将多个annotation xml文件转换为多个annotation txt文件

简介

• 当我们在使用数据集训练计算机视觉模型时，常常会遇到有的数据集提供了多个annotation xml文件，而YOLO模型所需要的annotation是基于每个图片的txt annotation文件，在这里提供笔者所用的xml文件转txt文件的方法

前期准备

创建项目文件夹

• 新建文件夹用于储存此项目

创建文件夹用于储存图像和xml标签

此处提供两种方法

• 代码法
  • 创建python文件并运行以下代码

    import os
    os.makedirs('VOCdevkit/VOC2007/Annotations')
    os.makedirs('VOCdevkit/VOC2007/JPEGImages')

• 直接法
  • 在项目文件夹内创建文件夹命名为VOCdevkit
  • 在VOCdevkit文件夹内创建文件夹命名为VOC2007
  • 在VOC2007文件夹内创建两个文件夹分别命名为Annotations和JPEGImages
•  成功后如图所示

 导入图像和xml标签 

• 将xml文件全部放入Annotations文件夹下

  

• 将图片全部放入JPEGImages文件夹下

 

进行转换

创建转换代码

• 在项目文件夹下创建python文件并输入以下代码

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


# 根据自己的需求设置类文件
classes = []


# Training ratio
# 根据自己的需求设置训练比
TRAIN_RATIO = 70


# Traversing folders
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)

# Normalization of width and height is performed
# Size is the width and height of the original image
def convert(size, box):
    dw = 1. / size[0]
    dh = 1. / size[1]
    # Get Center Point
    x = (box[0] + box[1]) / 2.0
    y = (box[2] + box[3]) / 2.0
    # Calculate width and height
    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)

# Parsing xml files
def convert_annotation(image_id):
    in_file = open('VOCdevkit/VOC2007/Annotations/%s.xml' % image_id,'rb')
    out_file = open('VOCdevkit/VOC2007/YOLOLabels/%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, "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, "YOLOLabels/")
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_one 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()

• 根据自己的需求设置类和训练比

 运行转换代码

 转换完成

• 转换完成后会在VOCdevkit文件夹下生成images文件夹和labels文件夹，每个文件夹都会根据所设置的训练比生成trian文件夹和val文件夹
• imges文件夹下会储存图片

•  labels文件夹下会储存所需的txt文件

 后续

• 若需要使用YOLO模型进行训练，则可直接复制images文件夹和labels文件夹
• 若只需要使用txt文件，则可复制labels->train和labels->val中的全部txt文件