Installing openvino raspberry pi 4

[fpardo]

Hi,

I've been trying to install openvino in a raspberry pi 4 using several methods. The last one is that pointed in this link:

https://www.intel.com/content/www/us/en/support/articles/000057005/boards-and-kits.html

I use as host machine Ubuntu 20.04 and following the steps in the guide I always got the same error when I try to build the image:

I've looking in forums but I couldn't found a solution to this problem. Any suggestions? Thanks in advance.

[Peh_Intel]

Hi Fpardo,

I would strongly recommend you to install OpenVINO™ Runtime for Raspbian OS using OpenVINO Runtime archive file for Debian (l_openvino_toolkit_debian9_2022.3.1.9227.cf2c7da5689_armhf.tgz).

1. Download and extract the archive file.
2. Install required system dependencies on Linux by running install_openvino_dependencies.sh script.
3. Set the Environment Variables by sourcing setupvars.sh script.
4. Setup Intel® Neural Compute Stick 2 by follow the steps in Configurations for Intel® Neural Compute Stick 2.

Regards,

Peh

[fpardo]

Hello,

I tried that way but when I install openvino development tools:

pip install openvino-dev==2022.3.1

I get an error duting the process. I have tried with both 32/64 bits and bullseye/buster and none of the installation worked.

Thanks for your time.

Regards

Nando

[Peh_Intel]

Hi Nando,

Installing Intel® Distribution of OpenVINO™ Toolkit from PyPI Repository (pip install openvino-dev==2022.3.1) is only available for the following supported OS:

• Ubuntu* 22.04 long-term support (LTS), 64 bit (Kernel 5.15+)
• Ubuntu 20.04 LTS, 64 bit (Kernel 5.15+)
• Ubuntu 18.04 LTS with limitations, 64 bit (Kernel 5.4+)
• Windows® 10 and 11
• macOS* 10.15 and later, 64 bit
• Red Hat* Enterprise Linux* 8, 64 bit

Hence, we additionally provide OpenVINO™ Runtime archive file for Debian. Since, this package doesn’t include Model Optimizer/Model Downloader, the ideal scenario is to use another machine to convert your model with Model Optimizer, then do your application development on the Raspberry Pi for a convenient build/test cycle on the target platform.

For OpenVINO™ Toolkit Intel’s Pre-Trained Models, you can directly download them through the following link:

https://storage.openvinotoolkit.org/repositories/open_model_zoo/2022.3/models_bin/1

Regards,

Peh

[fpardo]

Thanks for the information !!!

Regards

Fernando

[Peh_Intel]

Hi Fernando,

This thread will no longer be monitored since we have provided suggestion and answer. If you need any additional information from Intel, please submit a new question. 

Regards,

Peh