# How to preprocess input for pre trained networks?

**URL:** <https://discuss.pytorch.org/t/how-to-preprocess-input-for-pre-trained-networks/683>\
**Category:** vision\
**Created:** [February 23, 2017, 9:06am UTC](https://discuss.pytorch.org/t/how-to-preprocess-input-for-pre-trained-networks/683 "2017-02-23T09:06:26Z")\
**Posts on this page:** 1\
**Showing post:** 8

<div class="post-metadata">

**Author:** ![mehdi-shiba](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/mehdi-shiba/32/219_2.png) [@mehdi-shiba](https://discuss.pytorch.org/u/mehdi-shiba)\
**Post date:** [March 16, 2017, 6:03am UTC](https://discuss.pytorch.org/t/how-to-preprocess-input-for-pre-trained-networks/683/8 "2017-03-16T06:03:03Z")

</div>

Agreed. If it wasn’t for this thread, I would have missed this important Normalization step for sure. It would be nice if it could be added to the documentation.

---

_[View the full topic](https://discuss.pytorch.org/t/how-to-preprocess-input-for-pre-trained-networks/683)._