Will ‘torch.utils.data.DataLoader’ do normalization?

vision
#1

hi! the code is such as:

        train_transform = transforms.Compose([transforms.RandomHorizontalFlip(), transforms.ToTensor()])
        train_set = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=train_transform)
        self.train_loader = torch.utils.data.DataLoader(dataset=train_set,

then in def train():
for batch_num, (data, target) in enumerate(self.train_loader):
I find that data has been normalized. Does ‘torch.utils.data.DataLoader’ do normalization by default?
besides, how to see train_loader? why can we do for batch_num, (data, target) in enumerate(self.train_loader):? I can not understand the format of train_loader.
thanks!

#2

OK， I findtransforms.ToTensor() will normalize (0,1).