> ## Documentation Index
> Fetch the complete documentation index at: https://dragonwingdocs.qualcomm.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Run a Sample Application with a custom-trained model

> Integrate custom model with sample application.

This guide explains how to modify an existing Qualcomm IM SDK reference application to work with a custom-trained model. It uses a custom-trained YOLOv8 model as an example.

## Use a custom-trained YOLOv8 LiteRT model

Qualcomm IM SDK reference applications use the YOLOv8 model for object detection. This example explains how to run a custom-trained YOLOv8 variant with the current reference application.

To run your own custom-trained YOLOv8 model, complete the following steps:

1. Replace the existing model with your new model in the reference application.
2. Update the label files with your custom labels.
3. Run the reference application with the updated model.

### Update the label files

The Qualcomm IM SDK reference applications expect labels in JSON format. Update the `id`, `color`, and `label` values for each entry in the labels file yolov8\_custom.json.

The format for each label entry is:

```json theme={null}
[
  {"id": 0, "color": "0x00FF00FF", "label": "person"}
]
```

For example:

```json theme={null}
[
  {"id": 0, "color": "0x00FF00FF", "label": "person"},
  {"id": 1, "color": "0x00FF00FF", "label": "bicycle"},
  {"id": 2, "color": "0x0000FFFF", "label": "car"},
  {"id": 3, "color": "0x00FF00FF", "label": "motorcycle"}
]
```

### Run object detection with the custom model

To run object detection using the LiteRT runtime with your custom model and label files, complete the following steps:

<Steps>
  <Step title="Set the user environment variable on the host computer">
    ```shell theme={null}
    export USER=ubuntu
    ```
  </Step>

  <Step title="Copy the model to the device">
    ```shell theme={null}
    scp yolov8_custom.tflite $USER@<IP_ADDRESS_OF_TARGET_DEVICE>:/home/ubuntu/
    ssh $USER@<IP_ADDRESS_OF_TARGET_DEVICE>
    cp /home/ubuntu/yolov8_custom.tflite /etc/models/ 
    exit
    ```
  </Step>

  <Step title="Copy the label file to the device">
    ```shell theme={null}
    scp yolov8_custom.json $USER@<IP_ADDRESS_OF_TARGET_DEVICE>:/home/ubuntu/
    ssh $USER@<IP_ADDRESS_OF_TARGET_DEVICE>
    cp /home/ubuntu/yolov8_custom.json /etc/labels/
    exit
    ```
  </Step>

  <Step title="Sign in to the device using SSH">
    ```shell theme={null}
    ssh $USER@<IP_ADDRESS_OF_TARGET_DEVICE>
    ```
  </Step>

  <Step title="Edit the config_detection.json configuration file">
    ```json theme={null}
    {
      "file-path": "/etc/media/video.mp4",
      "ml-framework": "tflite",
      "yolo-model-type": "yolov8",
      "model": "/etc/models/yolov8_custom.tflite",
      "labels": "/etc/labels/yolov8_custom.json",
      "threshold": 40,
      "runtime": "dsp"
    }
    ```
  </Step>

  <Step title="Run the sample application">
    ```shell theme={null}
    gst-ai-object-detection --config-file=/etc/configs/config_detection.json
    ```
  </Step>
</Steps>

## Notes

* To display all available options, run:

  ```shell theme={null}
  gst-ai-object-detection -h
  ```

* To stop the application, press `Ctrl+C`.