深度学习划分数据集

最新推荐文章于 2024-08-04 02:35:58 发布

monbry

最新推荐文章于 2024-08-04 02:35:58 发布

阅读量258

点赞数

文章标签：神经网络深度学习

本文链接：https://blog.csdn.net/monbry/article/details/116929957

版权

# 数据集划分
import os
import random

root_dir = 'C:\deep-learning-for-image-processing-master\pytorch_object_detection\ssd\VOCdevkit\VOC2012\\'

## 0.35train 0.35val 0.3test
trainval_percent = 0.7
train_percent = 0.35
xmlfilepath = root_dir + 'Annotations'
txtsavepath = root_dir + 'ImageSets/Main'
total_xml = os.listdir(xmlfilepath)

num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
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()