hhk7734/tensorflow-yolov4

model assignment on multiple tpus

Opened this issue · 2 comments

hitch22 commented

Howdy,

I was wondering if there is a way to create multiple tflite interpreters so that I can assign and run multiple tpu models accordingly
(as outlined in: https://coral.ai/docs/edgetpu/multiple-edgetpu/#using-the-tensorflow-lite-python-api).

Could you please let me know if there is a way to run multiple models on different tpus?

Thanks in advance

hhk7734 commented

🤩 oh... I got to know this time.
I don't have USB-type edgeTPU.
It's a feature I want to test. When I'm done with what I'm doing now, I'll buy it and test it.

hitch22 commented

I see. It appears that "pci:" will let you choose the TPUs if you have the pci version.
I wonder if that will let me switch between my m.2 TPUs, which supposedly have 2 TPUs per chip.

🤩 oh... I got to know this time.
I don't have USB-type edgeTPU.
It's a feature I want to test. When I'm done with what I'm doing now, I'll buy it and test it.