# Registration Algorithm or Evolution Optimizer Not Deterministic

**URL:** <https://discourse.itk.org/t/registration-algorithm-or-evolution-optimizer-not-deterministic/6597>\
**Category:** Algorithms\
**Tags:** optimization, registration\
**Created:** [April 26, 2024, 3:42am UTC](https://discourse.itk.org/t/registration-algorithm-or-evolution-optimizer-not-deterministic/6597 "2024-04-26T03:42:28Z")\
**Posts on this page:** 1\
**Showing post:** 4

<div class="post-metadata">

**Author:** ![dzenanz](https://discourse.itk.org/user_avatar/discourse.itk.org/dzenanz/32/1093_2.png) [@dzenanz](https://discourse.itk.org/u/dzenanz)\
**Post date:** [April 26, 2024, 2:30pm UTC](https://discourse.itk.org/t/registration-algorithm-or-evolution-optimizer-not-deterministic/6597/4 "2024-04-26T14:30:36Z")

</div>

Take a look at this discussion about registration reproducibility:

> [@Unstable iteration for registration](https://discourse.itk.org/t/unstable-iteration-for-registration/410):
>
> Hi all, I am using itk.RegularStepGradientDescentOptimizerv4 to perform a multiresolution translation registration between two images. I ran my code in the same computation environment for the same two images at different times, but I got a slightly different results (please see the attached figures) during the iterations. I checked the results and found the difference mostly starting from the middle level of a image pyramid (I used 3-level image pyramid), and then the difference would be incre…

---

_[View the full topic](https://discourse.itk.org/t/registration-algorithm-or-evolution-optimizer-not-deterministic/6597)._