前言:本文跟随B站up主“炮哥带你学”实现一个入门级的YOLOv5项目
一、环境配置
本文写前已有anaconda并已配置好了pytorch与python环境
二、YOLOv5引入
github上即可将整个项目下载
三、labelimg标注数据集
本文写前,因配置环境时配置的是python3.10环境,因版本过高而导致labelimg使用闪退,故使用conda命令另行创建一个虚拟环境以下载labelimg
首先在cmd命令行界面内使用conda命令创建一个使用python3.8的虚拟环境
C:\Users\86186>conda create -n 环境名 python=3.8
接着激活该虚拟环境,准备在该环境下下载labelimg(这里我把虚拟环境命名为labelimg)
C:\Users\86186>conda activate labelimg
而后便会进入该环境
(labelimg) C:\Users\86186>
在该环境下下载labelimg
(labelimg) C:\Users\86186>pip install labelimg -i https://pypi.tuna.tsinghua.edu.cn/simple
下载完之后进入预训练的目标数据集(这里因为是虚拟环境内,cd命令无法直接进入,所以这是偏门的方法,cd命令后直接使用盘符E:进入目标盘才到数据集文件下)
(labelimg) C:\Users\86186>cd "E:\VOC2007"
(labelimg) C:\Users\86186>E:
而后命令行就会这样
(labelimg) E:\VOC2007>
此时便可输入命令打开labelimg了
(labelimg) E:\VOC2007>labelimg JPEGImages predefined_classes.txt
打开大概长这样
进来之后,首先改设置
随后修改图片标注后的保存位置,一般都在数据集文件下
快捷键:
保存标注文件:ctrl+s
A:切换到上一张图片
D:切换到下一张图片
W:调出标注所用十字架
del :删除标注框
Ctrl+u:选择标注的图片文件夹
Ctrl+r:选择标注好的label标签存在的文件夹
enter:选择
四、数据集格式转化与数据集划分
首先介绍一下VOC格式和yolo格式
VOC格式:此处沿用炮哥的图片,其内涵其实也是图片的各项数据与标签,但是较为清晰易懂
yolo格式:打开TXT文件后内容如下,大致上就是是图片进行归一化和数据化后的产物
0 0.512143611404435 0.4130893736805067 0.8975712777191129 0.733286418015482
至于格式转换,这里其实操作都差不多,直接cv然后改个路径比较方便,下为不知道源头是哪的代码,其中最大的注意点就是文件路径和标签名,类名不要出错了
1.VOC转yolo
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
def convert(size, box):
x_center = (box[0] + box[1]) / 2.0
y_center = (box[2] + box[3]) / 2.0
x = x_center / size[0]
y = y_center / size[1]
w = (box[1] - box[0]) / size[0]
h = (box[3] - box[2]) / size[1]
return (x, y, w, h)
def convert_annotation(xml_files_path, save_txt_files_path, classes):
xml_files = os.listdir(xml_files_path)
print(xml_files)
for xml_name in xml_files:
print(xml_name)
xml_file = os.path.join(xml_files_path, xml_name)
out_txt_path = os.path.join(save_txt_files_path, xml_name.split('.')[0] + '.txt')
out_txt_f = open(out_txt_path, 'w')
tree = ET.parse(xml_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))
# b=(xmin, xmax, ymin, ymax)
print(w, h, b)
bb = convert((w, h), b)
out_txt_f.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
if __name__ == "__main__":
# 需要转换的类别,需要一一对应
classes1 = ['boat', 'cat']
# 2、voc格式的xml标签文件路径
xml_files1 = r'C:\Users\86159\Desktop\VOC2007\Annotations'
# 3、转化为yolo格式的txt标签文件存储路径
save_txt_files1 = r'C:\Users\86159\Desktop\VOC2007\label'
convert_annotation(xml_files1, save_txt_files1, classes1)
2.yolo转VOC
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': "boat", # 创建字典用来对类型进行转换
'1': "cat", # 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 = "C:/Users/86159/Desktop/VOC2007/JPEGImage/" # 图片所在文件夹路径,后面的/一定要带上
txtPath = "C:/Users/86159/Desktop/VOC2007/yolo/" # txt所在文件夹路径,后面的/一定要带上
xmlPath = "C:/Users/86159/Desktop/VOC2007/Annotations1/" # xml文件保存路径,后面的/一定要带上
makexml(picPath, txtPath, xmlPath)
3.数据集划分,此处数据集为yolo格式的,且文件构成大致如下:
随后对数据集进行划分
import os, random, shutil
def moveimg(fileDir, tarDir):
pathDir = os.listdir(fileDir) # 取图片的原始路径
filenumber = len(pathDir)
rate = 0.1 # 自定义抽取图片的比例,比方说100张抽10张,那就是0.1
picknumber = int(filenumber * rate) # 按照rate比例从文件夹中取一定数量图片
sample = random.sample(pathDir, picknumber) # 随机选取picknumber数量的样本图片
print(sample)
for name in sample:
shutil.move(fileDir + name, tarDir + "\\" + name)
return
def movelabel(file_list, file_label_train, file_label_val):
for i in file_list:
if i.endswith('.jpg'):
# filename = file_label_train + "\\" + i[:-4] + '.xml' # 可以改成xml文件将’.txt‘改成'.xml'就可以了
filename = file_label_train + "\\" + i[:-4] + '.txt' # 可以改成xml文件将’.txt‘改成'.xml'就可以了
if os.path.exists(filename):
shutil.move(filename, file_label_val)
print(i + "处理成功!")
if __name__ == '__main__':
fileDir = r"C:\Users\86159\Desktop\hat\JPEGImages" + "\\" # 源图片文件夹路径
tarDir = r'C:\Users\86159\Desktop\hat\JPEGImages_val' # 图片移动到新的文件夹路径
moveimg(fileDir, tarDir)
file_list = os.listdir(tarDir)
file_label_train = r"C:\Users\86159\Desktop\hat\Annotations_yolo" # 源图片标签路径
file_label_val = r"C:\Users\86159\Desktop\hat\Annotations_val" # 标签
# 移动到新的文件路径
movelabel(file_list, file_label_train, file_label_val)