# Num samples in export posterior for Visium HD

**URL:** <https://discourse.scverse.org/t/num-samples-in-export-posterior-for-visium-hd/3278>\
**Category:** cell2location\
**Created:** [October 3, 2024, 11:48pm UTC](https://discourse.scverse.org/t/num-samples-in-export-posterior-for-visium-hd/3278 "2024-10-03T23:48:59Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![jairaj-mathur](https://yyz1.discourse-cdn.com/flex035/user_avatar/discourse.scverse.org/jairaj-mathur/32/1188_2.png) [@jairaj-mathur](https://discourse.scverse.org/u/jairaj-mathur)\
**Post date:** [October 3, 2024, 11:48pm UTC](https://discourse.scverse.org/t/num-samples-in-export-posterior-for-visium-hd/3278/1 "2024-10-03T23:48:59Z")

</div>

Hi all  
I am chunking Visium HD data to train model in parts, I had a question regarding export\_posterior. Should I increase the number of samples? Will that affect accuracy of my results? Same for the adata\_sc training, should I increase the number of samples there as well??

Sorry if this is a very naive or if my understanding of export\_posterior is wrong.

Thank you!