# Dynamic Structure of CNN

**URL:** <https://discuss.pytorch.org/t/dynamic-structure-of-cnn/45870>\
**Category:** Uncategorized\
**Created:** [May 22, 2019, 3:04am UTC](https://discuss.pytorch.org/t/dynamic-structure-of-cnn/45870 "2019-05-22T03:04:55Z")\
**Posts on this page:** 1\
**Showing post:** 8

<div class="post-metadata">

**Author:** ![Wafaa\_Wardah](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/wafaa_wardah/32/53794_2.png) [@Wafaa\_Wardah](https://discuss.pytorch.org/u/Wafaa_Wardah)\
**Post date:** [May 22, 2019, 10:43am UTC](https://discuss.pytorch.org/t/dynamic-structure-of-cnn/45870/8 "2019-05-22T10:43:49Z")

</div>

Thank you for your help. I agree kernel size of 3 is where I probably want to be. Also, I think I should be more interested in number of kernels (I mean channels\_out - is that correct understanding?) rather than kernel size.

Also, [this question](https://discuss.pytorch.org/t/utility-function-for-calculating-the-shape-of-a-conv-output/11173) is what I was trying to ask it seems.

Thank you again.

---

_[View the full topic](https://discuss.pytorch.org/t/dynamic-structure-of-cnn/45870)._