TFLite Support is a toolkit that helps users to develop ML and deploy TFLite models onto mobile devices.
Project description
- TFLite Support is a toolkit that helps users to develop ML and deploy TFLite models onto mobile devices. It consists of the following major components:
TFLite Support Util Library: a cross-platform library that helps to deploy TFLite models onto mobile devices.
TFLite Model Metadata: includes both human and machine readable information about what a model does and how to use the model.
TFLite Support Codegen: an executable that generates model interface automatically based on the TFLite Metadata and the Support Util Library. The model interface comes with high level APIs to interact with the model, such as loading and processing data, running inference, etc.
- This PyPI package includes the Python bindings for following features:
Metadata populator and displayer: can be used to populate the metadata and associated files into the model, as well as converting the populated metadata into the json format.
Android Codegen tool: generates the Java model interface used in Android for a particular model.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.