# Sample applications

Source: [https://docs.qualcomm.com/doc/80-70014-54/topic/sample-applications.html](https://docs.qualcomm.com/doc/80-70014-54/topic/sample-applications.html)

The TensorFlow Lite framework provides sample applications that you can use to execute an
            arbitrary TensorFlow Lite model and perform benchmarking.

- **Download models and sample images**  

The samples in Getting started use the label\_image sample         application provided by the TensorFlow Lite framework, which can run any classification         models (for example, MobileNet v1, v2).
- **Run a TensorFlow Lite model using an available delegate**  

The TensorFlow Lite open-source framework provides the Label Image tool to execute a         TensorFlow Lite model using an available delegate. The source code for the Label Image tool         is available on the [TensorFlow GitHub repository](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/examples/label_image).
- **Run QNN delegate using the external delegate interface**  

The QNN delegate relies on the Qualcomm AI Engine Direct API and its backends to         speed up models on the Adreno GPU and Hexagon Tensor Processor.

Last Published: Jul 12, 2024

Previous Topic
 
Develop a custom application to run the TensorFlow Lite model Next Topic

Download models and sample images