AnsweredAssumed Answered

S32V234 Matlab Vision Toolbox: Neural network without images as input?

Question asked by fixed-term.lukas.ebenstein@de.bosch.com on Apr 24, 2019
Latest reply on Apr 25, 2019 by dumitru-daniel.popa

Hello,

I am currently evaluating on how the S32V234 can be used for running neural networks. The provided CNN Matlab examples work pretty well on my dev-board. What I could not find was an example for a neural network that does not use an image as the input (but e.g. numbers), so I wonder what the recommended way is to use such networks.

 

  • Can I just use any neural network in Matlab and compile it for the S32V234 with nxpvt_codegen(…)?
  • Can I use any layers/neural network types I want?
  • Is there example code I overlooked?
  • Is there a better way to do this, other than Matlab?
  • If I do not use any of the nxpvt.apexcv.xxx commands the compiled program will solely run on the ARM processor?
  • Does the Vision Toolbox support the integrated Vivante GPU in any way?

 

Thanks a lot!

Outcomes