基于NEU-DET数据集构建用于yolov7训练的数据集（也适用于其他需要转换xml为txt标签文件的数据集）

目录

1. 将xml文件转为txt文件

（1）对于net-det数据集，需要更改的参数有：

（2）对于其他数据集，还需要修改数据集的标签类别classes：

（3）空白txt文件原因

2. 划分imags文件和labels文件

（1）需要修改的参数

---

1. 将xml文件转为txt文件

import xml.etree.ElementTree as ET

import pickle
import os
from os import listdir, getcwd
from os.path import join
import glob

classes = ["crazing","inclusion","patches","pitted_surface","rolled-in_scale","scratches"]


def convert(size, box):
    dw = 1.0 / size[0]
    dh = 1.0 / 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_name):
    in_file = open('./mydata/neu/lable/' + image_name[:-3] + 'xml')  # xml文件路径
    out_file = open('./mydata/neu/labels/' + image_name[:-3] + 'txt', 'w')  # 转换后的txt文件存放路径
    f = open('./mydata/neu/lable/' + image_name[:-3] + 'xml')
    xml_text = f.read()
    root = ET.fromstring(xml_text)
    f.close()
    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
        if cls not in classes:
            print(cls)
            print(image_name)
            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')


wd = getcwd()

if __name__ == '__main__':

    for image_path in glob.glob("./mydata/neu/images/*.jpg"):  # 每一张图片都对应一个xml文件这里写xml对应的图片的路径
        image_name = image_path.split('/')[-1]
        convert_annotation(image_name)

（1）对于net-det数据集，需要更改的参数有：

①convert_annotation函数中xml文件夹的路径和要生成的txt文件夹的路径

②主函数中图片文件夹的路径和后缀（jpg、bmp等）

（2）对于其他数据集，还需要修改数据集的标签类别classes：

要知道数据集的标签类别，可以打开xml文件查看：

（3）空白txt文件原因

生成完成后，记得查看生成的txt标签文件是否有0KB的空白文件，有的话原因可能是：

①图片本身没有标注

②标签类别写错了

2. 划分imags文件和labels文件

# 将图片和标注数据按比例切分为 训练集和测试集
import shutil
import random
import os

# 原始路径
image_original_path = "./mydata/neu/images/"
label_original_path = "./mydata/neu/labels/"

cur_path = os.getcwd()

# 训练集路径
train_image_path = os.path.join(cur_path, "datasets/defect/images/train/")
train_label_path = os.path.join(cur_path, "datasets/defect/labels/train/")

# 验证集路径
val_image_path = os.path.join(cur_path, "datasets/defect/images/val/")
val_label_path = os.path.join(cur_path, "datasets/defect/labels/val/")

# 测试集路径
test_image_path = os.path.join(cur_path, "datasets/defect/images/test/")
test_label_path = os.path.join(cur_path, "datasets/defect/labels/test/")

# 训练集目录
list_train = os.path.join(cur_path, "datasets/defect/train.txt")
list_val = os.path.join(cur_path, "datasets/defect/val.txt")
list_test = os.path.join(cur_path, "datasets/defect/test.txt")

train_percent = 0.8
val_percent = 0.1
test_percent = 0.1


def del_file(path):
    for i in os.listdir(path):
        file_data = path  + i
        os.remove(file_data)


def mkdir():
    if not os.path.exists(train_image_path):
        os.makedirs(train_image_path)
    else:
        del_file(train_image_path)
    if not os.path.exists(train_label_path):
        os.makedirs(train_label_path)
    else:
        del_file(train_label_path)

    if not os.path.exists(val_image_path):
        os.makedirs(val_image_path)
    else:
        del_file(val_image_path)
    if not os.path.exists(val_label_path):
        os.makedirs(val_label_path)
    else:
        del_file(val_label_path)

    if not os.path.exists(test_image_path):
        os.makedirs(test_image_path)
    else:
        del_file(test_image_path)
    if not os.path.exists(test_label_path):
        os.makedirs(test_label_path)
    else:
        del_file(test_label_path)


def clearfile():
    if os.path.exists(list_train):
        os.remove(list_train)
    if os.path.exists(list_val):
        os.remove(list_val)
    if os.path.exists(list_test):
        os.remove(list_test)


def main():
    mkdir()
    clearfile()

    file_train = open(list_train, 'w')
    file_val = open(list_val, 'w')
    file_test = open(list_test, 'w')

    total_txt = os.listdir(label_original_path)
    num_txt = len(total_txt)
    list_all_txt = range(num_txt)

    num_train = int(num_txt * train_percent)
    num_val = int(num_txt * val_percent)
    num_test = num_txt - num_train - num_val

    train = random.sample(list_all_txt, num_train)
    # train从list_all_txt取出num_train个元素
    # 所以list_all_txt列表只剩下了这些元素
    val_test = [i for i in list_all_txt if not i in train]
    # 再从val_test取出num_val个元素，val_test剩下的元素就是test
    val = random.sample(val_test, num_val)

    print("训练集数目：{}, 验证集数目：{}, 测试集数目：{}".format(len(train), len(val), len(val_test) - len(val)))
    for i in list_all_txt:
        name = total_txt[i][:-4]

        srcImage = image_original_path + name + '.jpg'
        srcLabel = label_original_path + name + ".txt"

        if i in train:
            dst_train_Image = train_image_path + name + '.jpg'
            dst_train_Label = train_label_path + name + '.txt'
            shutil.copyfile(srcImage, dst_train_Image)
            shutil.copyfile(srcLabel, dst_train_Label)
            file_train.write(dst_train_Image + '\n')
        elif i in val:
            dst_val_Image = val_image_path + name + '.jpg'
            dst_val_Label = val_label_path + name + '.txt'
            shutil.copyfile(srcImage, dst_val_Image)
            shutil.copyfile(srcLabel, dst_val_Label)
            file_val.write(dst_val_Image + '\n')
        else:
            dst_test_Image = test_image_path + name + '.jpg'
            dst_test_Label = test_label_path + name + '.txt'
            shutil.copyfile(srcImage, dst_test_Image)
            shutil.copyfile(srcLabel, dst_test_Label)
            file_test.write(dst_test_Image + '\n')

    file_train.close()
    file_val.close()
    file_test.close()


if __name__ == "__main__":
    main()

（1）需要修改的参数

①原始路径
设置为数据集的图片和标签文件（txt）所在文件夹。
②训练集路径
设置为数据集生成的训练集的图片和标签文件（txt）所在文件夹。
③验证集路径
设置为数据集生成的验证集的图片和标签文件（txt）所在文件夹。
④测试集路径
设置为数据集生成的测试集的图片和标签文件（txt）所在文件夹。
⑤训练集目录
设置为数据集生成的训练集的图片和标签文件（txt）的索引文件路径。
⑥设置划分比例
train_percent = 0.8
val_percent = 0.1
test_percent = 0.1