1# TensorFlow Lite Support
2
3TensorFlow Lite Support contains a set of tools and libraries that help
4developing ML with TFLite for mobile apps. See the [documentation on
5tensorflow.org](https://www.tensorflow.org/lite/inference_with_metadata/overview)
6for more information about all the efforts under TensorFlow Lite Support.
7
8This directory contains the Java code for the TensorFlow Lite SupportLibrary
9and TensorFlow Lite Task Library.
10
11## TensorFlow Lite Android Support Library
12
13Mobile application developers typically interact with typed objects such as
14bitmaps or primitives such as integers. However, the TensorFlow Lite Interpreter
15that runs the on-device machine learning model uses tensors in the form of
16ByteBuffer, which can be difficult to debug and manipulate. The TensorFlow Lite
17Android Support Library is designed to help process the input and output of
18TensorFlow Lite models, and make the TensorFlow Lite interpreter easier to use.
19
20We welcome feedback from the community as we develop this support library,
21especially around:
22
23*   Use-cases we should support including data types and operations
24*   Ease of use - does the APIs make sense to the community
25
26See the [documentation](https://www.tensorflow.org/lite/inference_with_metadata/lite_support)
27for more instruction and examples.
28
29
30## TensorFlow Lite Android Task Library
31TensorFlow Lite Task Library provides optimized ready-to-use model interfaces
32for popular machine learning tasks, such as image classification, question and
33answer, etc. The model interfaces are specifically designed for each task to
34achieve the best performance and usability. Task Library works cross-platform
35and is supported on Java, C++, and Swift.
36
37See the [documentation](https://www.tensorflow.org/lite/inference_with_metadata/task_library/overview)
38for more instruction and examples.
39