Python算法将数据集分割成训练集和测试集

将自己的数据集分成相应的训练集和测试集，并把相应的标签分成两个部分

import os
import cv2
import csv
import math
import random
import shutil


def move(filepath,destpath):
#从数据集中随机选取20%移动到另一文件夹下作为测试集，剩下的80%作为训练集
	pathdir=os.listdir(filepath)
	ranpath=random.sample(pathdir,int(0.2*len(pathdir)))
	print(ranpath)
	for alldir in ranpath:
		child=os.path.join(filepath,alldir)
		dest=os.path.join(destpath,alldir)
		shutil.copy(child,dest)
		os.remove(child)



def move_label(imgpath,labelpath,testpath):
#根据不同文件夹下的图片移动相应图片的标签
	labels=os.listdir(labelpath)
	for label in labels:
		imgdir=os.listdir(imgpath)
		for img in imgdir:
			if label.strip('.txt')==img.strip('.jpg'):
				print('###')
				label_path=os.path.join(labelpath,label)
				test_path=os.path.join(testpath,label)
				print(label_path)
				if labelpath:
					shutil.copy(label_path,test_path)
					os.remove(label_path)

def move_img(imgpath,labelpath,testpath):
	labels=os.listdir(labelpath)
	for label in labels:
		imgdir=os.listdir(imgpath)
		for img in imgdir:
			if label.strip('.txt')==img.strip('.jpg'):
				print('###')
				img_path=os.path.join(imgpath,img)
				test_path=os.path.join(testpath,img)
				shutil.copy(img_path,test_path)
				os.remove(img_path)

				
if __name__ == "__main__":
	move('./train','./test')
	move_img("./train",'./labels/test_labels','./test')