pytorch with CIFAR-100

Question

import torch
import torchvision
import torchvision.transforms as transforms
transform=transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5),(0.5))])
trainset=torchvision.datasets.CIFAR100(root='./dataset',train=True,
download=True,transform=transform)
trainloader=torch.utils.data.CIFAR100(trainset,batch_size=4,shuffle=True)
testset=torchvision.datasets.CIFAR100(root='./dataset',train=False,
download=True,transform=transform)
testloader=torch.utils.data.DataLoader(testset,batch_size=4,shuffle=False)
classes=('0','1','2','3','4','5','6','7','8','9')

错误消息如下所示模块"torch.utils.data"没有属性"CIFAR100">

当我将torch.utils.data与cifar-10一起使用时，它起了作用但它不适用于cifar-100你能告诉我为什么会这样吗？

Answer 1

列车装载机线路出现错误，您必须将列车集传递给torch.utils.data.DataLoader。将该行替换为，

trainloader=torch.utils.data.DataLoader(trainset,batch_size=4,shuffle=True)