It looks like you're new here. If you want to get involved, click one of these buttons!Sign In
It looks like you're new here. If you want to get involved, click one of these buttons!
I am trying to deploy a network called sphereface (https://github.com/wy1iu/sphereface#installation) on movidius stick using MvNC_SDK_1.07.10.
When I try to deploy it on the movidius stick by first compiling and generating the graph file using mvncCompile function provided by movidius and then using the python API, the inference results are coming as Nans. I have taken care of providing the data accurately by using the guidelines provided here(https://movidius.github.io/ncsdk/configure_network.html, https://movidius.github.io/ncsdk/Caffe.html) and used the sample code as a template.
It is running successfully and I am able to get the adequate results for inferencing with their trained model on my PC using the GPU.
You may find the python code in the following link (https://drive.google.com/open?id=0By7wafwe39eJcDZqbnhWSFlSb00)
Please let me know where I am going wrong.