Page-1

# Run inference Source: [https://docs.qualcomm.com/doc/80-70014-54/topic/run-inference.html](https://docs.qualcomm.com/doc/80-70014-54/topic/run-inference.html) You can use the TensorFlow Lite C++ APIs to create an application, load a TensorFlow Lite model, and execute the model on hardware using delegates. A typical application created using C++ APIs to run a TensorFlow Lite model involves the following steps: Figure : Workflow to create an application and run a TensorFlow Lite model - **[Load a TensorFlow Lite model](https://docs.qualcomm.com/doc/80-70014-54/topic/load-a-tensorflow-lite-model.html)** A TensorFlow Lite model is a FlatBuffers file that contains information on model operators and any associated weights and biases. - **[Create a TensorFlow Lite interpreter](https://docs.qualcomm.com/doc/80-70014-54/topic/create-a-tensorflow-lite-interpreter.html)** Using the TensorFlow C/C++ APIs, you can build an interpreter to run the model. - **[Prepare a model with a chosen delegate](https://docs.qualcomm.com/doc/80-70014-54/topic/prepare-a-model-with-a-chosen-delegate.html)** After creating an interpreter and allocating the necessary memory to run the model, prepare the model with a chosen delegate. This step creates an execution graph from the model loaded before and uses the underlying library to perform inference on the delegate hardware. - **[Prepare input/output buffers](https://docs.qualcomm.com/doc/80-70014-54/topic/prepare-input-output-buffers.html)** When building a standalone TensorFlow Lite application, the pipeline to execute TensorFlow Lite models requires preparing input data, for example, camera frames. - **[Run a model](https://docs.qualcomm.com/doc/80-70014-54/topic/execute-a-model.html)** To run inference, invoke a delegate using the `Invoke()` API. Before invoking this API, create the appropriate input and output buffers and provide them to the interpreter. **Parent Topic:** [TensorFlow Lite developer workflow](https://docs.qualcomm.com/doc/80-70014-54/topic/tensorflow-lite-developer-workflow.html) Last Published: Jul 12, 2024 [Previous Topic Convert using offline converter tool (CLI)](https://docs.qualcomm.com/bundle/publicresource/80-70014-54/topics/convert-using-offline-converter-tool-cli.md) [Next Topic Load a TensorFlow Lite model](https://docs.qualcomm.com/bundle/publicresource/80-70014-54/topics/load-a-tensorflow-lite-model.md)