# Prerequisites

Complete these preconditions before running the AI/ML sample applications.

1. Activate SSH on your Qualcomm Linux or Ubuntu host to sign in with SSH and connect to the target device. For instructions see:

    - [Sign in using SSH](https://docs.qualcomm.com/bundle/publicresource/topics/80-70029-254/how_to.html#use-ssh) for Qualcomm Linux
    - [Sign in using SSH](https://docs.qualcomm.com/bundle/publicresource/topics/80-90441-1/Use_Ubuntu_on_RB3_Gen2_3.html#sign-in-to-the-rb3-gen-2-console-using-ssh) for Ubuntu Server

Note

If SSH is already set up and Wi-Fi is connected, skip this step.
2. Sign in to the target device using SSH:

    - For Qualcomm Linux:

ssh root@<ip address of target device>
            Copy to clipboard
    - For Ubuntu Server:

ssh ubuntu@<ip address of target device>
            Copy to clipboard
3. On the target device, obtain the `download_artifacts.sh` script, set executable permissions, and run it to download the model, media, and label files:

cd /tmp/
        Copy to clipboard

curl -L -O https://raw.githubusercontent.com/quic/sample-apps-for-qualcomm-linux/refs/heads/main/qualcomm-linux/scripts/download_artifacts.sh
        Copy to clipboard

chmod +x download_artifacts.sh
        Copy to clipboard

./download_artifacts.sh
        Copy to clipboard

Note

For the Ubuntu build, use the `sudo` command.
4. The YOLOv8 model isn’t available by default. You can use the following options to either download the models using a script or export them with Qualcomm AI Hub APIs on the Linux host computer.

    If you are using [Multistream batch inference](https://docs.qualcomm.com/doc/80-70029-50/topic/multistream-batch-inference.html) application, you can generate a batch model.

    1. Download the models using a script:

        1. Create a [Qualcomm AI Hub account](https://app.aihub.qualcomm.com/account/).
        2. Select the account name, then go to **Settings** in the upper right corner, and select the API token.
        3. Export the models on the Linux host computer and set the required permissions:

curl -L -O https://raw.githubusercontent.com/quic/sample-apps-for-qualcomm-linux/refs/heads/main/qualcomm-linux/scripts/export_model.sh
                Copy to clipboard

chmod +x export_model.sh
                Copy to clipboard

            Replace *API\_TOKEN* with the selected key:

./export_model.sh --api-token=<API_TOKEN>
                Copy to clipboard
    2. Export the [YOLOv8-Detection-Quantized](https://github.com/quic/ai-hub-models/tree/main/qai_hub_models/models/yolov8_det) model using Qualcomm AI Hub APIs.

        Run the following command from the python environment that’s created from `export_model.sh`. For example, to export the YOLOv8 LiteRT model:

python -m qai_hub_models.models.yolov8_det.export --quantize w8a8 --target-runtime=tflite --device="Dragonwing RB3 Gen 2 Vision Kit"
            Copy to clipboard

        Activate the miniconda environment that’s created from the `export_model.sh` script:

source miniconda/bin/activate
            Copy to clipboard
    3. Generate a batch model.

        To change the batch size of the model, update *&lt;N&gt;* in the following `export` command:

python -m qai_hub_models.models.<Model_Name>.export --batch-size <N> --device="Dragonwing RB3 Gen 2 Vision Kit"
            Copy to clipboard

        For example, to export the YOLOv8 LiteRT model with `--batch-size 4`, run the following command from the python environment that’s created from `export_model.sh`:

python -m qai_hub_models.models.yolov8_det.export --quantize w8a8 --target-runtime=tflite --device="Dragonwing RB3 Gen 2 Vision Kit" --batch-size 4
            Copy to clipboard

        For example, to export the YOLOv8 QNN model, run the following command from the python environment that’s created from `export_model.sh`:

python -m qai_hub_models.models.yolov8_det.export --quantize w8a8 --target-runtime=qnn_context_binary --device="Dragonwing RB3 Gen 2 Vision Kit" --compile-options="--qairt_version 2.40" --profile-options "--qairt_version 2.40"
            Copy to clipboard

        - Update the `--qairt_version` value in the command to match the version installed on your device.
        - To check the QAIRT version, run the following command on the target device:

qnn-net-run --version
                Copy to clipboard
        - To find the QAIRT SDK versions that AIHUB supports for the export command, run the following command on your host machine:

qai-hub list-frameworks
                Copy to clipboard
        - Run the following command in the AIHUB environment to view the supported devices and update the device parameter accordingly:

qai-hub list-devices
                Copy to clipboard
5. The `download_artifacts.sh` script downloads a sample `video.mp4`file to the `/etc/media`directory of the target device. If you are using a custom video, then ensure that you push the video to `/etc/media` and update the file path in the `config.JSON` file of the application.
6. Use the HDMI port to connect the display to the target device. For instructions, see [Set up HDMI display](https://docs.qualcomm.com/bundle/publicresource/topics/80-70029-18/samples.html).
7. Run the following command on your Ubuntu device to ensure that the `weston-autostart` is installed:

> 
> 
> sudo apt install weston-autostart
>         Copy to clipboard

    Uninstall the `weston-autostart` package after you've completed running the sample applications to restore the default desktop environment

> 
> 
> sudo apt remove weston-autostart
>         Copy to clipboard
> 
> 
> Note
> 
> 
> Sample applications with GNOME display will be enabled in a later release.
8. In the terminal of the target device, run the following command in the SSH shell to activate the display:

    - For Qualcomm Linux:

export XDG_RUNTIME_DIR=/dev/socket/weston && export WAYLAND_DISPLAY=wayland-1
            Copy to clipboard
    - For Ubuntu Server:

sudo -i
            Copy to clipboard

export XDG_RUNTIME_DIR=/run/user/$(id -u ubuntu)/ && export WAYLAND_DISPLAY=wayland-1
            Copy to clipboard

## Troubleshooting

- If you face issues with the camera or display, see [Camera troubleshooting](https://docs.qualcomm.com/bundle/publicresource/topics/80-70029-17/troubleshooting.html) and [Display troubleshooting](https://docs.qualcomm.com/bundle/publicresource/topics/80-70029-18/debug.html).
- If any model isn’t available after downloading the script file, you can download the model from [IoT–Qualcomm AI Hub](https://aihub.qualcomm.com/iot/models/) and push it to the target device:

scp <model filename> root@<IP addr of the target device>:/etc/models
        Copy to clipboard

    For example:

scp mobilenet_v2_quantized.tflite root@<IP addr of the target device>:/etc/models
        Copy to clipboard
- To run the sample applications from the UART shell, remount the file system with read/write permissions and execute the following commands on the target device:

    - For Qualcomm Linux:

mount -o remount,rw /usr
            Copy to clipboard
    - For Ubuntu Server:

mount -o remount,rw /
            Copy to clipboard
- For Ubuntu Server, copy the model files to the user `home` folder and then use `sudo` command to copy the files to the `/etc/models` directory:

scp <modelfilename> ubuntu@<IP addr of the target device>:/home/ubuntu
        ssh ubuntu@<IP addr of the target device>
        sudo cp /home/ubuntu/<model filename> /etc/models
        Copy to clipboard

Last Published: Jun 03, 2026

[Previous Topic
Run AI/ML sample applications](https://docs.qualcomm.com/bundle/publicresource/80-70029-50/topics/ai-ml-sample-applications.md) [Next Topic
Image classification](https://docs.qualcomm.com/bundle/publicresource/80-70029-50/topics/gst-ai-classification.md)