How to work the Yollo(Caffe) learned model which contains custom layers?

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.

How to work the Yollo(Caffe) learned model which contains custom layers?

438 Views

I want to infer the learned Yollo(Caffe) model with Movidius neural Compute Stick.

The learned model contains layers type which I created(custom layer).

The following error occurred when I am trying to make a Graph file using by mvNCCompile command.

/usr/local/bin/ncsdk/Controllers/CaffeParser.py:231: RuntimeWarning: invalid value encountered in sqrt
[Error 4] Toolkit Error: Stage Type Not Supported: Reorg

https://movidius.github.io/ncsdk/caffe.html

According to the website…

"Caffe Layer Support:The following layers are supported in Caffe by the NCSDK.

The NCSDK does not support network training, so some layers that are only required for training are not supported."

So I have a question, is it possible to work the Yollo(Caffe) learned model which includes custom layer

with Movidius neural Compute Stick?

If custom layer isn't supported, how can I use it on Movid neural Compute Stick?

Do you have any suggestions?

Link Copied

0 Replies

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.