I am learning to write custom kernels on various platforms and ive found a very nice tutorial for CPU and GPU as follows:
I wanted to know if there is a similar tutorial for VPU and NCS2 as well?
Hi Ghulam Jilani,
Thank you for reaching out.
The Inference Engine supports only CPU and GPU custom kernels, it is not possible to write custom kernels for the VPU.
If you got any other question, feel free to ask.
Thanks for responding. But the following document describes a method to write custom layers for the NCS2 as well, can you please explain in which case or how this is applicable?
Hello Ghulam Jilani,
I apologize for the confusion, I was not aware of this document.
It is possible to implement a custom layer for VPUs. Is there a particular section of the guide that you need assistance with?