该文详细介绍了如何使用YOLOv5进行口罩检测，包括下载源码和数据集，创建虚拟环境，配置PyTorch，处理和转换数据，训练模型，以及解决训练中可能遇到的问题。此外，还讲述了如何将VisDrone数据集用于无人机航拍目标检测，数据集划分，预训练权重下载，模型训练和测试的过程。
一、YOLOv5-口罩检测
1.准备工作
(1)下载yolov5源码
◼ github官网地址：yolov5
◼ 百度网盘链接(提取码：8888)
(2)下载mask数据集
◼ 百度网盘链接(提取码：8888)
2.创建虚拟环境并配置
◼ 打开Anaconda Prompt，创建虚拟环境
conda create -n yolov5 python==3.8
◼ 打开项目，并配置虚拟环境
3.第三方库的下载
(1)下载PyTorch
◼ 打开Anaconda Prompt,进入创建的虚拟环境conda activate yolov5,输入命令（如下是上图配置的命令）
conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia
(2)其他库
部分第三方库下载失败：
(1)先在终端运行：
pip install -r requirements.txt(2)上述运行后报错：
command ‘pip install ‘pycocotools>=2.0’’ returned non-zero exit status 1.◼ 下载 vs_BuildTools.exe (提取码：8888)
◼ 打开后选这两个下载
◼ 下载成功后，再执行一下(1)
4.数据集划分
(1)在根目录下创建文件夹
◼ 创建文件夹VOCdevkit > VOCdevkit > Annotations
├── yolov-5
└── VOCdevkit
└── VOC2007
└── Annotations
◼ 将解压后的数据集中的 images 文件夹和 labels 文件夹拖到 VOC2007
├── yolov-5
└── VOCdevkit
└── VOC2007
├──Annotations
├──images
└──labels
◼ 在 images 和 labels 文件夹中分别删除 test_00000306
(2)先转换成xml标签
◼ 在根目录下创建一个 python 文件，并运行
# coding=utf-8
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': "hat", # 创建字典用来对类型进行转换
'1': "person", # 此处的字典要与自己的classes.txt文件中的类对应，且顺序要一致
}
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.shape
folder = 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width
widthcontent = 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height
heightcontent = 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depth
depthcontent = 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/images/" # 图片所在文件夹路径，后面的/一定要带上
txtPath = "VOCdevkit/VOC2007/labels/" # txt所在文件夹路径，后面的/一定要带上
xmlPath = "VOCdevkit/VOC2007/Annotations/" # xml文件保存路径，后面的/一定要带上
makexml(picPath, txtPath, xmlPath)
(3)再划分数据集
◼ 在根目录下创建一个 python 文件，并运行
# coding=utf-8
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
import random
from shutil import copyfile
classes = ["hat", "person"]
# classes=["ball"]
TRAIN_RATIO = 80 #训练集和验证集的比例，说明80%的训练集，20%的验证集
def 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]) / 2.0
y = (box[2] + box[3]) / 2.0
w = box[1] - box[0]
h = box[3] - box[2]
x = x * dw
w = w * dw
y = y * dh
h = h * dh
return (x, y, w, h)
def convert_annotation(image_id):
in_file = open('VOCdevkit/VOC2007/Annotations/%s.xml' % image_id)
out_file = open('VOCdevkit/VOC2007/labels/%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').text
cls = obj.find('name').text
if cls not in classes or int(difficult) == 1:
continue
cls_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, "images/")
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, "labels/")
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_test_dir = os.path.join(yolov5_images_dir, "val/")
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_test_dir = os.path.join(yolov5_labels_dir, "val/")
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')
test_file = open(os.path.join(wd, "yolov5_val.txt"), 'w')
train_file.close()
test_file.close()
train_file = open(os.path.join(wd, "yolov5_train.txt"), 'a')
test_file = open(os.path.join(wd, "yolov5_val.txt"), 'a')
list_imgs = os.listdir(image_dir) # list image files
prob = random.randint(1, 100)
print("Probability: %d" % prob)
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)
prob = random.randint(1, 100)
print("Probability: %d" % prob)
if (prob < TRAIN_RATIO): # train dataset
if os.path.exists(annotation_path):
train_file.write(image_path + '\n')
convert_annotation(nameWithoutExtention) # convert label
copyfile(image_path, yolov5_images_train_dir + voc_path)
copyfile(label_path, yolov5_labels_train_dir + label_name)
else: # test dataset
if os.path.exists(annotation_path):
test_file.write(image_path + '\n')
convert_annotation(nameWithoutExtention) # convert label
copyfile(image_path, yolov5_images_test_dir + voc_path)
copyfile(label_path, yolov5_labels_test_dir + label_name)
train_file.close()
test_file.close()
5.训练
(1)预训练权重配置
◼ github下载
◼ 百度网盘链接(提取码：8888)
◼ 下载后放到 weights 文件夹下 (本次训练用到yolov5s.pt)
(2)数据集配置
◼ 任意复制一个.yaml文件,改名为mask
# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC/
# Train command: python train.py --data voc.yaml
# Default dataset location is next to /yolov5:
# /parent_folder
# /VOC
# /yolov5
# download command/URL (optional)
download: bash data/scripts/get_voc.sh
# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
train: VOCdevkit/images/train # 597 images 划分的训练集的路径
val: VOCdevkit/images/val # 144 images 划分的验证集的路径
# number of classes
nc: 2 #检测的类别数
# class names
names: ['no-mask','mask'] #标签类别的名
(3)模型配置
◼ 预训练权重选择的是ylov5s.pt对应 models 模型应该选择yolov5s.yaml
◼ 为了不修改官方给的yolov5s.yaml，这里复制yolov5s.yaml，改名为mask
◼ 将yolov5s.yaml的代码复制到mask.yaml，修改检测的类别数 nc:2
(4)训练
◼ 打开 train 文件找到 main 函数，修改路径
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')
◼ 修改完后，就可以开始训练啦~
6.可能会遇到的报错
◼ github 上 yolo 的源代码会不断更新，许多 bug 可能不会遇到，如下是之前版本遇到的 bug ，希望有帮助~
(1)UnicodeDecodeError
◼ 报错：UnicodeDecodeError: 'gbk' codec can't decode byte 0xae in position 454: illegal multibyte sequence
◼ 解决：在 train.py 如下位置添加encoding='utf-8'
# Save run settings
with open(save_dir / 'hyp.yaml', 'w', encoding='utf-8') as f:
yaml.dump(hyp, f, sort_keys=False)
with open(save_dir / 'opt.yaml', 'w', encoding='utf-8') as f:
yaml.dump(vars(opt), f, sort_keys=False)
# Configure
plots = not opt.evolve # create plots
cuda = device.type = 'cpu'
init_seeds(2 + rank)
with open(opt.data, encoding='utf-8') as f:
data_dict = yaml.load(f, Loader=yaml.SafeLoader) # data dict
is_coco = opt.data.endswith('coco.yaml')
# Hyperparameters
with open(opt.hyp, encoding='utf-8') as f:
hyp = yaml.load(f, Loader=yaml.SafeLoader) # load hyps
(2)AttributeError
◼ 报错：AttributeError: module 'numpy' has no attribute 'int'
◼ 解决：将np.int修改为np.int_(修改如下两个文件中的np.int)
(3)RuntimeError
◼ 报错：RuntimeError: result type Float can't be cast to the desired output type _int64
◼ 解决：如图所示，修改两个地方
anchors, shape = self.anchors[i], p[i].shape
gain[2:6] = torch.tensor(p[i].shape)[[3, 2, 3, 2]] # xyxy gain
# Append
a = t[:, 6].long() # anchor indices
indices.append((b, a, gj.clamp_(0, shape[2] - 1), gi.clamp_(0, shape[3] - 1)))
7.测试
◼ 训练完后，会生成两个权重文件best.pt和last.pt，测试时使用best.pt
注意：train 下可能有多个 exp 文件夹，有的是运行 train.py 报错时产生的，weights 文件夹中没有权重文件（可删除）
(1)测试图片
◼ 测试图片存放路径如下
(2)修改权重和数据源
◼ 打开根目录下的detect.py文件，找到main函数设置权重的路径和测试图片路径
parser.add_argument('--weights', nargs='+', type=str, default='runs/train/exp/weights/best.pt', help='model.pt path(s)')
parser.add_argument('--source', type=str, default='data/images/mask', help='source')
◼ 修改后，就可以运行程序啦~（预测的图片会存放到runs/detect/exp）
二、YOLOv5-无人机航拍
1.准备工作
◼ 下载VisDrone数据集
◼百度网盘链接 (提取码：8888)
2.划分数据集
◼ 将数据集解压，拖到项目根目录下，如图
◼ 在根目录下创建一个 python 文件，并运行
from utils.general import os, Path
def visdrone2yolo(dir):
from PIL import Image
from tqdm import tqdm
def convert_box(size, box):
# Convert VisDrone box to YOLO xywh box
dw = 1. / size[0]
dh = 1. / size[1]
return (box[0] + box[2] / 2) * dw, (box[1] + box[3] / 2) * dh, box[2] * dw, box[3] * dh
(dir / 'labels').mkdir(parents=True, exist_ok=True) # make labels directory
pbar = tqdm((dir / 'annotations').glob('*.txt'), desc=f'Converting {dir}')
for f in pbar:
img_size = Image.open((dir / 'images' / f.name).with_suffix('.jpg')).size
lines = []
with open(f, 'r') as file: # read annotation.txt
for row in [x.split(',') for x in file.read().strip().splitlines()]:
if row[4] == '0': # VisDrone 'ignored regions' class 0
continue
cls = int(row[5]) - 1 # 类别号-1
box = convert_box(img_size, tuple(map(int, row[:4])))
lines.append(f"{cls} {' '.join(f'{x:.6f}' for x in box)}\n")
with open(str(f).replace(os.sep + 'annotations' + os.sep, os.sep + 'labels' + os.sep), 'w') as fl:
fl.writelines(lines) # write label.txt
dir = Path('VisDrone') # datasets文件夹下Visdrone2019文件夹目录
# Convert
for d in 'VisDrone2019-DET-train', 'VisDrone2019-DET-val', 'VisDrone2019-DET-test-dev':
visdrone2yolo(dir / d) # convert VisDrone annotations to YOLO labels
◼ 运行成功后，生成对应的labels文件夹
3.训练
(1)预训练权重下载
◼ github下载
◼ 百度网盘链接(提取码：8888)
◼ 下载后放到 weights 文件夹下 (本次训练用到yolov5l.pt)
(2)数据集配置
◼ 任意复制一个.yaml文件,改名为VisDrone
train: VisDrone/VisDrone2019-DET-train/images # train images (relative to 'path') 6471 images
val: VisDrone/VisDrone2019-DET-val/images # val images (relative to 'path') 548 images
test: VisDrone/VisDrone2019-DET-test-dev/images # test images (optional) 1610 images
# Classes
nc: 10 # number of classes
names: [ 'pedestrian', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', 'awning-tricycle', 'bus', 'motor' ]
(3)测试
parser.add_argument('--weights', type=str, default='weights/yolov5l.pt', help='initial weights path')
parser.add_argument('--cfg', type=str, default='models/yolov5l.yaml', help='model.yaml path')
parser.add_argument('--data', type=str, default='data/VisDrone.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=100)
parser.add_argument('--batch-size', type=int, default=2, help='total batch size for all GPUs')
parser.add_argument('--img-size', nargs='+', type=int, default=[960, 960], help='[train, test] image sizes')
parser.add_argument('--project', default='runs/train2', help='save to project/name')
4.测试
◼ 测试图片存放的位置
◼ 打开根目录下的detect.py文件，找到main函数设置权重的路径和测试图片路径
parser.add_argument('--weights', nargs='+', type=str, default='runs/train2/exp/weights/best.pt', help='model.pt path(s)')
parser.add_argument('--source', type=str, default='data/images/VisDrone', help='source') # file/folder, 0 for webcam
◼ 修改后，就可以运行程序啦~（预测的图片会存放到runs/detect/exp）
253
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
