No module named 'openvino.runtime'

[cimo]

Hi

I'm cimo,when i use this demo: face recognition demo,I have encountered some problems.

I am using a combination of Raspberry and NCS2，I have configured the Raspberry Access Environment in accordance with the official documentation， and  i successfully passed the test sample.For this demo , i have downloaded three module it need。But when i run:

python3 face_recognition_demo.py \

-i /dev/video0 \

-m_fd face-detection-retail-0004.xml \

-m_lm landmark-regression-retail-0009.xml \

-m_reid face-reidentification-retail-0095.xml \

--verbose \

-fg "/home/pi/facevideo/face_gallery" \

 -d_fd MYRIAD -d_lm MYRIAD -d_reid MYRIAD

It reminds me :

Traceback (most recent call last):
File "face_recognition_demo.py", line 26, in <module>
from openvino.runtime import Core, get_version
ModuleNotFoundError: No module named 'openvino.runtime'

I am very confused about this.I have installed Openvino correctly on the Raspberry.Does anyone help me?

My English is very poor. If there is a mistake, please forgive me, I am very grateful to everyone.

Here is some of mine config:

raspberry 4B (system:buster);

NCS2;

python 3.7 ;

l_openvino_toolkit_runtime_raspbian_p_2021.4.752.

Thank you again for your help again.

[Vladimir_Dudnik]

@cimo starting from OpenVINO 2022.1 OMZ python demo requires to install additional component for Open Model Zoo Model API, see documentation for more details.

Installing Python* Model API package

Use the following command to install Model API from source:

pip install <omz_dir>/demos/common/python

[cimo]

Thank you very much for your reply!

I have tried to do this and read the document carefully.If I have encountered any problems again, I hope you can enlighten me.Because my English level is general, reading documents is more difficult, and Chinese documents have not been updated for a long time.

[Wan_Intel]

Hi Cimo,

Thanks for reaching out to us.

Do you git clone the Open Model Zoo master branch on your Raspberry Pi 4B?

For your information, you have to git clone the specific branch of Open Model Zoo that match your OpenVINO™ Toolkit package.

I noticed that you are using l_openvino_toolkit_runtime_raspbian_p_2021.4.752 package on your Raspberry Pi 4B.

Therefore, you have to git clone the Open Model Zoo branch 2021.4.2 as follows:

git clone --depth 1 -b 2021.4.2 https://github.com/openvinotoolkit/open_model_zoo

If you encountered: ModuleNotFoundError: No module named 'ngraph' when running Python sample application, please refer to Building Open Source OpenVINO™ toolkit for Raspbian* OS and Intel® Neural Compute Stick 2 to resolve the issue.

On another note, the latest Chinese documents of OpenVINO™ Toolkit can be accessed as follows:

 

Regards,

Wan

[cimo]

Hi Wan,

To be honest, I am really touched by seeing everyone's reply.About Raspberry Parts and NCS2, less information or less documentation in Chinese.Most of them just built the face detection section, and  less people to build recognition demo, after all, the edge calculation's force is lower.But I am very interested in this，Your help and reply are critical to me.

I had git clone the Open Model Zoo branch 2021.4.2 when i start this project, now my OpenCV-Python version has a problem. Before this, your have good helps to me,so i am going well.

The latest document is only a directory is Chinese.But even if this makes me convenient.

I am sorry about my poor English ability again.I  use the translation software sometime,Thank you for your inclusive and your reply, I wish you a happy life.

[Wan_Intel]

Hi Cimo,

Thank you for your question.

If you need any additional information from Intel, please submit a new question as this thread is no longer being monitored.

Regards,

Wan