PYNQ + Vitis AI Libraries

Support
1

Hello,

I am trying to deploy the SSD MobileNet v2 trained with the COCO dataset at PYNQ. I am using Jupyter notebooks.
It is possible to use Vitis AI libraries (https://github.com/Xilinx/Vitis-AI/tree/master/tools/Vitis-AI-Library) to reimplement the post-processing? Have these libraries been ported to Python?

Thank you for the support.
Regards

2

These libs run on the DPU.
You can use the DPU with PYNQ, but currently only up to 1.3.2.

Cathal

3

Hello @cathalmccabe,

Thank you for your response.

Indeed I am already using that library. However, I think that it only provides the overlay to communicate with the DPU. However, the SSD MobileNet v2 is not fully compatible with the DPU, I had to remove the pre-processing and post-processing layers, and then, now, I have to reimplement them.
The pre-processing is easy to implement, and the examples already provide a framework for it. Although, post-processing requires decoding the confidence scores and the box encodings. The libraries in the Vitis AI Libraries, namely this one https://github.com/Xilinx/Vitis-AI/tree/master/tools/Vitis-AI-Library/xnnpp/src/tfssd, already provide this implementation, and I am avoiding translating it o Python.

I am trying to bind the libraries, but I think that the Vitis Ai 1.4 already provides this binding.

Thanks