frame

Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

Sign In

Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

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

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?

Sign In or Register to comment.