experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
nightly
STT-tensorflow/tensorflow/lite/toco
History
Yanhua Sun 1a61eebcc7 Replace direct TF app import with absl::app. 
(1) TF::app is deprecated
(2) direct TF import is discouraged.

PiperOrigin-RevId: 360918794
Change-Id: Ib750eab99f75a030eb1fff22b44b75b9a75ad7e1
2021-03-04 08:17:07 -08:00
..
g3doc
graph_transformations Pre-allocate memory for vectors where size is known. 2021-02-10 20:07:07 -08:00
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 Replace direct TF app import with absl::app. 2021-03-04 08:17:07 -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 hash table ops to Flex 2021-03-04 01:20:27 -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
BUILD Update TFLite types.proto to use separate quantized and unquantized types. 2021-02-24 18:51:44 -08:00
dump_graphviz.cc
dump_graphviz.h
export_tensorflow.cc Add nominal support for unsigned 32-bit integer tensor types. 2021-02-17 14:16:29 -08:00
export_tensorflow.h Qualify uses of std::string 2020-06-17 09:54:59 -07:00
format_port.h
import_tensorflow_test.cc Add nominal support for unsigned 32-bit integer tensor types. 2021-02-17 14:16:29 -08:00
import_tensorflow.cc Add nominal support for unsigned 32-bit integer tensor types. 2021-02-17 14:16:29 -08:00
import_tensorflow.h
model_cmdline_flags_test.cc
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
tensorflow_util.h
toco_cmdline_flags_test.cc
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
toco_convert_test.cc
toco_convert.cc
toco_convert.h
toco_flags.proto [lite] Deprecate _custom_opdefs field in TfLiteConverter. 2021-02-18 15:11:55 -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
toco_tooling.cc
toco_tooling.h
toco_types.h Qualify uses of std::string 2020-07-08 09:56:58 -07:00
toco.cc
tooling_util_test.cc
tooling_util.cc Update TFLite types.proto to use separate quantized and unquantized types. 2021-02-24 18:51:44 -08:00
tooling_util.h Removed unused protobuf dependency 2021-01-22 10:46:21 -08:00
types.proto Update TFLite types.proto to use separate quantized and unquantized types. 2021-02-24 18:51:44 -08:00

README.md

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