Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.
6570 Discussions

Need help in enabling Openvino for "AI Core XM 2280"

Gupta_harsh
Beginner
1,332 Views

Hi Team,

As my previous thread is closed , so that's why raising a new thread with the same problem as it did not got solved yet.

previous thread- 1653390#M31702 @Faiz_Intel 

 tried to installed OpenVINO Runtime version 2022.3.2 (LTS) using the Archive File method.

Steps followed :

Step 1: To install OpenVINO™ Runtime on Linux from an Archive File.

1. Create the /opt/intel folder for OpenVINO. If the folder already exists, skip this step.

sudo mkdir /opt/intel

[Note: The /opt/intel path is the recommended folder path for administrators or root users. If you prefer to install OpenVINO in regular userspace, the recommended path is /home/<USER>/intel. You may use a different path if desired.]

 

2. Browse to the current user’s Downloads folder.

cd <user_home>/Downloads

 

3. Download the OpenVINO Runtime archive file for your system.

(a) For Ubuntu 18.04, you can download the archive file from here, or use the following command on terminal.

curl -L https://storage.openvinotoolkit.org/repositories/openvino/packages/2022.3.2/linux/l_openvino_toolkit_ubuntu18_2022.3.2.9279.e2c7e4d7b4d_x86_64.tgz --output openvino_2022.3.2.tgz

(b) For Ubuntu 20.04, you can download the archive file from here, or use the following command on terminal.

curl -L https://storage.openvinotoolkit.org/repositories/openvino/packages/2022.3.2/linux/l_openvino_toolkit_ubuntu20_2022.3.2.9279.e2c7e4d7b4d_x86_64.tgz --output openvino_2022.3.2.tgz

 

4. Extract the file.

tar -xf openvino_2022.3.2.tgz

 

5. Rename the extracted folder.

(a) For Ubuntu 18.04, use the following command.

sudo mv l_openvino_toolkit_ubuntu18_2022.3.2.9279.e2c7e4d7b4d_x86_64 /opt/intel/openvino_2022.3.2

(b) For Ubuntu 20.04, use the following command.

sudo mv l_openvino_toolkit_ubuntu20_2022.3.2.9279.e2c7e4d7b4d_x86_64 /opt/intel/openvino_2022.3.2

 

6. Install required system dependencies on Linux.

cd /opt/intel/openvino_2022.3.2

sudo -E ./install_dependencies/install_openvino_dependencies.sh

 

7. (Optional) Install numpy Python Library.

[Note: This step is required only when you decide to use Python API.]

cd /opt/intel/openvino_2022.3.2

python3 -m pip install -r ./python/python3.<x>/requirements.txt

 

8. For simplicity, it is useful to create a symbolic link as below.

cd /opt/intel

sudo ln -s openvino_2022.3.2 openvino_2022

[Note: If you have already installed a previous release of OpenVINO 2022, a symbolic link to the openvino_2022 folder may already exist. Unlink the previous link with sudo unlink openvino_2022, and then re-run the command above. The /opt/intel/openvino_2022 folder now contains the core components for OpenVINO.]

 

Step 2: To configure VPU, the following additional installation steps are required.

1. Set the environment variables.

[Note: You must update several environment variables before you can compile and run OpenVINO applications. Open a terminal window and run the setupvars.sh script as shown below to temporarily set your environment variables. If your <INSTALL_DIR> is not /opt/intel/openvino_2022, use the correct one instead. The command must be re-run every time you start a new terminal session.]

source /opt/intel/openvino_2022/setupvars.sh

 

2. Install dependencies.

/opt/intel/openvino_2022/runtime/3rdparty/hddl/install_IVAD_VPU_dependencies.sh

 

[Note: If the Linux kernel is updated after the installation, it is required to install drivers again.]

cd /opt/intel/openvino_2022/runtime/3rdparty/hddl/drivers

sudo ./setup.sh install

Screen shot for after these steps is attached:


Additionally, I also ran few commands to check the installation of VPU and also to verify if our VPU is connected and available on Linux .
Also attaching the output of that commands.
Commands that I ran are:

1)lspci

2)lsusb

3)python3 -c "from openvino.runtime import Core; print(Core().available_devices)"

4)python3 -c "from openvino.runtime import get_version; print(get_version())"



So, could you please check why VPU is not getting detecting when i am printing the core().available_devices


Thanks

0 Kudos
4 Replies
Aznie_Intel
Moderator
1,274 Views

Hi Gupta_harsh,

 

Thank you for reaching out, and apologize for the inconvenience. After the installation, could you please check if the device is listed in the /dev/ directory by running the following command:

ls /dev/hddl*

 

You should see a device like /dev/hddl0, indicating that the VPU is recognized. Additionally, please review the system logs for any issues related to the device initialization by running:

dmesg | grep -i hddl

Let me know if you encounter any issues!

 

 

Regards,

Aznie

 

0 Kudos
Gupta_harsh
Beginner
1,243 Views

Hi Aznie,

As per your suggestion I ran the commands and still not able to recognize the VPU.

Also adding the screenshot for those commands.
dmesg.png

Thanks

0 Kudos
Aznie_Intel
Moderator
1,203 Views

Hi Gupta_harsh,

 

I will escalate this to the engineering team for further investigation and will update you with the information shortly.

 

 

Regards,

Aznie


0 Kudos
Aznie_Intel
Moderator
742 Views

Hi Gupta_harsh,


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,

Aznie


0 Kudos
Reply