# Several problems when implement Bayes by backprop using edward

**URL:** <https://discourse.edwardlib.org/t/several-problems-when-implement-bayes-by-backprop-using-edward/701>\
**Category:** General\
**Created:** [March 30, 2018, 12:37am UTC](https://discourse.edwardlib.org/t/several-problems-when-implement-bayes-by-backprop-using-edward/701 "2018-03-30T00:37:35Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![sejabs](https://avatars.discourse-cdn.com/v4/letter/s/db5fbb/32.png) [@sejabs](https://discourse.edwardlib.org/u/sejabs)\
**Post date:** [March 30, 2018, 12:37am UTC](https://discourse.edwardlib.org/t/several-problems-when-implement-bayes-by-backprop-using-edward/701/1 "2018-03-30T00:37:35Z")

</div>

I’m a newbie of DL. I heard Edward when I used Pymc3 for a while and I decided to swing to Edward for my project. Now when I read the “ed.klqp” code and try to implement Bayes by backprop using edward, I have some problems seeking help.

1. in the annotation of klqp, it is showed

> based on the reparameterization trick [@kingma2014auto].

however, following the code I can’t see the trick which need to sample from standard normal. The code still sample values from q(z) not N(0,I). Is there something I have missed?

1. in the context of mini batch, if my understanding is right, the klqp need to compute full `log q(z) - log p(z)` every loop. But in the Bayes by backprop, they use mean loss `1/M * (log q(z) - log p(z))` every batch, and `M` is the number of batch. Is there different performance between the two algorithm?