How to use pruned models in ARM compute Library

[Afef00]

Due to the limited memory on Zedboard I was not able to build ARM NN and I choose the cross compilation of ARM NN on it. Now I want to implement a pruned model but I could'nt find any way for that? Is it even possible to do that? Regards

[morgolock]

Hi @Afef00

Have you managed to cross-compile ArmNN? Are you looking into doing inference on the Gpu or Cpu?

Can you confirm if your board has a CortexA9? https://developer.arm.com/Processors/Cortex-A9 . This is an armv7a architecture and ArmNN/ACL have been optimized for aarch64. You won't get great performance on the Cpu backend on armv7a. As an alternative I would suggest tflite.

Hope this helps.

[morgolock]

Closing this due to inactivity, please reopen if you still need support