• Home
Name Date Size #Lines LOC

..--

g3doc/06-Sep-2024-42

graph_transformations/06-Sep-2024-20,10614,169

logging/06-Sep-2024-1,5011,156

python/06-Sep-2024-866655

runtime/06-Sep-2024-6121

tensorflow_graph_matching/06-Sep-2024-1,119736

tflite/06-Sep-2024-6,8135,464

BUILDD06-Sep-202416.3 KiB506482

README.mdD06-Sep-20241.3 KiB3022

allocate_transient_arrays.ccD06-Sep-202413 KiB353256

allocate_transient_arrays.hD06-Sep-20241.9 KiB4513

args.ccD06-Sep-20246.1 KiB175119

args.hD06-Sep-20247.5 KiB205130

dump_graphviz.ccD06-Sep-202426.3 KiB788585

dump_graphviz.hD06-Sep-20241 KiB309

export_tensorflow.ccD06-Sep-2024108.9 KiB2,5642,306

export_tensorflow.hD06-Sep-20241.1 KiB3110

format_port.hD06-Sep-20242.7 KiB7435

import_tensorflow.ccD06-Sep-2024110.4 KiB2,8112,344

import_tensorflow.hD06-Sep-20241.9 KiB5120

import_tensorflow_test.ccD06-Sep-202425.4 KiB756593

model.hD06-Sep-202477.3 KiB2,4921,064

model_cmdline_flags.ccD06-Sep-202420.4 KiB467419

model_cmdline_flags.hD06-Sep-20241.7 KiB4418

model_cmdline_flags_test.ccD06-Sep-20242.3 KiB6743

model_flags.protoD06-Sep-20249 KiB226198

tensorflow_util.ccD06-Sep-20247.6 KiB202181

tensorflow_util.hD06-Sep-20241.1 KiB3312

toco.ccD06-Sep-20242.2 KiB5936

toco_cmdline_flags.ccD06-Sep-202418.8 KiB365317

toco_cmdline_flags.hD06-Sep-20241.6 KiB3815

toco_cmdline_flags_test.ccD06-Sep-20241.9 KiB6132

toco_convert.ccD06-Sep-20244.7 KiB11276

toco_convert.hD06-Sep-20241.5 KiB3817

toco_convert_test.ccD06-Sep-20245.2 KiB190141

toco_flags.protoD06-Sep-202413.7 KiB304255

toco_graphviz_dump_options.ccD06-Sep-2024887 237

toco_graphviz_dump_options.hD06-Sep-20241.1 KiB3311

toco_port.ccD06-Sep-20247.8 KiB279209

toco_port.hD06-Sep-20243.8 KiB12082

toco_port_test.ccD06-Sep-20242 KiB6742

toco_tooling.ccD06-Sep-202421.4 KiB515391

toco_tooling.hD06-Sep-20242.3 KiB6029

toco_types.hD06-Sep-20241.1 KiB3817

tooling_util.ccD06-Sep-202488.5 KiB2,4812,159

tooling_util.hD06-Sep-202415.3 KiB371202

tooling_util_test.ccD06-Sep-20247.5 KiB215152

types.protoD06-Sep-20241.6 KiB8360

README.md

1# TensorFlow Lite Converter
2
3The TensorFlow Lite Converter converts TensorFlow graphs into
4TensorFlow Lite graphs. There are additional usages that are also detailed in
5the usage documentation.
6
7## Usage documentation
8
9Usage information is given in these documents:
10
11*   [Command-line glossary](../g3doc/r1/convert/cmdline_reference.md)
12*   [Command-line examples](../g3doc/r1/convert/cmdline_examples.md)
13*   [Python API examples](../g3doc/r1/convert/python_api.md)
14
15## Where the converter fits in the TensorFlow landscape
16
17Once an application developer has a trained TensorFlow model, the TensorFlow
18Lite Converter will accept
19that model and generate a TensorFlow Lite
20[FlatBuffer](https://google.github.io/flatbuffers/) file. The converter currently supports
21[SavedModels](https://www.tensorflow.org/guide/saved_model#using_savedmodel_with_estimators),
22frozen graphs (models generated via
23[freeze_graph.py](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/tools/freeze_graph.py)),
24and `tf.Keras` model files.  The TensorFlow Lite FlatBuffer file can be shipped
25to client devices, generally mobile devices, where the TensorFlow Lite
26interpreter handles them on-device.  This flow is represented in the diagram
27below.
28
29![drawing](../g3doc/r1/images/convert/workflow.svg)
30