处理数据集python脚本（处理自己制作的数据集）

import os

class BatchRename():
    '''
    批量重命名文件夹中的图片文件
    '''

    def __init__(self):
        self.path = './qiche1'  # 表示需要命名处理的文件夹

    def rename(self):
        filelist = os.listdir(self.path)  # 获取文件路径
        total_num = len(filelist)  # 获取文件长度（个数）
        print(total_num)
        print(filelist)
        for file in filelist:
            # print(file)
            filelist1 = os.listdir(self.path + '/' + file)
            print(filelist1)
            i = 1  # 表示文件的命名是从1开始的
            for item in filelist1:
                if item.endswith('.jpg'):  # 初始的图片的格式为jpg格式的（或者源文件是png格式及其
                    # 他格式，后面的转换格式就可以调整为自己需要的格式即可）
                    print(item)
                    # print(self.path)
                    src = os.path.join('./qiche1'+ '/'+file+'/'+item)
                    print(src)
                    dst = os.path.join('./qiche1'+ '/'+file+'/'+'qiche1_'+file+'_'+ str(i) + '.jpg')  # 处理后的格式也为jpg格式的，当然这里可以改成png格式
                    # dst = os.path.join(os.path.abspath(self.path), '0000' + format(str(i), '0>3s') + '.jpg')    这种情况下的命名格式为0000000.jpg形式，可以自主定义想要的格式
                    try:
                        os.rename(src,dst)
                        print('converting %s to %s ...' % ( src,dst))
                        i = i + 1
                    except:
                        continue
            print('total %d to rename & converted %d jpgs' % (total_num, i))


if __name__ == '__main__':
    demo = BatchRename()
    demo.rename()

2，数据集划分

import os
from shutil import copy
import random


def mkfile(file):
    if not os.path.exists(file):
        os.makedirs(file)


file = 'car/images'
flower_class = [cla for cla in os.listdir(file) if ".txt" not in cla]
mkfile('car/train')
for cla in flower_class:
    mkfile('car/train/'+cla)

mkfile('car/val')
for cla in flower_class:
    mkfile('car/val/'+cla)

split_rate = 0.1
for cla in flower_class:
    cla_path = file + '/' + cla + '/'
    images = os.listdir(cla_path)
    num = len(images)
    eval_index = random.sample(images, k=int(num*split_rate))
    for index, image in enumerate(images):
        if image in eval_index:
            image_path = cla_path + image
            new_path = 'car/val/' + cla
            copy(image_path, new_path)
        else:
            image_path = cla_path + image
            new_path = 'car/train/' + cla
            copy(image_path, new_path)
        print("\r[{}] processing [{}/{}]".format(cla, index+1, num), end="")  # processing bar
    print()
print("processing done!")