Error while trying to execute segnet example (with tensorRT 2.1) on Ubuntu 16.04

Accelerated Computing GPU-Accelerated Libraries
1

Hi !

I’m trying to execute a segnet example on my host machine in order to split the sky and the terrain on a picture (FCN AlexNet).
I’m using TensorRT 2.1 and my machine is on Ubuntu 16.04.
I have a pretrained model.

I use this command :

./segnet-console drone_0428.png output_0428.png \--prototxt=deploy.prototxt \--model=snapshot_iter_27132.caffemodel \--labels=fpv-labels.txt \--colors=fpv-deploy-colors.txt \--input_blob=data \--output_blob=score_fr

And i get this :

segnet-console
  args (9):  0 [./segnet-console]  1 [drone_0428.png]  2 [output_0428.png]  3 [--prototxt=deploy.prototxt]  4 [--model=snapshot_iter_27132.caffemodel]  5 [--labels=fpv-labels.txt]  6 [--colors=fpv-deploy-colors.txt]  7 [--input_blob=data]  8 [--output_blob=score_fr]  


segNet -- loading segmentation network model from:
       -- prototxt:   deploy.prototxt
       -- model:      snapshot_iter_27132.caffemodel
       -- labels:     fpv-labels.txt
       -- colors:     fpv-deploy-colors.txt
       -- input_blob  'data'
       -- output_blob 'score_fr'
       -- batch_size  2

[GIE]  attempting to open cache file snapshot_iter_27132.caffemodel.2.tensorcache
[GIE]  cache file not found, profiling network model
terminate called after throwing an instance of 'nvinfer1::CudaError'
  what():  std::exception
Aborted (core dumped)

Here is the backtrace from gdb :

#0  0x00007ffff715f428 in __GI_raise (sig=sig@entry=6) at ../sysdeps/unix/sysv/linux/raise.c:54
#1  0x00007ffff716102a in __GI_abort () at abort.c:89
#2  0x00007fffeed4b84d in __gnu_cxx::__verbose_terminate_handler() ()
   from /usr/lib/x86_64-linux-gnu/libstdc++.so.6
#3  0x00007fffeed496b6 in ?? () from /usr/lib/x86_64-linux-gnu/libstdc++.so.6
#4  0x00007fffeed49701 in std::terminate() () from /usr/lib/x86_64-linux-gnu/libstdc++.so.6
#5  0x00007fffeed49919 in __cxa_throw () from /usr/lib/x86_64-linux-gnu/libstdc++.so.6
#6  0x00007ffff0fe15e8 in nvinfer1::throwCudaError(char const*, char const*, int, int, char const*)
    () from /usr/lib/x86_64-linux-gnu/libnvinfer.so.3
#7  0x00007ffff0fe2f6d in nvinfer1::cudnn::hasNativeFp16() ()
   from /usr/lib/x86_64-linux-gnu/libnvinfer.so.3
#8  0x00007ffff1001e07 in nvinfer1::cudnn::HardwareContext::HardwareContext() ()
   from /usr/lib/x86_64-linux-gnu/libnvinfer.so.3
#9  0x00007ffff0ffcd25 in createInferBuilder_INTERNAL ()
   from /usr/lib/x86_64-linux-gnu/libnvinfer.so.3
#10 0x00007ffff751646b in nvinfer1::(anonymous namespace)::createInferBuilder(nvinfer1::ILogger&) ()
   from /home/poudlard/TensorRT/jetson-inference-master/build/x86_64/lib/libjetson-inference.so
#11 0x00007ffff7516811 in tensorNet::ProfileModel(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > const&, unsigned int, std::ostream&) ()
   from /home/poudlard/TensorRT/jetson-inference-master/build/x86_64/lib/libjetson-inference.so
#12 0x00007ffff7516edf in tensorNet::LoadNetwork(char const*, char const*, char const*, char const*, std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocator<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > const&, unsigned int) ()
   from /home/poudlard/TensorRT/jetson-inference-master/build/x86_64/lib/libjetson-inference.so
#13 0x00007ffff7514e2c in segNet::Create(char const*, char const*, char const*, char const*, char const*, char const*, unsigned int) ()
   from /home/poudlard/TensorRT/jetson-inference-master/build/x86_64/lib/libjetson-inference.so
#14 0x00007ffff7514c40 in segNet::Create(int, char**) ()
   from /home/poudlard/TensorRT/jetson-inference-master/build/x86_64/lib/libjetson-inference.so
#15 0x0000000000403140 in main ()

Any idea what I did wrong ? :(

Thanks a lot !

2

Hi !

For information : despite the update of the segNet example last week, I still have the same issue.
Anybody have any clue on the origin of this ?

Thanks !

3

Solved.
I had an issue with Nvidia’s drivers.
Solution : Reinstall + reboot.