It looks like you're new here. If you want to get involved, click one of these buttons!Sign In
Thanks for the help getting the graph frozen and mvNCCompile running. I am still getting a compile error:
~/workspace/movidius$ mvNCCompile ./frozen_v5_detector.pb -in input_map -on detection_output/Sigmoid -s12 -o ./movidius_v5_detector.graph
mvNCCompile v02.00, Copyright @ Movidius Ltd 2016
/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py:766: DeprecationWarning: builtin type EagerTensor has no module attribute
EagerTensor = c_api.TFE_Py_InitEagerTensor(_EagerTensorBase)
/usr/local/lib/python3.5/dist-packages/tensorflow/python/util/tf_inspect.py:45: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead
if d.decorator_argspec is not None), _inspect.getargspec(target))
[Error 5] Toolkit Error: Stage Details Not Supported: ResizeNearestNeighbor
It looks to me that mvNCCompile doesn't support the upsampling layers. Will this be supported in future releases, and if so, do you have a estimate of the release date?
I've tried to open NCS device through JAVA APP call JNI (JNI wrap the mvncOpenDevice API), but it always report cannot open NCS device with return code -6, which is "MVNC_TIMEOUT Timeout in the communication with the device", can you help me out ... and is there any successful work on this pipeline ?
I am trying to install the API. But, I am running into the same error which is described in the post: https://ncsforum.movidius.com/discussion/132/undefined-reference-to-libusb-strerror#latest. I have really tried everything I could but I cannot solve it. Could you please help?
Thank you in advance,