# How to deploy a pretrained model on PYNQ Z2?

**URL:** <https://discuss.pynq.io/t/how-to-deploy-a-pretrained-model-on-pynq-z2/6464>\
**Category:** Support\
**Created:** [December 20, 2023, 5:50am UTC](https://discuss.pynq.io/t/how-to-deploy-a-pretrained-model-on-pynq-z2/6464 "2023-12-20T05:50:37Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Shubh\_Kawa](https://sea1.discourse-cdn.com/flex019/user_avatar/discuss.pynq.io/shubh_kawa/32/5464_2.png) [@Shubh\_Kawa](https://discuss.pynq.io/u/Shubh_Kawa)\
**Post date:** [December 20, 2023, 5:50am UTC](https://discuss.pynq.io/t/how-to-deploy-a-pretrained-model-on-pynq-z2/6464/1 "2023-12-20T05:50:37Z")

</div>

I am new to PYNQ and i wish to deploy my pre trained model on PYNQ Z2 board for inference.  
I haven’t been able to install tensorflow or pytorch as I am getting the error that there are no compatible versions present.  
Is there any other way to deploy deep learning models for inference?  
PYNQ Z2 v2.5, ubuntu 18.04

---

<div class="post-metadata">

**Author:** ![cathalmccabe](https://sea1.discourse-cdn.com/flex019/user_avatar/discuss.pynq.io/cathalmccabe/32/3348_2.png) [@cathalmccabe](https://discuss.pynq.io/u/cathalmccabe)\
**Post date:** [December 21, 2023, 7:30pm UTC](https://discuss.pynq.io/t/how-to-deploy-a-pretrained-model-on-pynq-z2/6464/2 "2023-12-21T19:30:26Z")

</div>

I would recommended DPU-PYNQ [GitHub - Xilinx/DPU-PYNQ: DPU on PYNQ](https://github.com/Xilinx/DPU-PYNQ) but it doesn’t support Zynq 7000 (Pynq-Z2)

Have you tried FINN:

> **[FINN](https://xilinx.github.io/finn/)**
>
> Dataflow compiler for QNN inference on FPGAs

Cathal