Context :
I would like to inference my CNN model on IMX-8qxp unit. As your website states, inference is supported on Vulkan GPU on IMX-8qxp through eIQ for ARM-NN & TF-Lite models(https://www.nxp.com/docs/en/fact-sheet/EIQ-FS.pdf )[Page-2] . Following are the related questions.
Questions :
1) IMX-8qxp has 1x4-shader Vulkan GPU. Can we access this GPU using latest eIQ package for CNN model inference?
2) If yes, would you please share some reference documents?
3) If GPU based CNN inference is supported, can we use eIQ as stand-alone module or does it BSP to be rebuilt?
4) GpuAcc flag in ARM-NN supports only Mali-based GPU. Can you please point me to a sample C++ testapp in which eIQ is used for inference on Vulkan GPU?
