How do they know mean and std, the input value of transforms.Normalize

CGContextTranslateCTM(context, 10, 10);

CGAffineTransform transform = CGAffineTransformIdentity;
transform = CGAffineTransformTranslate(transform, 10, 10);
CGContextConcatCTM(context, transform);

trainTransform  = tv.transforms.Compose([tv.transforms.ToTensor(), 
                  tv.transforms.Normalize((0.4914, 0.4822, 0.4466), (0.247, 0.243, 0.261))])

trainSet = tv.datasets.CIFAR10(root=dataDir, train=True,
                                    download=False, transform=trainTransform)

dataloader = torch.utils.data.DataLoader(trainset, batch_size=32, shuffle=False, num_workers=4)

images, labels = iter(dataloader).next()
print images
print images.max()
print images.min()

[[ 1.8649,  1.8198,  1.8348,  ...,  0.3924,  0.3774,  0.2572],
      [ 1.9701,  1.9550,  1.9851,  ...,  0.7230,  0.6929,  0.6629],
      [ 2.0001,  1.9550,  2.0001,  ...,  0.7831,  0.7530,  0.7079],
      ...,
      [-0.8096, -1.0049, -1.0350,  ..., -1.3355, -1.3655, -1.4256],
      [-0.7796, -0.8697, -0.9749,  ..., -1.2754, -1.4557, -1.5609],
      [-0.7645, -0.7946, -0.9298,  ..., -1.4106, -1.5308, -1.5909]]]])
tensor(2.1309)
tensor(-1.9895) 

trainTransform  = tv.transforms.Compose([tv.transforms.ToTensor(), 
                  tv.transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

transform = transforms.Compose([
    transforms.RandomHorizontalFlip(p=0.5)
    transforms.Resize(40),
    transforms.RandomCrop(32),
    transforms.ToTensor(),
    transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))])

// at this level test is infered as with or without lineData
const test= akpiDTOtoAkpiData({
  id: 1,
  name: 'my name',
  startDate: '2019',
  periodData: [] as PeriodDto[],
});

if ('lineData' in test) {
  // here test is precisely the type with lineData
}

transform = transforms.Compose([
   transforms.ToTensor(),
   transforms.Normalize(mean=[0.5, 0.5],
                        std=[0.5, 0.5])
])