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.
6392 Discussions

Any plan to support custom batch size or batch inference?

idata
Employee
556 Views

As title, I know the batch size is fixed to 1 while conversion currently.

 

I wonder if there is a chance that this constraint would be changed in the future?
0 Kudos
1 Reply
idata
Employee
241 Views

@amacs.mist At the moment, there are no plans to change the batch size. With NCSDK v 2.04, you can now pipeline inferences from several networks on a single ncs device using the new fifo class. You can read more about it for the Python API at https://movidius.github.io/ncsdk/ncapi/python_api_migration.html and here is some example code https://github.com/movidius/ncappzoo/blob/ncsdk2/apps/image-classifier/image-classifier.py.

0 Kudos
Reply