# Are there any differences between nn.activations and nn.function.activations?

**URL:** <https://discuss.pytorch.org/t/are-there-any-differences-between-nn-activations-and-nn-function-activations/2744>\
**Category:** Uncategorized\
**Created:** [May 7, 2017, 3:46am UTC](https://discuss.pytorch.org/t/are-there-any-differences-between-nn-activations-and-nn-function-activations/2744 "2017-05-07T03:46:13Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![recastrodiaz](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/r/c2a13f/32.png) [@recastrodiaz](https://discuss.pytorch.org/u/recastrodiaz)\
**Post date:** [May 7, 2017, 10:11am UTC](https://discuss.pytorch.org/t/are-there-any-differences-between-nn-activations-and-nn-function-activations/2744/2 "2017-05-07T10:11:48Z")

</div>

PyTorch activations use the functional API [under the hood](https://github.com/pytorch/pytorch/blob/master/torch/nn/modules/activation.py). So you can safely use one or the other. However, the **nn.module** additionally implements `_repr_` which lets you easily pretty print a [summary of your network](https://discuss.pytorch.org/t/is-there-similar-pytorch-function-as-model-summary-as-keras/2678).

---

_[View the full topic](https://discuss.pytorch.org/t/are-there-any-differences-between-nn-activations-and-nn-function-activations/2744)._