# Batched probability distribution specification in Turing similar to Tensorflow Probability

**URL:** <https://discourse.julialang.org/t/batched-probability-distribution-specification-in-turing-similar-to-tensorflow-probability/103953>\
**Category:** General Usage\
**Tags:** package, turing, distributions\
**Created:** [September 17, 2023, 4:18pm UTC](https://discourse.julialang.org/t/batched-probability-distribution-specification-in-turing-similar-to-tensorflow-probability/103953 "2023-09-17T16:18:38Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![gsood-gaurav](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/gsood-gaurav/32/52996_2.png) [@gsood-gaurav](https://discourse.julialang.org/u/gsood-gaurav)\
**Post date:** [September 17, 2023, 4:18pm UTC](https://discourse.julialang.org/t/batched-probability-distribution-specification-in-turing-similar-to-tensorflow-probability/103953/1 "2023-09-17T16:18:38Z")

</div>

In tensorflow probability there is this idea of batch\_shape and event\_shape while declaring a set of distribtuions. What is the equivalent of it in Turing.jl + Distributions.jl

For instance if I want to declare a batch of 3 multivariate normal distributions with event\_shape 4, how will i do it in turing.jl + distributions.jl