- 手上目前拥有数据集是一大坨,没有train,test,val的划分,如图所示
- 目录结构:
|---data
|---dslr
|---images
|---back_pack
|---a.jpg
|---b.jpg
...
- 转换后的格式如图
目录结构为:
|---datanews
|---dslr
|---images
|---test
|---train
|---valid
|---back_pack
|---a.jpg
|---b.jpg
...
- 代码如下:
4.1 先创建同样结构的层级结构
4.2 然后讲原始数据按照比例划分
4.3 移入到对应的文件目录里面
import os, random, shutil
def make_dir(source, target):
'''
创建和源文件相似的文件路径函数
:param source: 源文件位置
:param target: 目标文件位置
'''
dir_names = os.listdir(source)
for names in dir_names:
for i in ['train', 'valid', 'test']:
path = target + '/' + i + '/' + names
if not os.path.exists(path):
os.makedirs(path)
def divideTrainValiTest(source, target):
'''
创建和源文件相似的文件路径
:param source: 源文件位置
:param target: 目标文件位置
'''
pic_name = os.listdir(source)
for classes in pic_name:
pic_classes_name = os.listdir(os.path.join(source, classes))
random.shuffle(pic_classes_name)
train_list = pic_classes_name[0:int(0.8 * len(pic_classes_name))]
valid_list = pic_classes_name[int(0.8 * len(pic_classes_name)):int(0.9 * len(pic_classes_name))]
test_list = pic_classes_name[int(0.9 * len(pic_classes_name)):]
for train_pic in train_list:
shutil.copyfile(source + '/' + classes + '/' + train_pic, target + '/train/' + classes + '/' + train_pic)
for validation_pic in valid_list:
shutil.copyfile(source + '/' + classes + '/' + validation_pic,
target + '/valid/' + classes + '/' + validation_pic)
for test_pic in test_list:
shutil.copyfile(source + '/' + classes + '/' + test_pic, target + '/test/' + classes + '/' + test_pic)
if __name__ == '__main__':
filepath = r'../data/dslr/images'
dist = r'../datanews/dslr/images'
make_dir(filepath, dist)
divideTrainValiTest(filepath, dist)