01-25-2019 12:19 PM
I am trying to create an object detector based on the example below. I have converted the keras model trained with over 100 images and converted to C++ using kerasify. The challenge is to convert kerasify to run on the Xilinx Zynq 7000 (Zedboard) by removing STL and using the NEON instrinsics without high level synthesis at this stage. Currently running a modified kerasify using Xilinx libraries, I am getting a maximum of 3 frames per second. Is there any benefits to carry on with the conversion or move straight to HLS?
06-21-2019 07:31 AM - edited 06-21-2019 07:32 AM
I am also currently facing an issue to run kerasify c++ model on xilinx zynq 7000. Can you please explain how to change the kerasify library to make it work on zynq 7000.
PS: I have very little knowledge in ARM-NEON programming.
06-22-2019 05:08 AM
Have you tried compiling kerasify using the xilinx compiler? It is standard C++ and libraries which should be supported by the Xilinx compiler which is based on GCC.
06-24-2019 07:21 AM
08-02-2019 07:54 PM
From memory you have to replace the function using the xilinx library to load the model from SD card.