STT-tensorflow/tensorflow/lite/toco
Jaesung Chung 62feaa576a Update the remaining unchanged spots, which read builtin code
PiperOrigin-RevId: 338183423
Change-Id: Ib208da7e61475165b58dbac3771c9c330ca6f101
2020-10-20 19:30:01 -07:00
..
g3doc
graph_transformations resolutions 2020-07-27 00:08:05 +00:00
logging Remove references to tf_proto_library in TF. 2020-09-23 15:42:34 -07:00
python tflite_convert: register custom op defs at the beginning of process 2020-10-05 14:54:04 -07:00
runtime
tensorflow_graph_matching Qualify uses of std::string 2020-06-16 17:31:31 -07:00
tflite Update the remaining unchanged spots, which read builtin code 2020-10-20 19:30:01 -07:00
allocate_transient_arrays.cc Qualify uses of std::string 2020-06-17 09:54:59 -07:00
allocate_transient_arrays.h
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 Remove references to tf_proto_library in TF. 2020-09-23 15:42:34 -07:00
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
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
toco_graphviz_dump_options.cc
toco_graphviz_dump_options.h
toco_port_test.cc
toco_port.cc Qualify uses of std::string 2020-06-17 09:54:59 -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 Add complex<double> tensor support in TFLite 2020-07-13 18:19:24 -07:00
tooling_util.h Qualify uses of std::string 2020-06-17 09:54:59 -07:00
types.proto Add complex<double> tensor support in TFLite 2020-07-13 18:19:24 -07:00

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