PASCAL VOC数据集训练集、验证集、测试集的划分和提取，得到test.txt、train.txt、trainval.txt、val.txt文件代码

训练集、验证集、测试集按比例精确划分

创建py文件，将下属代码放入所创建的文件里，VOC2007数据集与py文件在同一目录下

# 数据集划分
import os
import random

root_dir = './VOC2007/'


## trainval_percent为 train 与 val在整个数据集中的比例
trainval_percent = 0.8
# train_percent 为 train在整个数据集中的比例
train_percent = 0.7
# 因此上述配置得到
## 0.7train 0.1val 0.2test


xmlfilepath = root_dir + 'Annotations'
txtsavepath = root_dir + 'ImageSets/Main'
total_xml = os.listdir(xmlfilepath)

num = len(total_xml)  # 100
list = range(num)
tv = int(num * trainval_percent)  # 80
tr = int(tv * train_percent)  # 80*0.7=56
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)

ftrainval = open(root_dir + 'ImageSets/Main/trainval.txt', 'w')
ftest = open(root_dir + 'ImageSets/Main/test.txt', 'w')
ftrain = open(root_dir + 'ImageSets/Main/train.txt', 'w')
fval = open(root_dir + 'ImageSets/Main/val.txt', 'w')

for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        ftrainval.write(name)
        if i in train:
            ftrain.write(name)
        else:
            fval.write(name)
    else:
        ftest.write(name)

ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

实验结果