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.
6404 Discussions

Is it possible to run certain layers of a network on different devices on Tensorflow?

idata
Employee
‎08-06-2018 06:00 AM
531 Views

Hello All, Hope all are doing okay.

 

I have a problem regarding tensorflow with NCS….here is my question.

 

I have been trying to run inference on a custom Tensorflow model on Movidius Neural Compute Stick. The problem is, the final layer is unsupported by NCSDK. Since the final layer is computationally quite light, I would like to know if there is a possibility to run that layer on CPU?

 

My previous searches led me to these:

 

     

  1. Distributed Computing Tensorflow

    2.  

  2. Placing Variables on CPU??

    3.  

 

I just need to be able to run inference up to a certain layer on the NCS, then process the last layer on CPU.

 

Thanks

0 Kudos

Link Copied

0 Replies
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.