# Any implementation of 'Fixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs'?

**URL:** <https://discourse.julialang.org/t/any-implementation-of-fixed-smooth-convolutional-layer-for-avoiding-checkerboard-artifacts-in-cnns/65881>\
**Category:** Machine Learning\
**Tags:** flux\
**Created:** [August 5, 2021, 12:48pm UTC](https://discourse.julialang.org/t/any-implementation-of-fixed-smooth-convolutional-layer-for-avoiding-checkerboard-artifacts-in-cnns/65881 "2021-08-05T12:48:36Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![czexana](https://avatars.discourse-cdn.com/v4/letter/c/7993a0/32.png) [@czexana](https://discourse.julialang.org/u/czexana)\
**Post date:** [August 5, 2021, 12:48pm UTC](https://discourse.julialang.org/t/any-implementation-of-fixed-smooth-convolutional-layer-for-avoiding-checkerboard-artifacts-in-cnns/65881/1 "2021-08-05T12:48:36Z")

</div>

Hello,

I’m wondering if anyone has implemented the above paper, found at [[2002.02117] Fixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs](https://arxiv.org/abs/2002.02117) that purports to fix checkerboard artifacts in conv and convtranspose layers with stride greater than one.

I have no experience with time-based DSP and I can’t get my head around what their ‘zero-order hold kernel’ actually equates to when using an image dataset …

Thanks in advance for any insight!

---

<div class="post-metadata">

**Author:** ![ToucheSir](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/touchesir/32/14411_2.png) [@ToucheSir](https://discourse.julialang.org/u/ToucheSir)\
**Post date:** [August 5, 2021, 4:13pm UTC](https://discourse.julialang.org/t/any-implementation-of-fixed-smooth-convolutional-layer-for-avoiding-checkerboard-artifacts-in-cnns/65881/2 "2021-08-05T16:13:27Z")

</div>

This is the first time I’ve seen this paper and they provide 0 information on how the operation was actually implemented in code, so I imagine not? Something like this should really have an accompanying code listing or repo…

---

<div class="post-metadata">

**Author:** ![czexana](https://avatars.discourse-cdn.com/v4/letter/c/7993a0/32.png) [@czexana](https://discourse.julialang.org/u/czexana)\
**Post date:** [August 6, 2021, 9:10am UTC](https://discourse.julialang.org/t/any-implementation-of-fixed-smooth-convolutional-layer-for-avoiding-checkerboard-artifacts-in-cnns/65881/3 "2021-08-06T09:10:54Z")

</div>

Thanks for the reply.

I was surprised I couldn’t find any implementation details or repo - not even a note on which packages they used to do the tests.

I’ll see if I can cobble something together over the weekend, as a test. I have a basic idea how to implement it, but it likely won’t be pretty!