experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
snyk-fix-028eeea4de26df9a8044b86bdbb40317
STT-tensorflow/tensorflow/lite/experimental/support/metadata
History
Lu Wang f53e1aac65 Stamp the version number for all metadata components simultaneously 
PiperOrigin-RevId: 317349859
Change-Id: Ica912c3fb310889185c026e6d73ce4c69a9f0505
2020-06-19 12:01:16 -07:00
..
cc Stamp the version number for all metadata components simultaneously 2020-06-19 12:01:16 -07:00
flatbuffers_lib systemlibs: unbundle pybind11 2020-04-08 03:38:38 +08:00
java Stamp the version number for all metadata components simultaneously 2020-06-19 12:01:16 -07:00
testdata Stamp the minimum metadata parser version in MetadataPopulator. 2020-05-26 14:14:12 -07:00
BUILD Stamp the version number for all metadata components simultaneously 2020-06-19 12:01:16 -07:00
build_defs.bzl Stamp the version number for all metadata components simultaneously 2020-06-19 12:01:16 -07:00
metadata_parser_test.py Stamp the version number for all metadata components simultaneously 2020-06-19 12:01:16 -07:00
metadata_parser.py.template Stamp the version number for all metadata components simultaneously 2020-06-19 12:01:16 -07:00
metadata_schema.fbs Stamp the version number for all metadata components simultaneously 2020-06-19 12:01:16 -07:00
metadata_test.py Stamp the minimum metadata parser version in MetadataPopulator. 2020-05-26 14:14:12 -07:00
metadata.py Stamp the minimum metadata parser version in MetadataPopulator. 2020-05-26 14:14:12 -07:00
README.md Readme for TensorFlow Lite Metadata and CodeGen 2020-03-10 21:53:51 -07:00

README.md

TensorFlow Lite Metadata and Android wrapper code generator

Note: Both TensorFlow Lite Metadata and the Android wrapper code generator are in experimental (beta) phase.

TensorFlow Lite metadata provides a structured framework for storing metadata to convey information for both the developer that will utilitised the model and code generators which can create wrapper around the model. For information on how to populate model metadata, please refer to the TensorFlow Lite Metadata documentation.

The first code generator which takes advantage of this metadata format is the TensorFlow Lite Android Code Generator. For more information on how to use this generator, please refer to the TensorFlow Lite Android wrapper code generator documentation.