# Image normalization

**URL:** <https://discuss.pytorch.org/t/image-normalization/93115>\
**Category:** Uncategorized\
**Created:** [August 17, 2020, 4:36pm UTC](https://discuss.pytorch.org/t/image-normalization/93115 "2020-08-17T16:36:08Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![mariosasko](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/mariosasko/32/27520_2.png) [@mariosasko](https://discuss.pytorch.org/u/mariosasko)\
**Post date:** [August 18, 2020, 1:42am UTC](https://discuss.pytorch.org/t/image-normalization/93115/2 "2020-08-18T01:42:27Z")

</div>

Usually, the images are scaled to the [0, 1] interval first (`images = images / 255)`. Then, to normalize them, you can use `torchvision`'s `transforms.Normalize` and this is a [link](https://discuss.pytorch.org/t/about-normalization-using-pre-trained-vgg16-networks/23560/6) to the post where it’s explained how to compute the mean and std of the images.

---

_[View the full topic](https://discuss.pytorch.org/t/image-normalization/93115)._