Hi, I'm building the face-recognition system on the INTEL UPSQUARED. I have converted the necessary model. Here's my workflow: DETECTING FACES -> FACE ALIGNMENT -> EXTRACTING EMBEDDING VECTORS -> COMPUTING EUCLIDEAN DISTANCE. I intend to run the detecting model on GPU, the extracting model on the VPU (MYRIAD) and computing the distance on CPU. Is there any way that I can run 2 models in Asynchronous mode ( in Python ). Thank you very much.
I think you can create 2 differents threads (or process) to run 2 models in parallel. Maybe using a queue in python (which is guaranteed to thread-safe). Hope that helps