Tiny-ImageNet下载与加载

Tiny-ImageNet的下载链接如下：http://cs231n.stanford.edu/tiny-imagenet-200.zip

下载完成后进行解压，可以看到在windows下的目录显示为：

可以看到train文件夹中，所有图片都像ImageNet一样放在以类别命名的文件夹中，可以不用管，但是val文件夹中同样也需要像Imagenet一样利用脚本将各文件放置于文件夹中，以符合pytorch读取数据的要求，这里我们通过如下脚本实现：

import glob
import os
from shutil import move
from os import rmdir

target_folder = './tiny-imagenet-200/val/'

val_dict = {}
with open('./tiny-imagenet-200/val/val_annotations.txt', 'r') as f:
    for line in f.readlines():
        split_line = line.split('	')
        val_dict[split_line[0]] = split_line[1]
        
paths = glob.glob('./tiny-imagenet-200/val/images/*')
for path in paths:
    file = path.split('/')[-1]
    folder = val_dict[file]
    if not os.path.exists(target_folder + str(folder)):
        os.mkdir(target_folder + str(folder))
        os.mkdir(target_folder + str(folder) + '/images')
       
for path in paths:
    file = path.split('/')[-1]
    folder = val_dict[file]
    dest = target_folder + str(folder) + '/images/' + str(file)
    move(path, dest)
    
rmdir('./tiny-imagenet-200/val/images')

就让Tiny-ImageNet的文件格式基本与ImageNet一致了，在DataLoader时，也可以用相似的代码，这里是将尺寸变成了32来处理

def tiny_loader(batch_size, data_dir):
    num_label = 200
    normalize = transforms.Normalize((0.4802, 0.4481, 0.3975), (0.2770, 0.2691, 0.2821))
    transform_train = transforms.Compose(
        [transforms.RandomResizedCrop(32), transforms.RandomHorizontalFlip(), transforms.ToTensor(),
         normalize, ])
    transform_test = transforms.Compose([transforms.Resize(32), transforms.ToTensor(), normalize, ])
    trainset = datasets.ImageFolder(root=os.path.join(data_dir, 'train'), transform=transform_train)
    testset = datasets.ImageFolder(root=os.path.join(data_dir, 'val'), transform=transform_test)
    train_loader = torch.utils.data.DataLoader(trainset, batch_size=batch_size, shuffle=True, pin_memory=True)
    test_loader = torch.utils.data.DataLoader(testset, batch_size=batch_size, shuffle=False, pin_memory=True)
    return train_loader, test_loader, num_label

就可以正常进行训练了