Why the normalize scalr of input transform is 0.5 but not 255*0.5 ?

I wonder why the preprocess normalize scalar is different betweet train and inference.

- Train :in insightface/recognition/arcface_torch/dataset.py
```
class MXFaceDataset(Dataset):
def __init__(self, root_dir, local_rank):
super(MXFaceDataset, self).__init__()
self.transform = transforms.Compose(
[transforms.ToPILImage(),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),
])
self.root_dir = root_dir
self.local_rank = local_rank
```
- Inference: in insightface/recognition/arcface_torch/inference.py
```
def inference(weight, name, img):
if img is None:
img = np.random.randint(0, 255, size=(112, 112, 3), dtype=np.uint8)
else:
img = cv2.imread(img)
img = cv2.resize(img, (112, 112))
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = np.transpose(img, (2, 0, 1))
img = torch.from_numpy(img).unsqueeze(0).float()
img.div_(255).sub_(0.5).div_(0.5)
net = get_model(name, fp16=False)
net.load_state_dict(torch.load(weight))
net.eval()
feat = net(img).numpy()
print(feat)
```

Why the normalize scalr of input transform for trainning is 0.5 but not 255*0.5 ? @nttstar