# MNIST Normalization

**URL:** <https://discuss.pytorch.org/t/mnist-normalization/49080>\
**Category:** vision\
**Created:** [June 27, 2019, 4:27am UTC](https://discuss.pytorch.org/t/mnist-normalization/49080 "2019-06-27T04:27:54Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![1414b35e42c77e0a57dd](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/1414b35e42c77e0a57dd/32/7689_2.png) [@1414b35e42c77e0a57dd](https://discuss.pytorch.org/u/1414b35e42c77e0a57dd)\
**Post date:** [June 27, 2019, 4:27am UTC](https://discuss.pytorch.org/t/mnist-normalization/49080/1 "2019-06-27T04:27:54Z")

</div>

I’m confused about normalization process to MNIST.  
In 64 batch size, I think `transforms.Normalize((0.1307), (0.3081)` is right.

In my case, I already do `train_dataset.train_data.float() / 255.` in MNIST class so I can get (0.1307),(0.3081).  
then do not need to use normalization any more?  
This is my code.

```auto
class MNIST(data.Dataset):
    def __init__ (self, split, transform=None):
        # self.transform = transformers.get_basic_transformer()
        self.split = split
        self.transform = transform

        if split == "train":

            train_dataset = datasets.MNIST(
                root="data/mnist", train=True, download=True, transform=None)
            self.X = train_dataset.train_data.float() / 255.
            self.y = train_dataset.train_labels

            np.random.seed(2)
            ind = np.random.choice(
                len(train_dataset), len(train_dataset), replace=False)
            self.X = self.X[ind]
            self.y = self.y[ind]

        elif split == "val":
            test_dataset = datasets.MNIST(root="data/mnist",
                                          train=False, download=True, transform=None)

            self.X = test_dataset.test_data.float() / 255.
            self.y = test_dataset.test_labels

    def __getitem__ (self, index):
        X, y = self.X[index].clone(), self.y[index].clone()

        X = self.transform(X[None])

        return X, y

    def __len__ (self):
        """Return size of dataset."""
        return self.X.shape[0]

```

```auto
    pre_process = transforms.Compose(
        [transforms.Normalize(mean=[0.5], std=[0.5])]) DO I HAVE TO DO THIS ?

```

- What about test dataset? Should I re-calculate mean and std from test data?

---

<div class="post-metadata">

**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\
**Post date:** [June 27, 2019, 10:21am UTC](https://discuss.pytorch.org/t/mnist-normalization/49080/2 "2019-06-27T10:21:13Z")

</div>

`transforms.Normalize` will standardize the data such that it’ll have a zero mean and unit variance.  
You don’t need to apply it, but it might help your training.

> [@1414b35e42c77e0a57dd](#):
>
> What about test dataset? Should I re-calculate mean and std from test data?

No, you should apply the same statistics calculated from the training dataset.  
Otherwise this would be considered as data leakage.

---

<div class="post-metadata">

**Author:** ![1414b35e42c77e0a57dd](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/1414b35e42c77e0a57dd/32/7689_2.png) [@1414b35e42c77e0a57dd](https://discuss.pytorch.org/u/1414b35e42c77e0a57dd)\
**Post date:** [June 27, 2019, 10:52am UTC](https://discuss.pytorch.org/t/mnist-normalization/49080/3 "2019-06-27T10:52:59Z")

</div>

@ptrblck  
Thanks a reply !

My questions was not clear.  
What I want to ask you is that `train_dataset.train_data.float() / 255.` makes normalization  
then, `[transforms.Normalize(mean=[0.5], std=[0.5])])` is not needed ?

---

<div class="post-metadata">

**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\
**Post date:** [June 27, 2019, 11:03am UTC](https://discuss.pytorch.org/t/mnist-normalization/49080/4 "2019-06-27T11:03:02Z")

</div>

I think your question was clear, but my answer probably wasn’t. 😉

Dividing by `255.` will normalize the data to the range `[0, 1]`.  
`transforms.Normalize` will standardize this data to zero mean and unit variance.  
So, `Normalize` might yield advantages for your training, but your model might also learn with fine without it.

Anyway, I would recommend using it. 😉