History

Xunkai Zhang 6642441bee [tfls.codegen] Update Image Classifier generation to new API. PiperOrigin-RevId: 316031289 Change-Id: I918dc5563f80e3bd163dec77b72374242484e936		2020-06-11 20:20:19 -07:00
..
python
android_java_generator.cc	[tfls.codegen] Update Image Classifier generation to new API.	2020-06-11 20:20:19 -07:00
android_java_generator.h	[tfls.codegen] Update Image Classifier generation to new API.	2020-06-11 20:20:19 -07:00
BUILD
code_generator_test.cc
code_generator.cc	This CL optimizes C++11 range-based for loops where the variable is copied in each iteration but it would suffice to obtain it by const reference. This is only applied to loop variables of types that are expensive to copy which means they are not trivially copyable or have a non-trivial copy constructor or destructor.	2020-04-07 14:38:02 -07:00
code_generator.h
metadata_helper.cc	[tfls.codegen] Fix potential nullptr seg fault.	2020-04-14 17:13:31 -07:00
metadata_helper.h
README.md
utils_test.cc
utils.cc	[tfls.codegen] Update Image Classifier generation to new API.	2020-06-11 20:20:19 -07:00
utils.h

README.md

TensorFlow Lite Android Wrapper Code Generator

For TensorFlow Lite model enhanced with metadata, developers can use the TensorFlow Lite Android wrapper code generator to create platform specific wrapper code. The wrapper code removes the need to interact directly with ByteBuffer. Instead, developers can interact with the TensorFlow Lite model with typed objects such as Bitmap and Rect.

The usefulness of the code generator depend on the completeness of the TensorFlow Lite model's metadata entry. Refer to the <Codegen usage> section under relevant fields in metadata_schema.fbs, to see how the codegen tool parses each field.