PYNQ: PYTHON PRODUCTIVITY

BNN with custom neural network Ultra96v2

Hello everyone,

I am a beginner in ML on FPGA. I rebuilt bnn project and opened it. I used Vivado 2018.2.

I saw BlackBoxJam IP core. Can I modify this IP block if I want to use I new neural network?

Is it a black box for me? How I can modify it (from HLS or from Vivado)?

Can anyone explain to me what the steps are to get started?

You would be best checking on the BNN repo first: https://github.com/Xilinx/BNN-PYNQ/
and corresponding docs for FINN project.
https://xilinx.github.io/finn/

Cathal

I suppose you followed these steps https://github.com/Xilinx/BNN-PYNQ#hardware-design-rebuilt

The BNN builds on top of https://github.com/Xilinx/finn-hlslib, and the function that includes the different layers are here https://github.com/Xilinx/BNN-PYNQ/tree/master/bnn/src/network.

As Cathal mention, you can find more documentation on BNN and FINN repos.