STT-tensorflow/tensorflow/lite/toco
Karim Nosir 96b0f783fe [lite] Add field in toco flags to control enabling tflite variables.
PiperOrigin-RevId: 356001474
Change-Id: Ia109c884aa286e2dc757cad38dc5703daf4fd186
2021-02-06 00:57:19 -08:00
..
g3doc
graph_transformations resolutions 2020-07-27 00:08:05 +00:00
logging Comment out a number of google-internal targets when copybara-exporting instead of removing them. 2021-01-26 05:47:31 -08:00
python PY2 removal cleanup 2021-01-20 17:11:44 -08:00
runtime
tensorflow_graph_matching Optimize calls to std::string::find() and friends for a single char. 2020-12-17 18:11:13 -08:00
tflite Add uint64 tensor support in TFLite 2020-11-17 14:01:21 -08:00
allocate_transient_arrays.cc Qualify uses of std::string 2020-06-17 09:54:59 -07:00
allocate_transient_arrays.h Migrate TensorFlow Lite out of tensorflow/contrib 2018-10-31 14:20:28 -07:00
args.cc Migrating deprecated aliases for absl::StrSplit, and the corresponding predicates 2020-06-22 10:28:15 -07:00
args.h Qualify uses of std::string 2020-06-17 09:54:59 -07:00
BUILD Comment out a number of google-internal targets when copybara-exporting instead of removing them. 2021-01-26 05:47:31 -08:00
dump_graphviz.cc Qualify uses of std::string 2020-06-17 09:54:59 -07:00
dump_graphviz.h Qualify uses of std::string 2020-06-17 09:54:59 -07:00
export_tensorflow.cc Qualify uses of std::string 2020-06-17 09:54:59 -07:00
export_tensorflow.h Qualify uses of std::string 2020-06-17 09:54:59 -07:00
format_port.h Qualify uses of std::string 2020-06-17 09:54:59 -07:00
import_tensorflow_test.cc Qualify uses of std::string 2020-06-17 09:54:59 -07:00
import_tensorflow.cc Qualify uses of std::string 2020-06-17 09:54:59 -07:00
import_tensorflow.h Qualify uses of std::string 2020-06-17 09:54:59 -07:00
model_cmdline_flags_test.cc Qualify uses of std::string 2020-06-17 09:54:59 -07:00
model_cmdline_flags.cc Merge pull request from tg-at-google:sign-compare-warning-fixes-batch-1-fix2 2020-06-26 11:35:48 -07:00
model_cmdline_flags.h Qualify uses of std::string 2020-06-17 09:54:59 -07:00
model_flags.proto Propagate unknown rank of tensor shape information to MLIR 2020-11-17 00:38:39 -08:00
model.h Rollback of BroadcastTo op additions (part 3) 2020-07-23 16:38:48 -07:00
README.md
tensorflow_util.cc Qualify uses of std::string 2020-06-17 09:54:59 -07:00
tensorflow_util.h Qualify uses of std::string 2020-06-17 09:54:59 -07:00
toco_cmdline_flags_test.cc Qualify uses of std::string 2020-06-17 09:54:59 -07:00
toco_cmdline_flags.cc Merge branch 'master' into sign-compare-warning-fixes-batch-1-fix2 2020-06-24 15:08:13 -04:00
toco_cmdline_flags.h Qualify uses of std::string 2020-06-17 09:54:59 -07:00
toco_convert_test.cc Qualify uses of std::string 2020-06-17 09:54:59 -07:00
toco_convert.cc Qualify uses of std::string 2020-06-17 09:54:59 -07:00
toco_convert.h Qualify uses of std::string 2020-06-17 09:54:59 -07:00
toco_flags.proto [lite] Add field in toco flags to control enabling tflite variables. 2021-02-06 00:57:19 -08:00
toco_graphviz_dump_options.cc
toco_graphviz_dump_options.h
toco_port_test.cc
toco_port.cc Internal naming change 2020-10-23 09:50:59 -07:00
toco_port.h Qualify uses of std::string 2020-06-17 09:54:59 -07:00
toco_tooling.cc Qualify uses of std::string 2020-06-17 09:54:59 -07:00
toco_tooling.h Qualify uses of std::string 2020-06-17 09:54:59 -07:00
toco_types.h Qualify uses of std::string 2020-07-08 09:56:58 -07:00
toco.cc Qualify uses of std::string 2020-06-17 09:54:59 -07:00
tooling_util_test.cc
tooling_util.cc Resource & variant type additions to TFLite schema 2021-01-29 17:12:52 -08:00
tooling_util.h Removed unused protobuf dependency 2021-01-22 10:46:21 -08:00
types.proto Resource & variant type additions to TFLite schema 2021-01-29 17:12:52 -08:00

TensorFlow Lite Converter

The TensorFlow Lite Converter converts TensorFlow graphs into TensorFlow Lite graphs. There are additional usages that are also detailed in the usage documentation.

Usage documentation

Usage information is given in these documents:

Where the converter fits in the TensorFlow landscape

Once an application developer has a trained TensorFlow model, the TensorFlow Lite Converter will accept that model and generate a TensorFlow Lite FlatBuffer file. The converter currently supports SavedModels, frozen graphs (models generated via freeze_graph.py), and tf.Keras model files. The TensorFlow Lite FlatBuffer file can be shipped to client devices, generally mobile devices, where the TensorFlow Lite interpreter handles them on-device. This flow is represented in the diagram below.

drawing