Machine Learning with Android 11: What's new

You would not directly use the model for your edge device. You would need to compress it or optimize the model so you can run it on the edge device as it has limited computation power, network availability, and disk space. In this document, however, we will not be discussing about the optimization process. We will be deploying a .tflite You can read more about TensorFlow Lite and the Model Optimization process with TensorFlow Lite.