# Normalization in the mnist example

**URL:** <https://discuss.pytorch.org/t/normalization-in-the-mnist-example/457>\
**Category:** Uncategorized\
**Created:** [February 12, 2017, 8:50am UTC](https://discuss.pytorch.org/t/normalization-in-the-mnist-example/457 "2017-02-12T08:50:41Z")\
**Posts on this page:** 1\
**Showing post:** 7

<div class="post-metadata">

**Author:** ![smth](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/smth/32/13_2.png) [@smth](https://discuss.pytorch.org/u/smth)\
**Post date:** [March 2, 2017, 3:39am UTC](https://discuss.pytorch.org/t/normalization-in-the-mnist-example/457/7 "2017-03-02T03:39:31Z")

</div>

Yes. On Imagenet, we’ve done a pass on the dataset and calculated per-channel mean/std. In CIFAR10, I thought that this was unncessary to be introduced to the reader, and we quite often just use `0.5, 0.5, 0.5` on many datasets to rerange them to `[-1, +1]`. Sorry if this was confusing 🙂

---

_[View the full topic](https://discuss.pytorch.org/t/normalization-in-the-mnist-example/457)._