History

ziv-gabel 06ee9615ad Initial commit: AOSP 14 with modifications for Unplugged OS		2025-10-06 13:59:42 +00:00
..
jni	Initial commit: AOSP 14 with modifications for Unplugged OS	2025-10-06 13:59:42 +00:00
src	Initial commit: AOSP 14 with modifications for Unplugged OS	2025-10-06 13:59:42 +00:00
AndroidManifest.xml	Initial commit: AOSP 14 with modifications for Unplugged OS	2025-10-06 13:59:42 +00:00
BUILD	Initial commit: AOSP 14 with modifications for Unplugged OS	2025-10-06 13:59:42 +00:00
debug_version_script.lds	Initial commit: AOSP 14 with modifications for Unplugged OS	2025-10-06 13:59:42 +00:00
default_version_script.lds	Initial commit: AOSP 14 with modifications for Unplugged OS	2025-10-06 13:59:42 +00:00
README.md	Initial commit: AOSP 14 with modifications for Unplugged OS	2025-10-06 13:59:42 +00:00
tflite_version_script.lds	Initial commit: AOSP 14 with modifications for Unplugged OS	2025-10-06 13:59:42 +00:00

README.md

TensorFlow Lite Support

TensorFlow Lite Support contains a set of tools and libraries that help developing ML with TFLite for mobile apps. See the documentation on tensorflow.org for more information about all the efforts under TensorFlow Lite Support.

This directory contains the Java code for the TensorFlow Lite SupportLibrary and TensorFlow Lite Task Library.

TensorFlow Lite Android Support Library

Mobile application developers typically interact with typed objects such as bitmaps or primitives such as integers. However, the TensorFlow Lite Interpreter that runs the on-device machine learning model uses tensors in the form of ByteBuffer, which can be difficult to debug and manipulate. The TensorFlow Lite Android Support Library is designed to help process the input and output of TensorFlow Lite models, and make the TensorFlow Lite interpreter easier to use.

We welcome feedback from the community as we develop this support library, especially around:

Use-cases we should support including data types and operations
Ease of use - does the APIs make sense to the community

See the documentation for more instruction and examples.

TensorFlow Lite Android Task Library

TensorFlow Lite Task Library provides optimized ready-to-use model interfaces for popular machine learning tasks, such as image classification, question and answer, etc. The model interfaces are specifically designed for each task to achieve the best performance and usability. Task Library works cross-platform and is supported on Java, C++, and Swift.

See the documentation for more instruction and examples.