# What is the equivalent of Caffe's propagate\_down: false?

**URL:** <https://discuss.pytorch.org/t/what-is-the-equivalent-of-caffes-propagate-down-false/8936>\
**Category:** Uncategorized\
**Created:** [October 21, 2017, 10:42pm UTC](https://discuss.pytorch.org/t/what-is-the-equivalent-of-caffes-propagate-down-false/8936 "2017-10-21T22:42:05Z")\
**Posts on this page:** 1\
**Showing post:** 3

<div class="post-metadata">

**Author:** ![hyojin](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/h/a183cd/32.png) [@hyojin](https://discuss.pytorch.org/u/hyojin)\
**Post date:** [October 23, 2017, 7:04am UTC](https://discuss.pytorch.org/t/what-is-the-equivalent-of-caffes-propagate-down-false/8936/3 "2017-10-23T07:04:03Z")

</div>

Thanks. This makes sense, but I was unsure to use detach because of what is said in the following post:

> [@Quick Detach() Question](https://discuss.pytorch.org/t/quick-detach-question/1090/4):
>
> If in2 is detached, you can’t call loss.backward at all, since net2(in2) are not taken into account by the computation of the gradient. When a variable is detached, the backward computations will not visit the branches that start from this variable (all the operations done on it). So as @albanD suggested, you need to create a new graph (hence the new variable requiring a gradient) if you want to compute a gradient with respect to the new network (net2) independently on previous operation (net1…

“When a variable is detached, the backward computations will not visit the branches that start from this variable (all the operations done on it).”

If I understand this statement correctly, this is not exactly what I want. I do want backprop on operations that involved this variable (although not with respect to this variable itself.)

---

_[View the full topic](https://discuss.pytorch.org/t/what-is-the-equivalent-of-caffes-propagate-down-false/8936)._