在pytorch中使用了datalloader函数,并且清除了iter函数,但是next()函数导致错误。如果您知道解决方案或原因,请帮助我。
我已经更改了批量大小。
import torch
import torchvision
import torchvision.transforms as transforms
from torchvision.datasets import ImageFolder
transform = transforms.Compose([transforms.Resize(224,224),
transforms.ToTensor(),
transforms.Normalize((0.5,0.5,0.5),(0.5,0.5,0.5))])
train = ImageFolder('/home/minseok/study/dog_cat/train',transform)
valid = ImageFolder('/home/minseok/study/dog_cat/valid',transform)
train_loader = torch.utils.data.DataLoader(train,batch_size=256,num_workers=8,shuffle=True)
valid_loader = torch.utils.data.DataLoader(valid,batch_size=2,num_workers=1,shuffle=True)
dataiter = iter(valid_loader) #It's safe up to here
images, labels = dataiter.next() # error
很抱歉我的英语解释不好,因为它不是英语。
答案 0 :(得分:0)
您尝试过这个吗?
images, labels = next(dataiter)