数据集划分

 接上一篇xml转txt，接下来进行数据集划分。

# -*- coding: utf-8 -*-
"""
Author:smile
Date:2022/09/11 10：00
顺序：脚本A1
简介：分训练集、验证集和测试集，按照 8：1：1 的比例来分，训练集8，验证集1，测试集1

"""
import os
import random
import argparse

parser = argparse.ArgumentParser()
# xml文件的地址，根据自己的数据进行修改 xml一般存放在Annotations下
parser.add_argument('--xml_path', default='D:/代码/YOLOv8/ultralytics-main/datasets/kitti/D0015/Annotations', type=str, help='input xml label path')
# 数据集的划分，地址选择自己数据下的ImageSets/Main
parser.add_argument('--txt_path', default='D:/代码/YOLOv8/ultralytics-main/datasets/kitti/D0015/ImageSets', type=str, help='output txt label path')
opt = parser.parse_args()

train_percent = 0.8  # 训练集所占比例
val_percent = 0.1  # 验证集所占比例
test_persent = 0.1  # 测试集所占比例

xmlfilepath = opt.xml_path
txtsavepath = opt.txt_path
total_xml = os.listdir(xmlfilepath)

if not os.path.exists(txtsavepath):
    os.makedirs(txtsavepath)

num = len(total_xml)
list = list(range(num))

t_train = int(num * train_percent)
t_val = int(num * val_percent)

train = random.sample(list, t_train)
num1 = len(train)
for i in range(num1):
    list.remove(train[i])

val_test = [i for i in list if not i in train]
val = random.sample(val_test, t_val)
num2 = len(val)
for i in range(num2):
    list.remove(val[i])

file_train = open(txtsavepath + '/train.txt', 'w')
file_val = open(txtsavepath + '/val.txt', 'w')
file_test = open(txtsavepath + '/test.txt', 'w')

for i in train:
    name = total_xml[i][:-4] + '\n'
    file_train.write(name)

for i in val:
    name = total_xml[i][:-4] + '\n'
    file_val.write(name)

for i in list:
    name = total_xml[i][:-4] + '\n'
    file_test.write(name)

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

划分训练集、验证集和测试集，按照 8：1：1 的比例来分，训练集8，验证集1，测试集1。

更改部分包括两点：

第一点：两条路径需要换成自己真实的路径。

第二点：三者比例换成自己打算的。

最终结果为：

接下来，将其具体划分到images和labels文件夹下。

# -*- coding=utf-8 -*-
import xml.etree.ElementTree as ET
import pickle
import os
import shutil
from os import listdir, getcwd
from os.path import join
sets = ['train', 'val', 'test']  # 如果不需要test就不写
classes = ['Car', 'Cyclist', 'Pedestrian']  # 修改成自己数据集的类别
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('Annotations/%s.xml' % (image_id),encoding='utf-8')
    out_file = open('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')
wd = getcwd()
print(wd)
for image_set in sets:
    if not os.path.exists('labels/'):
        os.makedirs('labels/')
    image_ids = open('ImageSets/%s.txt' % (image_set),encoding='utf-8').read().strip().split()
    image_list_file = open('images_%s.txt' % (image_set), 'w',encoding='utf-8')
    labels_list_file=open('labels_%s.txt'%(image_set),'w',encoding='utf-8')
    for image_id in image_ids:
        image_list_file.write('%s.png\n' % (image_id))
        labels_list_file.write('%s.txt\n'%(image_id))
#         convert_annotation(image_id) #如果标签已经是txt格式，将此行注释掉，所有的txt存放到all_labels文件夹。
    image_list_file.close()
    labels_list_file.close()


def copy_file(new_path,path_txt,search_path):#参数1：存放新文件的位置  参数2：为上一步建立好的train,val训练数据的路径txt文件  参数3：为搜索的文件位置
    if not os.path.exists(new_path):
        os.makedirs(new_path)
    with open(path_txt, 'r') as lines:
        filenames_to_copy = set(line.rstrip() for line in lines)
        # print('filenames_to_copy:',filenames_to_copy)
        # print(len(filenames_to_copy))
    for root, _, filenames in os.walk(search_path):
        # print('root',root)
        # print(_)
        # print(filenames)
        for filename in filenames:
            if filename in filenames_to_copy:
                shutil.copy(os.path.join(root, filename), new_path)

#按照划分好的训练文件的路径搜索目标，并将其复制到yolo格式下的新路径
copy_file('./images/train/','./images_train.txt','./all_images')
copy_file('./images/val/','./images_val.txt','./all_images')
copy_file('./images/test/','./images_test.txt','./all_images')
copy_file('./labels/train/','./labels_train.txt','./all_labels')
copy_file('./labels/val/','./labels_val.txt','./all_labels')
copy_file('./labels/test/','./labels_test.txt','./all_labels')

最终结果为：

具体目录格式：