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.
6406 Discussions

Back propogation

idata
Employee
‎07-25-2018 09:12 AM
633 Views

Haven't seen anything to suggest the NCS supports this, but just wanted to double check that there's no back prop support in the current API ( 2.05 ), and that any arbitrary layer in the model cannot be read out using updated weights.

 

Many thanks..

0 Kudos

Link Copied

2 Replies
idata
Employee
‎07-25-2018 04:56 PM
315 Views

@Jay The NCS is designed to be used with models that are ready for deployment, therefore there isn't any back propagation or training related support in the NCSDK. If any changes are to be made to the model (layers, weights, etc), it must be done before compiling the model for the NCSDK. Once a model is converted to a Movidius graph file format, changes cannot be made to the model.

0 Kudos
Copy link
idata
Employee
‎07-26-2018 08:12 AM
315 Views

Thanks @Tome_at_Intel

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.