# Julia equivalence tf.nn.l2\_loss(x) in Flux

**URL:** <https://discourse.julialang.org/t/julia-equivalence-tf-nn-l2-loss-x-in-flux/82420>\
**Category:** General Usage\
**Tags:** flux\
**Created:** [June 8, 2022, 9:27am UTC](https://discourse.julialang.org/t/julia-equivalence-tf-nn-l2-loss-x-in-flux/82420 "2022-06-08T09:27:57Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![HerAdri](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/heradri/32/5816_2.png) [@HerAdri](https://discourse.julialang.org/u/HerAdri)\
**Post date:** [June 8, 2022, 9:27am UTC](https://discourse.julialang.org/t/julia-equivalence-tf-nn-l2-loss-x-in-flux/82420/1 "2022-06-08T09:27:57Z")

</div>

Which is the function inside the Flux package that is equivalent to Python tensorflow.python.ops.[nn.l2\_loss()](https://www.typeerror.org/docs/tensorflow~2.4/nn/l2_loss)?

---

<div class="post-metadata">

**Author:** ![albheim](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/albheim/32/34660_2.png) [@albheim](https://discourse.julialang.org/u/albheim)\
**Post date:** [June 8, 2022, 9:39am UTC](https://discourse.julialang.org/t/julia-equivalence-tf-nn-l2-loss-x-in-flux/82420/2 "2022-06-08T09:39:08Z")

</div>

You can read a bit about regularization in the flux [documentation](https://fluxml.ai/Flux.jl/stable/models/regularisation/#Regularisation).  
The idea is that you simple create your own regularization expression using julia code, and include that as part of the loss function.