I'm trying to convert SSD facedetection Caffe model, but mvNCCompile coredumps very time I attempt to do that:
$ mvNCCompile ssd.prototxt -w ssd.caffemodel -s 12 -o ssd.graph
mvNCCompile v02.00, Copyright @ Movidius Ltd 2016
WARNING: Logging before InitGoogleLogging() is written to STDERR
F0803 16:52:59.384896 2180 blob.cpp:507] Check failed: count_ == proto.data_size() (4704 vs. 0)
*** Check failure stack trace: ***
Aborted (core dumped)
Anyone has any ideas? This model works perfectly fine when loaded into openCV using readNetFromCaffe() function and performs the inference perfectly fine. It somehow causes mvNCCompile to coredump during conversion.
The model I'm trying to convert can be found here
and protoxt
here
I'm using API V1 because like I mentioned here before, V2 is broken beyond belief and no one at Intel seems to pay any attention to it, so, yeah.
