Community
cancel
Showing results for 
Search instead for 
Did you mean: 
idata
Community Manager
739 Views

Both OpenVINO demos are failing

Both OpenVINO demos are failing, the ones that verify that the NCS device attached to the computer do work.

 

Here is the output when running one of the demos:

 

Run /opt/intel/computer_vision_sdk/deployment_tools/demo/../model_downloader/downloader.py --name "squeezenet1.1" ###############|| Start downloading models ||############### ...100%, 9 KB, 20257 KB/s, 0 seconds passed ========= squeezenet1.1.prototxt ====> /opt/intel/computer_vision_sdk_2018.2.300/deployment_tools/demo/classification/squeezenet/1.1/caffe/squeezenet1.1.prototxt ###############|| Start downloading weights ||############### ...100%, 4834 KB, 1600 KB/s, 3 seconds passed ========= squeezenet1.1.caffemodel ====> /opt/intel/computer_vision_sdk_2018.2.300/deployment_tools/demo/classification/squeezenet/1.1/caffe/squeezenet1.1.caffemodel ###############|| Start downloading topologies in tarballs ||############### ###############|| Post processing ||############### ========= Changing input dimensions in squeezenet1.1.prototxt ========= ################################################### Configure Model Optimizer INTEL_CVSDK_DIR environment variable is not set. Trying to run ./setvars.sh to set it. [setupvars.sh] OpenVINO environment initialized Found existing environment. Skipping installing dependencies for Model Optimizer. If you want to install again, remove venv directory. Then run the script again ################################################### Convert a model with Model Optimizer Target folder ir/squeezenet1.1 already exists. Skipping IR generation../demo_squeezenet_download_convert_run.sh: line 166: If you want to convert a model again, remove the entire ${$ir_dir} folder. ${run_again}: bad substitution ################################################### Build Inference Engine samples Target folder /opt/intel/computer_vision_sdk/deployment_tools/demo/../inference_engine/samples/build already exists. Skipping samples building.If you want to rebuild samples, remove the entire /opt/intel/computer_vision_sdk/deployment_tools/demo/../inference_engine/samples/build folder. Then run the script again ################################################### Run Inference Engine classification sample Run ./classification_sample -d CPU -i /opt/intel/computer_vision_sdk/deployment_tools/demo/../demo/car.png -m /opt/intel/computer_vision_sdk/deployment_tools/demo/../demo/ir/squeezenet1.1/squeezenet1.1.xml [ INFO ] InferenceEngine: API version ............ 1.1 Build .................. 11653 [ INFO ] Parsing input parameters [ INFO ] Loading plugin API version ............ 1.1 Build .................. lnx_20180510 Description ....... MKLDNNPlugin [ INFO ] Loading network files: /opt/intel/computer_vision_sdk/deployment_tools/demo/../demo/ir/squeezenet1.1/squeezenet1.1.xml /opt/intel/computer_vision_sdk/deployment_tools/demo/../demo/ir/squeezenet1.1/squeezenet1.1.bin [ INFO ] Preparing input blobs [ WARNING ] Image is resized from (787, 259) to (227, 227) [ INFO ] Batch size is 1 [ INFO ] Preparing output blobs [ INFO ] Loading model to the plugin [ INFO ] Starting inference (1 iterations) ./demo_squeezenet_download_convert_run.sh: line 201: 9265 Illegal instruction (core dumped) ./classification_sample -d $target_device -i $target_image_path -m "$ROOT_DIR/demo/${ir_dir}/squeezenet1.1.xml" Error on or near line 201; exiting with status 1

 

I get a similar error when running the other Demo as well.

 

Where do I find the core dump, that I can add to this message?

 

Here's my CPU info:

 

uinfo processor : 0 vendor_id : GenuineIntel cpu family : 6 model : 42 model name : Intel(R) Core(TM) i5-2415M CPU @ 2.30GHz stepping : 7 cpu MHz : 2294.770 cache size : 3072 KB physical id : 0 siblings : 2 core id : 0 cpu cores : 2 apicid : 0 initial apicid : 0 fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid pni pclmulqdq ssse3 cx16 sse4_1 sse4_2 x2apic popcnt aes xsave avx hypervisor lahf_lm pti flush_l1d bugs : cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf bogomips : 4589.54 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management: processor : 1 vendor_id : GenuineIntel cpu family : 6 model : 42 model name : Intel(R) Core(TM) i5-2415M CPU @ 2.30GHz stepping : 7 cpu MHz : 2294.770 cache size : 3072 KB physical id : 0 siblings : 2 core id : 1 cpu cores : 2 apicid : 1 initial apicid : 1 fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid pni pclmulqdq ssse3 cx16 sse4_1 sse4_2 x2apic popcnt aes xsave avx hypervisor lahf_lm pti flush_l1d bugs : cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf bogomips : 4589.54 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management:

 

And OS info:

 

Linux ubuntu 4.15.0-42-generic #45~16.04.1-Ubuntu SMP Mon Nov 19 13:02:27 UTC 2018 x86_64 x86_64 x86_64 GNU/Linux

 

Python info:

 

PYTHONPATH=:/opt/movidius/caffe/python

 

Python 3.5.2
Tags (1)
0 Kudos
1 Reply
idata
Community Manager
282 Views

Hi @neomatrix369,

 

Thanks for reaching out. I see that you are using the OpenVINO toolkit. Taking a look at the log description it looks like the Model Optimizer has not been set, that could be causing the error:

 

Configure Model Optimizer INTEL_CVSDK_DIR environment variable is not set. Trying to run ./setvars.sh to set it. [setupvars.sh] OpenVINO environment initialized Found existing environment. Skipping installing dependencies for Model Optimizer. If you want to install again, remove venv directory. Then run the script again.

 

Couple of suggestions to try:

 

     

  1. Set the environment variables by following the instructions in the OpenVINO documentation: https://software.intel.com/en-us/articles/OpenVINO-Install-Linux#inpage-nav-2-3. There is an option to set the environment variables permanently so you don't have to set them every time a new Terminal is opened.
  2.  

  3. Also configure the Model Optimizer as described in the OpenVINO documentation: https://software.intel.com/en-us/articles/OpenVINO-Install-Linux#inpage-nav-2-4.
  4.  

  5. If the problem continues, I'd suggest to report your issue in the OpenVINO community forum here: https://software.intel.com/en-us/forums/computer-vision.
  6.  

 

Hope this helps.

 

Best Regards,

 

Luis
Reply