Movidius plugin

[yleal]

Hi everyone,

I'm trying to get the Movidius plugin following the steps from https://docs.openvino.ai/latest/openvino_docs_install_guides_installing_openvino_ivad_vpu.html#doxid-openvino-docs-install-guides-installing-openvino-ivad-vpu for Linux, but the first command: 

source /opt/intel/openvino_2022/setupvars.sh

I don't have that directory, just openvino or openvino_env, when I do the previous steps about getting openvino. But there is not setupvars. I mean, it isn't anywhere. What did I forget to do or what is it wrong? What should I do to get that plugin (for myriad, vpu)???

Thank you so much.

[Hairul_Intel]

Hi yleal,

Thank you for reaching out to us.

Please follow the Install OpenVINO™ Runtime on Linux from an Archive File guide to install OpenVINO™ Runtime on Linux.

Once you’ve finished the installation, the setupvars.sh file should be located in the following directory:

/opt/intel/openvino_2022.2.0.7713

Regards,

Hairul

[yleal]

Thank  you  very much, it did work. 

Now I have two other problems:

1) When I build the demo applications on Linux (I go to  the correct directory), I run 

build_demos.sh

but I get 

build_demos.sh: command not found

2) I want to run face detection MTCNN Python Demo, and I nedeed to add mtcnn-p/o/r.xml files, but they are not in they directory they were before, I think that's because I follow the instruction to convert them omz_converter --list models.lst (not sure, but before they were there), so I get the following error:

How can I solve these errors? 

[Hairul_Intel]

Hi yleal,

To run the script for building the samples (<openvino_dir>/samples/c or <openvino_dir>/samples/cpp directory), run the following command in a terminal:

source build_samples.sh

Here is the directory for the completed build samples:

/home/<user>/inference_engine_.samples_build/intel64/Release

Regarding the MTCNN models, you can download and convert it again using OpenVINO™ Development Tools.

Run the following command to download the MTCNN models:

omz_downloader --name mtcnn

Run the following command to convert the MTCNN models:

omz_converter --name mtcnn

Pease note that the MTCNN models required by Face Detection MTCNN Python* Demo is only supported on CPU and GPU devices but not supported on MYRIAD devices. Refer to the Public Pre-Trained Models Device Support for more information.

Regards,

Hairul

[yleal]

Ok! Thank you very much, I did not realize! 

If I try to build the demo apps, writting source build_demos.sh as indicated in https://docs.openvino.ai/latest/omz_demos.html 

I get this and I don't know why, how can I solve??

-- Detecting CXX compile features - done
CMake Error at CMakeLists.txt:140 (find_package):
By not providing "FindOpenCV.cmake" in CMAKE_MODULE_PATH this project has
asked CMake to find a package configuration file provided by "OpenCV", but
CMake did not find one.

Could not find a package configuration file provided by "OpenCV" with any
of the following names:

OpenCVConfig.cmake
opencv-config.cmake

Add the installation prefix of "OpenCV" to CMAKE_PREFIX_PATH or set
"OpenCV_DIR" to a directory containing one of the above files. If "OpenCV"
provides a separate development package or SDK, be sure it has been
installed.

[Hairul_Intel · Accepted solution]

Hi yleal,

For your information, some OpenVINO samples can also extend their capabilities when compiled with OpenCV as a dependency. To install OpenCV for OpenVINO, see the instructions on GitHub.

Run the following command to install OpenCV from default Ubuntu repositories:

sudo apt update

sudo apt install libopencv-dev python3-opencv

Regards,

Hairul

[Hairul_Intel]

Hi yleal,

This thread will no longer be monitored since this issue has been resolved. If you need any additional information from Intel, please submit a new question.

Regards,

Hairul