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
1,580 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.

link of the previous thread-

"community.intel.com/t5/Intel-Distribution-of-OpenVINO/Need-help-in-enabling-Openvino-for-quot-AI-Core-XM-2280-quot/m-p/1638456#M31551"

Main problem:

I am trying to install OpenVino SDK that supports VPU (AI Core XM 2280) on intel Up Xtreme Device. However I couldn't able to figure which version of OpenVino should I be using for the same.

After installation of latest openvino package when i am running below command still it is showing ["CPU"] only and VPU is still not detecting.

python -c "from openvino import Core; print(Core().available_devices)"


As per suggestion provided by @zulkifli, I also tried :
Tried to install openvino using the installater.
But after successful installation when i am checking the devices using command:
python -c "from openvino import Core; print(Core().available_devices)"

It is still showing ["CPU"] only and VPU is still not detecting.

0 Kudos
1 Solution
Faiz_Intel
Moderator
1,498 Views

Hi Gupta_harsh,

Thank you for reaching out to us.

 

Could you please confirm if you have installed OpenVINO Runtime version 2022.3.2 (LTS) using the Archive File method? If not, kindly follow the steps outlined below to proceed with the installation.


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



Regards,

Faiz


View solution in original post

0 Kudos
4 Replies
Faiz_Intel
Moderator
1,499 Views

Hi Gupta_harsh,

Thank you for reaching out to us.

 

Could you please confirm if you have installed OpenVINO Runtime version 2022.3.2 (LTS) using the Archive File method? If not, kindly follow the steps outlined below to proceed with the installation.


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



Regards,

Faiz


0 Kudos
Gupta_harsh
Beginner
1,396 Views

Hi Faiz,

Thank you for providing the detailed steps to enable the VPU. I have followed the instructions as you outlined and have completed the process. I have also attached a screenshot of the final step for your reference. Could you kindly confirm if the installation was successful and if everything is set up correctly?

Additionally, I would appreciate it if you could elaborate on the commands that can be used to check the current VPU device in use. The following command, which I attempted, does not seem to work:

 

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

 

Lastly, if there are any sample applications available that demonstrate how to utilize the VPU effectively, I would be grateful if you could share them or provide further guidance.

Looking forward to your response and assistance.

Thanksinstall.png

0 Kudos
Faiz_Intel
Moderator
1,336 Views

Hi Gupta_harsh,

Firstly, could you please verify if your VPU is connected and available on Linux?


(a) Since the AI Core XM 2280 uses the PCIe interface, check if it is listed using the following command:

lspci

This will display all PCIe devices, and you should see an entry for the VPU.


(b) However, if it's connected through USB (like other VPUs), you can run:

lsusb

Look for entries related to the VPU.


To verify if OpenVINO is correctly installed, run the following command:

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

If OpenVINO was successfully installed, you will see a list of available devices.


To check the version of OpenVINO Runtime, run the following command:

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


Kindly share screenshots of the outputs for the commands above to assist in verification. Additionally, please confirm whether you are developing in C/C++ or Python?



Regards,

Faiz


0 Kudos
Faiz_Intel
Moderator
1,126 Views

Thank you for your question. If you need any additional information from Intel, please submit a new question as Intel is no longer monitoring this thread.


0 Kudos
Reply