Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.
6251 Discussions

Run Multilple Models in Asynchronous mode

Nguyen__Vuong
Beginner
‎04-16-2019 08:25 PM
156 Views

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. 

0 Kudos

Link Copied

1 Reply
Truong__Dien_Hoa
New Contributor II
‎04-18-2019 07:21 AM
156 Views

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

0 Kudos
Copy link
Reply

Community support is provided during standard business hours (Monday to Friday 7AM - 5PM PST). Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.