + label_name)elif(nameWithoutExtention.startswith("test_00004")):if os.path.exists(annotation_path):test_file.write(image_path + '\n')convert_annotation(nameWithoutExtention) # convert labelcopyfile(image_path, yolov5_images_test_dir + voc_path)copyfile(label_path, yolov5_labels_test_dir + label_name)else: # train datasetif os.path.exists(annotation_path):train_file.write(image_path + '\n')convert_annotation(nameWithoutExtention) # convert labelcopyfile(image_path, yolov5_images_train_dir + voc_path)copyfile(label_path, yolov5_labels_train_dir + label_name)train_file.close()
val_file.close()
test_file.close()

划分后文件结构如图所示，在VOCdevkit下生成了images与labels文件夹分别存放图片和yolo标签文件。
在这里插入图片描述
images下文件结构如图所示，test、train、val文件夹用以存放不同类型的数据集图片，labels文件夹同理

在这里插入图片描述

4 模型训练

4.1 下载yolov5预训练模型

同样在github的yolov5官网release页面可找到发布的预训练模型，如图所示。使用预训练模型能加快训练速度。实验中选择最基础的yolo5s.pt，精度更高的预训练模型需要更长的训练时间，实验中选择5s即可。
在这里插入图片描述
将下载后的模型放入weights目录下，如图所示

4.2 更改配置文件

4.2.1 修改模型配置文件

本着不破坏原文件的原则，将我们需要修改的models目录下的yolov5s.yaml复制，重命名为mask.yaml，修改其中nc为2，即改类型数量(number of classes)为2，如图所示
在这里插入图片描述

4.2.2 修改数据集配置文件

接着修改数据集配置文件，复制data下的voco.yaml，也重命名为mask.yaml，修改数据集对应位置，类型数量，类型名字，如图所示
在这里插入图片描述

4.2.3 修改训练代码参数

最后修改train.py中的参数加载修改后的配置，并设置需要的配置，那么训练的配置就已配置完毕

if __name__ == '__main__':parser = argparse.ArgumentParser()parser.add_argument('--weights', type=str, default='weights/yolov5s.pt', help='initial weights path')parser.add_argument('--cfg', type=str, default='models/mask.yaml', help='model.yaml path')parser.add_argument('--data', type=str, default='data/mask.yaml', help='data.yaml path')parser.add_argument('--hyp', type=str, default='data/hyp.scratch.yaml', help='hyperparameters path')parser.add_argument('--epochs', type=int, default=200)parser.add_argument('--batch-size', type=int, default=8, help='total batch size for all GPUs')parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='[train, test] image sizes')parser.add_argument('--rect', action='store_true', help='rectangular training')parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')parser.add_argument('--notest', action='store_true', help='only test final epoch')parser.add_argument('--noautoanchor', action='store_true', help='disable autoanchor check')parser.add_argument('--evolve', action='store_true', help='evolve hyperparameters')parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')parser.add_argument('--cache-images', action='store_true', help='cache images for faster training')parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')parser.add_argument('--adam', action='store_true', help='use torch.optim.Adam() optimizer')parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')parser.add_argument('--workers', type=int, default=8, help='maximum number of dataloader workers')parser.add_argument('--project', default='runs/train', help='save to project/name')parser.add_argument('--entity', default=None, help='W&B entity')parser.add_argument('--name', default='exp', help='save to project/name')parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')parser.add_argument('--quad', action='store_true', help='quad dataloader')parser.add_argument('--linear-lr', action='store_true', help='linear LR')parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')parser.add_argument('--upload_dataset', action='store_true', help='Upload dataset as W&B artifact table')parser.add_argument('--bbox_interval', type=int, default=-1, help='Set bounding-box image logging interval for W&B')parser.add_argument('--save_period', type=int, default=-1, help='Log model after every "save_period" epoch')parser.add_argument('--artifact_alias', type=str, default="latest", help='version of dataset artifact to be used')opt = parser.parse_args()