# Run machine learning use cases

Source: [https://docs.qualcomm.com/doc/80-70022-50/topic/machine-learning-use-cases.html](https://docs.qualcomm.com/doc/80-70022-50/topic/machine-learning-use-cases.html)

LiteRT and the Qualcomm Neural Processing SDK runtime are used for inference in the
        machine learning use cases.

Before you run the use cases, do the following:

- Complete the preconditions mentioned in [GStreamer command-line use cases](https://docs.qualcomm.com/doc/80-70022-50/topic/gstreamer-application-use-cases.html).
- [Prerequisites](https://docs.qualcomm.com/doc/80-70022-50/topic/download-model-and-label-files.html).

Important: The AI procedures in this guide are compatible
            with Qualcomm AI Runtime SDK v2.38 and LiteRT (or TFLite) v2.16.1. Ensure that you
            download the matching SDKs to your host computer before starting AI/ML
            development.

The use cases described use a MobileNet LiteRT model to classify scenes from a single
            camera stream and either overlay or compose the classification labels. 
Note: These instructions are validated on a Ubuntu 22.04 host
                computer.

1. Create the Python 3.10 virtual
                environment:

        sudo apt-get install python3.10Copy to clipboard

        python3.10 -m venv py3.10Copy to clipboard

        source py3.10/bin/activateCopy to clipboard
2. Generate the yolov5.tflite
                model:

        git clone https://github.com/ultralytics/yolov5.gitCopy to clipboard

        cd yolov5Copy to clipboard

        python -m pip install -r requirements.txt tensorflow-cpuCopy to clipboard

        python export.py --weights yolov5m.pt --img 320 --include tflite --int8 --data data/coco128.yamlCopy to clipboard
3. Push the model to the target device:
    - For Qualcomm
                        Linux:

            scp yolov5m-int8.tflite root@<IP address of the device>:/etc/models/yolov5.tfliteCopy to clipboard
    - For Ubuntu
                        Server:

            scp yolov5m-int8.tflite ubuntu@<IP address of the device>:/home/ubuntu
            ssh ubuntu@<IP address of the device>
            sudo cp /home/ubuntu/yolov5.tflite /etc/modelsCopy to clipboard

The YOLO-NAS and YOLOv5 models are trained on the same dataset. Use the same label file
            for YOLOv5.
- For Qualcomm
                    Linux:

        ssh root@<ip-addr of the target device>Copy to clipboard

        cp /etc/labels/yolox.json /etc/labels/yolov5.json Copy to clipboard
- For Ubuntu
                    Server:

        ssh ubuntu@<IP address of the device>
        sudo cp /etc/labels/yolonas.labels /etc/labels/yolov5.labelsCopy to clipboard

- **[LiteRT use cases](https://docs.qualcomm.com/doc/80-70022-50/topic/tensorflow-lite-use-cases.html)**  

LiteRT is a set of tools that allows on-device machine learning. You can  run your         models on mobile, embedded, and edge devices. LiteRT use cases allow you to run use cases         for image classification, object detection, image segmentation, and pose         estimation.
- **[Qualcomm Neural Processing SDK use cases](https://docs.qualcomm.com/doc/80-70022-50/topic/qualcomm-neural-processing-sdk-use-cases.html)**  

Qualcomm Neural Processing SDK (formerly known as Qualcomm Snapdragon Neural         Processing Engine (SNPE)) is used to run deep neural networks for inference. The use cases         describe the image classification, object detection, and image segmentation scenarios using         different ML models.

**Parent Topic:** [GStreamer command-line use cases](https://docs.qualcomm.com/doc/80-70022-50/topic/gstreamer-application-use-cases.html)

Last Published: Feb 20, 2026

[Previous Topic
GStreamer command-line use cases](https://docs.qualcomm.com/bundle/publicresource/80-70022-50/topics/gstreamer-application-use-cases.md) [Next Topic
LiteRT use cases](https://docs.qualcomm.com/bundle/publicresource/80-70022-50/topics/tensorflow-lite-use-cases.md)