xml2txt:
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import copy
from lxml.etree import Element, SubElement, tostring, ElementTree
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
classes = ["white"] # 类别
CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))
def convert(size, box):
dw = 1. / size[0]
dh = 1. / size[1]
x = (box[0] + box[1]) / 2.0 # (x_min + x_max) / 2.0
y = (box[2] + box[3]) / 2.0 # (y_min + y_max) / 2.0
w = box[1] - box[0] # x_max - x_min
h = box[3] - box[2] # y_max - y_min
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('D:\python_project\yolov5-master\yolov5-master\data\data1\labels\%s.xml' % (image_id), encoding='UTF-8')
out_file = open('D:\python_project\yolov5-master\yolov5-master\data\data1\lable_txt\%s.txt' % (image_id), 'w') # 生成txt格式文件
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'):
cls = obj.find('name').text
# print(cls)
if cls not in classes:
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')
xml_path = os.path.join(CURRENT_DIR, 'D:\python_project\yolov5-master\yolov5-master\data\data1\labels/')
# xml list
img_xmls = os.listdir(xml_path)
for img_xml in img_xmls:
label_name = img_xml.split('.')[0]
print(label_name)
convert_annotation(label_name)
txt2xml:
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': "0", # 创建字典用来对类型进行转换
'1': "1",
'2': "2",# 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] + ".bmp")
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] + ".bmp")
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 = "E:\python_project\yolov5-master\zengqiang\data\images/" # 图片所在文件夹路径,后面的/一定要带上
txtPath = "E:\python_project\yolov5-master\zengqiang\data\labels/" # txt所在文件夹路径,后面的/一定要带上
xmlPath = "E:\python_project\yolov5-master\zengqiang\Annotations/" # xml文件保存路径,后面的/一定要带上
makexml(picPath, txtPath, xmlPath)
dataSplit :
import os
import random
from shutil import copyfile
def split_dataset(image_folder, txt_folder, output_folder, split_ratio=(0.8, 0.2, 0)):
# Ensure output folders exist
for dataset in ['train', 'val', 'test']:
if not os.path.exists(os.path.join(output_folder, dataset, 'images')):
os.makedirs(os.path.join(output_folder, dataset, 'images'))
if not os.path.exists(os.path.join(output_folder, dataset, 'txt')):
os.makedirs(os.path.join(output_folder, dataset, 'txt'))
# Get list of image files
image_files = [f for f in os.listdir(image_folder) if f.endswith(('.jpg', '.jpeg', '.png','.bmp'))]
random.shuffle(image_files)
num_images = len(image_files)
num_train = int(split_ratio[0] * num_images)
num_val = int(split_ratio[1] * num_images)
train_images = image_files[:num_train]
val_images = image_files[num_train:num_train + num_val]
test_images = image_files[num_train + num_val:]
# Copy images to respective folders
for dataset, images_list in zip(['train', 'val', 'test'], [train_images, val_images, test_images]):
for image_file in images_list:
image_path = os.path.join(image_folder, image_file)
copyfile(image_path, os.path.join(output_folder, dataset, 'images', image_file))
txt_file = os.path.splitext(image_file)[0] + '.txt'
txt_path = os.path.join(txt_folder, txt_file)
# Copy corresponding txt file if exists
if os.path.exists(txt_path):
copyfile(txt_path, os.path.join(output_folder, dataset, 'txt', txt_file))
if __name__ == "__main__":
image_folder_path = r"E:\PythonProjects\yolov5-master\data\ImageSets\images"
txt_folder_path = r"E:\PythonProjects\yolov5-master\data\ImageSets\labels"
output_dataset_path = r"E:\PythonProjects\yolov5-master\data\ImageSets\data"
split_dataset(image_folder_path, txt_folder_path, output_dataset_path)
带标签图像增强:
'''
Author: CodingWZP
Email: codingwzp@gmail.com
Date: 2021-08-06 10:51:35
LastEditTime: 2021-08-09 10:53:43
Description: Image augmentation with label.
'''
import xml.etree.ElementTree as ET
import os
import imgaug as ia
import numpy as np
import shutil
from tqdm import tqdm
from PIL import Image
from imgaug import augmenters as iaa
ia.seed(1)
def read_xml_annotation(root, image_id):
in_file = open(os.path.join(root, image_id))
tree = ET.parse(in_file)
root = tree.getroot()
bndboxlist = []
for object in root.findall('object'): # 找到root节点下的所有country节点
bndbox = object.find('bndbox') # 子节点下节点rank的值
xmin = int(bndbox.find('xmin').text)
xmax = int(bndbox.find('xmax').text)
ymin = int(bndbox.find('ymin').text)
ymax = int(bndbox.find('ymax').text)
# print(xmin,ymin,xmax,ymax)
bndboxlist.append([xmin, ymin, xmax, ymax])
# print(bndboxlist)
bndbox = root.find('object').find('bndbox')
return bndboxlist
def change_xml_list_annotation(root, image_id, new_target, saveroot, id):
in_file = open(os.path.join(root, str(image_id) + '.xml')) # 这里root分别由两个意思
tree = ET.parse(in_file)
# 修改增强后的xml文件中的filename
elem = tree.find('filename')
elem.text = (str(id) + '.jpg')
xmlroot = tree.getroot()
# 修改增强后的xml文件中的path
elem = tree.find('path')
if elem != None:
elem.text = (saveroot + str(id) + '.jpg')
index = 0
for object in xmlroot.findall('object'): # 找到root节点下的所有country节点
bndbox = object.find('bndbox') # 子节点下节点rank的值
# xmin = int(bndbox.find('xmin').text)
# xmax = int(bndbox.find('xmax').text)
# ymin = int(bndbox.find('ymin').text)
# ymax = int(bndbox.find('ymax').text)
new_xmin = new_target[index][0]
new_ymin = new_target[index][1]
new_xmax = new_target[index][2]
new_ymax = new_target[index][3]
xmin = bndbox.find('xmin')
xmin.text = str(new_xmin)
ymin = bndbox.find('ymin')
ymin.text = str(new_ymin)
xmax = bndbox.find('xmax')
xmax.text = str(new_xmax)
ymax = bndbox.find('ymax')
ymax.text = str(new_ymax)
index = index + 1
tree.write(os.path.join(saveroot, str(id + '.xml')))
def mkdir(path):
# 去除首位空格
path = path.strip()
# 去除尾部 \ 符号
path = path.rstrip("\\")
# 判断路径是否存在
# 存在 True
# 不存在 False
isExists = os.path.exists(path)
# 判断结果
if not isExists:
# 如果不存在则创建目录
# 创建目录操作函数
os.makedirs(path)
print(path + ' 创建成功')
return True
else:
# 如果目录存在则不创建,并提示目录已存在
print(path + ' 目录已存在')
return False
if __name__ == "__main__":
IMG_DIR = r"E:\PythonProjects\yolov5-master\data\data1\images"
XML_DIR = r"E:\PythonProjects\yolov5-master\data\data1\Annotations"
AUG_XML_DIR = r"E:\PythonProjects\yolov5-master\data\data1\data1\xml" # 存储增强后的XML文件夹路径
try:
shutil.rmtree(AUG_XML_DIR)
except FileNotFoundError as e:
a = 1
mkdir(AUG_XML_DIR)
AUG_IMG_DIR = r"E:\PythonProjects\yolov5-master\data\data1\data1\img" # 存储增强后的影像文件夹路径
try:
shutil.rmtree(AUG_IMG_DIR)
except FileNotFoundError as e:
a = 1
mkdir(AUG_IMG_DIR)
AUGLOOP = 1 # 每张影像增强的数量
boxes_img_aug_list = []
new_bndbox = []
new_bndbox_list = []
# 影像增强
seq = iaa.Sequential([
# iaa.Invert(1),
iaa.Fliplr(1), # 镜像
# iaa.Multiply((1.2, 1.5)), # change brightness, doesn't affect BBs
# iaa.GaussianBlur(sigma=(0, 3.0)), # iaa.GaussianBlur(0.5),
# iaa.Affine(
# translate_px={"x": 15, "y": 15},
# scale=(0.8, 0.95),
# ) # translate by 40/60px on x/y axis, and scale to 50-70%, affects BBs
])
for name in tqdm(os.listdir(XML_DIR), desc='Processing'):
bndbox = read_xml_annotation(XML_DIR, name)
# 保存原xml文件
shutil.copy(os.path.join(XML_DIR, name), AUG_XML_DIR)
# 保存原图
og_img = Image.open(IMG_DIR + '/' + name[:-4] + '.jpg')
og_img.convert('RGB').save(AUG_IMG_DIR + name[:-4] + '.jpg', 'JPEG')
og_xml = open(os.path.join(XML_DIR, name))
tree = ET.parse(og_xml)
# 修改增强后的xml文件中的filename
elem = tree.find('filename')
elem.text = (name[:-4] + '.jpg')
tree.write(os.path.join(AUG_XML_DIR, name))
for epoch in range(AUGLOOP):
seq_det = seq.to_deterministic() # 保持坐标和图像同步改变,而不是随机
# 读取图片
img = Image.open(os.path.join(IMG_DIR, name[:-4] + '.jpg'))
# sp = img.size
img = np.asarray(img)
# bndbox 坐标增强
for i in range(len(bndbox)):
bbs = ia.BoundingBoxesOnImage([
ia.BoundingBox(x1=bndbox[i][0], y1=bndbox[i][1], x2=bndbox[i][2], y2=bndbox[i][3]),
], shape=img.shape)
bbs_aug = seq_det.augment_bounding_boxes([bbs])[0]
boxes_img_aug_list.append(bbs_aug)
# new_bndbox_list:[[x1,y1,x2,y2],...[],[]]
n_x1 = int(max(1, min(img.shape[1], bbs_aug.bounding_boxes[0].x1)))
n_y1 = int(max(1, min(img.shape[0], bbs_aug.bounding_boxes[0].y1)))
n_x2 = int(max(1, min(img.shape[1], bbs_aug.bounding_boxes[0].x2)))
n_y2 = int(max(1, min(img.shape[0], bbs_aug.bounding_boxes[0].y2)))
if n_x1 == 1 and n_x1 == n_x2:
n_x2 += 1
if n_y1 == 1 and n_y2 == n_y1:
n_y2 += 1
if n_x1 >= n_x2 or n_y1 >= n_y2:
print('error', name)
new_bndbox_list.append([n_x1, n_y1, n_x2, n_y2])
# 存储变化后的图片
image_aug = seq_det.augment_images([img])[0]
path = os.path.join(AUG_IMG_DIR,
str(str(name[:-4]) + '_' + str(epoch)) + '.jpg')
image_auged = bbs.draw_on_image(image_aug, size=0)
Image.fromarray(image_auged).convert('RGB').save(path)
# 存储变化后的XML
change_xml_list_annotation(XML_DIR, name[:-4], new_bndbox_list, AUG_XML_DIR,
str(name[:-4]) + '_' + str(epoch))
# print(str(str(name[:-4]) + '_' + str(epoch)) + '.jpg')
new_bndbox_list = []
print('Finish!')
批量修改图像后缀
import os
# 设置要处理的文件夹路径
folder_path = r'E:\PythonProjects\yolov5-master\data\data1\images'
# 获取文件夹中所有文件的文件名
file_names = [f for f in os.listdir(folder_path) if os.path.isfile(os.path.join(folder_path, f))]
# 筛选出jpg文件
jpg_files = [f for f in file_names if f.lower().endswith('.png')]
# 将jpg文件改为png格式
for jpg_file in jpg_files:
old_file_path = os.path.join(folder_path, jpg_file)
new_file_path = os.path.join(folder_path, os.path.splitext(jpg_file)[0] + '.jpg')
os.rename(old_file_path, new_file_path)
print('所有jpg文件已经更改为png格式')
------------------------------------------------------2024.7.25 持续更新