Tiny ImageNet数据集预处理

Tiny Imagenet是斯坦福大学提供的图像分类数据集，其中包含200个类别，每个类别包含500张训练图像，50张验证图像及50张测试图像，数据集地址：Tiny ImageNet

导入所需模块

import os
import sys
from torch.utils.data import Dataset, DataLoader
import numpy as np
import cv2
from torchvision import transforms

处理TXT文件

训练集

labels_t = []
image_names = []
with open('.\\tiny-imagenet-200\\wnids.txt') as wnid:
    for line in wnid:
        labels_t.append(line.strip('\n'))
for label in labels_t:
    txt_path = '.\\tiny-imagenet-200\\train\\'+label+'\\'+label+'_boxes.txt'
    image_name = []
    with open(txt_path) as txt:
        for line in txt:
            image_name.append(line.strip('\n').split('\t')[0])
    image_names.append(image_name