Hi all,
I am trying to run some inferences using the OpenVINO Workbench Docker image https://hub.docker.com/r/openvino/workbench . Everything works well using my CPU as targeted device (Configuration -> Select Environment). But I get the following error when I select my Intel Movidius Myriad X VPU (a Neural Compute Stick 2):
"Cannot infer this model on Intel(R) Movidius(TM) Neural Compute Stick 2 (NCS 2). Possible causes: Drivers setup failed. Update the drivers or run inference on a CPU." (cf attached screenshot).
I did not change the start_workbench.sh script. Here are my execution params:
./start_workbench.sh -IMAGE_NAME openvino/workbench -TAG latest -ENABLE_MYRIAD -DETACHED -ASSETS_DIR /hdd-raid0/openvino_workbench
However, I can play with the NCS2 using the classification or cross check commands provided by https://hub.docker.com/r/openvino/ubuntu18_dev.
Any idea ?
Thxxxx!
Link Copied
All I can say is this is a very old product question. You can't infer anything. Because a wild guess you are using the device's graphics. In fact it's supposed to be empty. Good luck777
Greetings,
You need to install the NCS2 driver correctly before doing any inferencing or etc with it.
Both MYRIAD(NCS2) and hddl is supported as in here: https://docs.openvinotoolkit.org/latest/workbench_docs_Workbench_DG_Install_Workbench.html
Make sure to select according to your OS and follow the additonal steps required to activete the NCS2 usage: https://docs.openvinotoolkit.org/latest/openvino_docs_IE_DG_supported_plugins_MYRIAD.html
Sincerely,
Iffa
Could you please tell me where is mentioned that NCS2 drivers are required, when following the Docker based installation ?
Thxxx
This is how you can use a Docker* Image for Intel® Vision Accelerator Design with Intel® Movidius™ VPUs: https://docs.openvinotoolkit.org/latest/openvino_docs_install_guides_installing_openvino_docker_linu...
Kindly navigate to the specific topic. You will find that there are a few additional steps to be done before NCS2 can be used with Docker.
and see Configuration guide for HDDL device or Configuration Guide for Intel® Vision Accelerator Design with Intel® Movidius™ VPUs as mentioned in the above link.
Sincerely,
Iffa
I finally followed the non docker based installation procedure
https://docs.openvinotoolkit.org/latest/workbench_docs_Workbench_DG_Install_from_Package.html
(including)-> "Install OpenVINO™ Package"
(including)-> https://docs.openvinotoolkit.org/latest/openvino_docs_install_guides_installing_openvino_linux.html
(including)->"Steps for Intel® Neural Compute Stick 2"
At the end, it is asked to start the workbench container (even if you followed the non docker based installation).. and inferences on the Myriad work.
Thx a lot for your quick replies... I think Intel must reorganize this documentation.
++
The issue is noted.
Thanks for your feedback.
If you don't have any further inquiries, shall I close this thread?
Sincerely,
Iffa
Yes! Thx a lot.
Greetings,
Intel will no longer monitor this thread since this issue has been resolved. If you need any additional information from Intel, please submit a new question
Thanks.
Sincerely,
Iffa
For more complete information about compiler optimizations, see our Optimization Notice.