# DPU PYNQ on ZCU104 and ZCU111

**URL:** <https://discuss.pynq.io/t/dpu-pynq-on-zcu104-and-zcu111/3853>\
**Category:** Support\
**Created:** [March 16, 2022, 11:14am UTC](https://discuss.pynq.io/t/dpu-pynq-on-zcu104-and-zcu111/3853 "2022-03-16T11:14:30Z")\
**Posts on this page:** 1\
**Showing post:** 20

<div class="post-metadata">

**Author:** ![Nagendra](https://sea1.discourse-cdn.com/flex019/user_avatar/discuss.pynq.io/nagendra/32/2653_2.png) [@Nagendra](https://discuss.pynq.io/u/Nagendra)\
**Post date:** [April 13, 2022, 5:14am UTC](https://discuss.pynq.io/t/dpu-pynq-on-zcu104-and-zcu111/3853/20 "2022-04-13T05:14:50Z")

</div>

Hi @skalade

Thank you for your reply.  
Yes, I am following the example design “[PYNQ-CNN-ATTEMPT/FPGA\_CNN.ipynb at master · ZhaoqxCN/PYNQ-CNN-ATTEMPT · GitHub](https://github.com/ZhaoqxCN/PYNQ-CNN-ATTEMPT/blob/master/Minst-CNN/FPGA_CNN.ipynb)” trying to replicate this design on the ZCU111 board. Here we are using allocate instead of xlnk, so there must be a different way to load the weights in the memory and I am not sure what the exact issue is. Can you suggest me a way to solve this?

 ![Screenshot 2022-04-13 at 04-59-33 FPGA_CNN - Jupyter Notebook](https://us1.discourse-cdn.com/flex019/uploads/pynq1/original/2X/e/e6baeb70c2eec18b44111b10376a320661b81c4a.png)

![Screenshot 2022-04-13 at 05-00-57 FPGA_CNN - Jupyter Notebook](https://us1.discourse-cdn.com/flex019/uploads/pynq1/original/2X/8/8a55e3edf5430e21576ee75d7b11ade8d3815977.png)

---

_[View the full topic](https://discuss.pynq.io/t/dpu-pynq-on-zcu104-and-zcu111/3853)._