mvNCCompile coredump when compiling caffe model

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.

mvNCCompile coredump when compiling caffe model

637 Views

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.

Link Copied

0 Replies

Community support is provided Monday to Friday. 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.