# How to use have batch norm not forget batch statistics it just used?

**URL:** <https://discuss.pytorch.org/t/how-to-use-have-batch-norm-not-forget-batch-statistics-it-just-used/103437>\
**Category:** Uncategorized\
**Created:** [November 19, 2020, 9:58pm UTC](https://discuss.pytorch.org/t/how-to-use-have-batch-norm-not-forget-batch-statistics-it-just-used/103437 "2020-11-19T21:58:45Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![Brando\_Miranda](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/brando_miranda/32/14355_2.png) [@Brando\_Miranda](https://discuss.pytorch.org/u/Brando_Miranda)\
**Post date:** [September 8, 2021, 7:51pm UTC](https://discuss.pytorch.org/t/how-to-use-have-batch-norm-not-forget-batch-statistics-it-just-used/103437/2 "2021-09-08T19:51:25Z")

</div>

related: [How does pytorch’s batch norm know if the forward pass its doing is for inference or training?](https://discuss.pytorch.org/t/how-does-pytorch-s-batch-norm-know-if-the-forward-pass-its-doing-is-for-inference-or-training/16857)

---

_[View the full topic](https://discuss.pytorch.org/t/how-to-use-have-batch-norm-not-forget-batch-statistics-it-just-used/103437)._