问如何通过分层抽样将图片文件夹拆分成测试/训练/验证集？

EN

pip install split-folders

import split_folders
split_folders.ratio('Data', output="output", seed=1337, ratio=(.8, 0.1,0.1)) 

import os
import numpy as np
import shutil

# # Creating Train / Val / Test folders (One time use)
root_dir = 'Data2'
posCls = '/DPN+'
negCls = '/DPN-'

os.makedirs(root_dir +'/train' + posCls)
os.makedirs(root_dir +'/train' + negCls)
os.makedirs(root_dir +'/val' + posCls)
os.makedirs(root_dir +'/val' + negCls)
os.makedirs(root_dir +'/test' + posCls)
os.makedirs(root_dir +'/test' + negCls)

# Creating partitions of the data after shuffeling
currentCls = posCls
src = "Data2"+currentCls # Folder to copy images from

allFileNames = os.listdir(src)
np.random.shuffle(allFileNames)
train_FileNames, val_FileNames, test_FileNames = np.split(np.array(allFileNames),
                                                          [int(len(allFileNames)*0.7), int(len(allFileNames)*0.85)])


train_FileNames = [src+'/'+ name for name in train_FileNames.tolist()]
val_FileNames = [src+'/' + name for name in val_FileNames.tolist()]
test_FileNames = [src+'/' + name for name in test_FileNames.tolist()]

print('Total images: ', len(allFileNames))
print('Training: ', len(train_FileNames))
print('Validation: ', len(val_FileNames))
print('Testing: ', len(test_FileNames))

# Copy-pasting images
for name in train_FileNames:
    shutil.copy(name, "Data2/train"+currentCls)

for name in val_FileNames:
    shutil.copy(name, "Data2/val"+currentCls)

for name in test_FileNames:
    shutil.copy(name, "Data2/test"+currentCls)

import os
import numpy as np
import shutil
import pandas as pd


def train_test_split():
    print("########### Train Test Val Script started ###########")
    #data_csv = pd.read_csv("DataSet_Final.csv") ##Use if you have classes saved in any .csv file

    root_dir = 'New_folder_to_be_created'
    classes_dir = ['class 1', 'class 2', 'class 3', 'class 4']

    #for name in data_csv['names'].unique()[:10]:
    #    classes_dir.append(name)

    processed_dir = 'Existing_folder_to_take_images_from'

    val_ratio = 0.20
    test_ratio = 0.20

    for cls in classes_dir:
        # Creating partitions of the data after shuffeling
        print("$$$$$$$ Class Name " + cls + " $$$$$$$")
        src = processed_dir +"//" + cls  # Folder to copy images from

        allFileNames = os.listdir(src)
        np.random.shuffle(allFileNames)
        train_FileNames, val_FileNames, test_FileNames = np.split(np.array(allFileNames),
                                                                  [int(len(allFileNames) * (1 - (val_ratio + test_ratio))),
                                                                   int(len(allFileNames) * (1 - val_ratio)),
                                                                   ])

        train_FileNames = [src + '//' + name for name in train_FileNames.tolist()]
        val_FileNames = [src + '//' + name for name in val_FileNames.tolist()]
        test_FileNames = [src + '//' + name for name in test_FileNames.tolist()]

        print('Total images: '+ str(len(allFileNames)))
        print('Training: '+ str(len(train_FileNames)))
        print('Validation: '+  str(len(val_FileNames)))
        print('Testing: '+ str(len(test_FileNames)))

        # # Creating Train / Val / Test folders (One time use)
        os.makedirs(root_dir + '/train//' + cls)
        os.makedirs(root_dir + '/val//' + cls)
        os.makedirs(root_dir + '/test//' + cls)

        # Copy-pasting images
        for name in train_FileNames:
            shutil.copy(name, root_dir + '/train//' + cls)

        for name in val_FileNames:
            shutil.copy(name, root_dir + '/val//' + cls)

        for name in test_FileNames:
            shutil.copy(name, root_dir + '/test//' + cls)

    print("########### Train Test Val Script Ended ###########")

train_test_split()