Run the Image Classification Sample Application

​

Download model and label files

1. Enable Wi-Fi and SSH on the device. The device requires an internet connection to download the artifacts needed to run sample applications. If SSH and Wi-Fi are already configured, skip this step. Follow Setup an SSH connection to enable Wi-Fi and SSH on the device.
2. On the host computer, set the user environment variable:
   export USER=root
   
3. Sign in to the target device using SSH:
   ssh $USER@<IP_ADDRESS_OF_TARGET_DEVICE>
   
4. On the target device, download and run the download_artifacts.sh script to download the model and label files:
   cd /tmp
   curl -fsSL https://raw.githubusercontent.com/qualcomm/sample-apps-for-qualcomm-linux/refs/heads/main/qualcomm-linux/scripts/download_artifacts.sh | bash
   
5. (Optional) Download the YOLOv8 model, which is not included in the default download. Use one of the following methods:
   • Download with a script
   • Export with AI Hub APIs
   • Generate a batch model

   1. Create a Qualcomm AI Hub account.
   2. Go to Settings in the upper right corner and copy your API key.
   3. Run the following commands on the host computer:
      curl -L -O https://raw.githubusercontent.com/qualcomm/sample-apps-for-qualcomm-linux/refs/heads/main/qualcomm-linux/scripts/export_model.sh
      chmod +x export_model.sh
      
      Replace <API_KEY> with your API key:
      ./export_model.sh --api-key=<API_KEY>
      
      The models are downloaded to the export_assets directory.
   4. Copy the model to the /etc/models/ directory on the device:
      scp <working-directory>/export_assets/yolov8_det-tflite-w8a8/yolov8_det.tflite $USER@<IP_ADDRESS_OF_TARGET_DEVICE>:/etc/models/
      

   Use the YOLOv8-Detection-Quantized model from AI Hub.Current releases use the following SDK versions:

   • Qualcomm Linux (GA 2.0): Qualcomm AI Runtime SDK v2.47.0.260601

   For example, to export the YOLOv8 QNN model, run:

   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 2.45" --profile-options "--qairt_version 2.45"
   

   Update --qairt_version to match the version installed on your target device. To check the installed version:

   qairt-net-run --version
   

   To list the QAIRT SDK versions supported by AI Hub for the export command, run this command on the host device:

   qai-hub list-frameworks
   

   To list supported devices, run this command on the host device:

   qai-hub list-devices
   

   For example, to export the YOLOv8 LiteRT model, run:

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

   To change the batch size, update <N> in the following export command:

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

   For example, to export the YOLOv8 LiteRT model with batch size 4:

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

​

Run the sample application

1. On the host computer, set the user environment variable:
   export USER=root
   
2. Sign in to the device using SSH:
   ssh $USER@<IP_ADDRESS_OF_TARGET_DEVICE>
   
3. Run the sample application:
   gst-ai-classification --config-file=/etc/configs/config_classification.json
   
   For more information about the configuration fields or available options, use the help command:
   gst-ai-classification -h
   

​

Configure the application

{
  "file-path": "<path-to-input-video>",
  "ml-framework": "<snpe or tflite or qnn or onnx>",
  "model": "<path-to-model-file>",
  "labels": "<path-to-label-file>",
  "threshold": "<postprocessing threshold, integer value from 1 to 100>",
  "runtime": "<dsp, gpu, or cpu>",
  "output-type": "<waylandsink, filesink, or rtspsink>"
}

{
  "file-path": "/etc/media/video.mp4",
  "ml-framework": "tflite",
  "model": "/etc/models/inception_v3_quantized.tflite",
  "labels": "/etc/labels/classification.json",
  "threshold": 40,
  "runtime": "dsp"
}

​

Notes

• To stop the application, press Ctrl+C.
• To enable GStreamer debug logging, set the GST_DEBUG environment variable. For example, to log all warnings:
  export GST_DEBUG=2
  
  For more troubleshooting options, see Troubleshooting.