# Different learning rate for a specific layer

**URL:** <https://discuss.pytorch.org/t/different-learning-rate-for-a-specific-layer/33670>\
**Category:** Uncategorized\
**Created:** [January 3, 2019, 10:28am UTC](https://discuss.pytorch.org/t/different-learning-rate-for-a-specific-layer/33670 "2019-01-03T10:28:04Z")\
**Posts on this page:** 1\
**Showing post:** 18

<div class="post-metadata">

**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\
**Post date:** [December 15, 2022, 8:32pm UTC](https://discuss.pytorch.org/t/different-learning-rate-for-a-specific-layer/33670/18 "2022-12-15T20:32:42Z")

</div>

Your idea should generally work, but note that you would need to use `param[1]` in the `list` instead of `temp[1]` as it’s undefined.

---

_[View the full topic](https://discuss.pytorch.org/t/different-learning-rate-for-a-specific-layer/33670)._
