用python划分数据集,训练集:测试集=5:5
import os
import random
import shutil
from shutil import copy2
datadir_normal = "./data/Stanford Cars (CAR)/car_ims" # 照片所处的文件夹相对比本程序的相对路径
all_data = os.listdir(datadir_normal) # (图片文件夹)
num_all_data = len(all_data)
print("num_all_data: " + str(num_all_data))
index_list = list(range(num_all_data))
# print(index_list)
random.shuffle(index_list)
num = 0
trainDir = "./data/CAR_train/" # (将训练集放在这个文件夹下,若没有该文件夹,则会生成)
if not os.path.exists(trainDir):
os.mkdir(trainDir)
testDir = "./data/CAR_test/" # (将测试集放在这个文件夹下,若没有该文件夹,则会生成)
if not os.path.exists(testDir):
os.mkdir(testDir)
for i in index_list:
fileName = os.path.join(datadir_normal, all_data[i])
if num < num_all_data * 0.5:
# print(str(fileName))
copy2(fileName, trainDir)
else:
copy2(fileName, testDir)
num += 1
引用: