Accelarating Convolution Neural Networks on PYNQ-Z1

Hello, in order to accelarate CNN, should I just run my python code to the terminal of PYNQ-Z1 or should I transform it to HDL with Vivado and HDL (VHDL, Verilog)??

Thanks…

Yes, you need to create the hardware design. Running (Python/C) software in the terminal will only execute that software on the ARM processor.
You could create the design using VHDL/Verilog, or HLS (C based), or other design methods.

Cathal

1 Like

Do you follow any tutorial for this design? I mean how do I create a hardware design by using C in order to running it to the FPGA (not to the CPU)?