目标检测数据集划分篇

数据集划分单纯数据集划分不进行标签转换

8；1；1划分train val test

并保存到train.txt/ val.txt /test.txt

---

数据集划分

在 VOCdevkit 目录下创建split.py，运行之后会在 Main 文件夹下生成三个个txt文件：

 train.txt、val.txt、test.txt

# -*- 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=r'F:\dataset\underwater\URPC\new\urpc2020\labels', 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=r'F:\dataset\underwater\URPC\new\urpc2020\Imagesets\Main', 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()