• Home
  • History
  • Annotate
  • only in /external/tensorflow/tensorflow/contrib/lite/toco/
NameDateSize

..10-Aug-20184 KiB

allocate_transient_arrays.cc10-Aug-201811.7 KiB

allocate_transient_arrays.h10-Aug-20181.9 KiB

args.h10-Aug-20188.1 KiB

BUILD10-Aug-201811.5 KiB

dump_graphviz.cc10-Aug-201813.8 KiB

dump_graphviz.h10-Aug-20181,013

export_tensorflow.cc10-Aug-201878.5 KiB

export_tensorflow.h10-Aug-20181.1 KiB

format_port.h10-Aug-20182.9 KiB

g3doc/10-Aug-20184 KiB

graph_transformations/10-Aug-20184 KiB

import_tensorflow.cc10-Aug-201878.5 KiB

import_tensorflow.h10-Aug-20181.6 KiB

model.h10-Aug-201853.8 KiB

model_cmdline_flags.cc10-Aug-201818.2 KiB

model_cmdline_flags.h10-Aug-20181.7 KiB

model_flags.proto10-Aug-20187.3 KiB

python/10-Aug-20184 KiB

README.md10-Aug-20181 KiB

runtime/10-Aug-20184 KiB

tensorflow_graph_matching/10-Aug-20184 KiB

tensorflow_util.cc10-Aug-20187.6 KiB

tensorflow_util.h10-Aug-20181.2 KiB

tflite/10-Aug-20184 KiB

toco.cc10-Aug-20184.7 KiB

toco_cmdline_flags.cc10-Aug-201810.8 KiB

toco_cmdline_flags.h10-Aug-20181.6 KiB

toco_flags.proto10-Aug-20186.3 KiB

toco_graphviz_dump_options.cc10-Aug-2018895

toco_graphviz_dump_options.h10-Aug-20181.2 KiB

toco_port.cc10-Aug-20185.9 KiB

toco_port.h10-Aug-20183.1 KiB

toco_port_test.cc10-Aug-20181.8 KiB

toco_tooling.cc10-Aug-201812.6 KiB

toco_tooling.h10-Aug-20181.9 KiB

toco_types.h10-Aug-20181.4 KiB

tooling_util.cc10-Aug-201864.5 KiB

tooling_util.h10-Aug-201813 KiB

tooling_util_test.cc10-Aug-20183.7 KiB

types.proto10-Aug-20181,003

README.md

1# The TensorFlow Lite Optimizing Converter
2
3The TensorFlow Lite Optimizing Converter's most typical use is converting from the TensorFlow GraphDef to the TensorFlow Lite
4format, but it supports much more than that.
5
6## Usage documentation
7
8Usage information is given in these documents:
9
10*   [Command-line examples](g3doc/cmdline_examples.md)
11*   [Command-line reference](g3doc/cmdline_reference.md)
12*   [Python API](g3doc/python_api.md)
13
14## Design documentation
15
16Coming soon!
17
18## Where the converter fits in the TensorFlow landscape
19
20In the typical case, an application developer is using TensorFlow to design and
21train models, then uses TensorFlow's freeze_graph.py to generate a frozen
22inference graph, then uses the converter to convert that into a TensorFlow Lite flatbuffer file,
23then ships that file to client devices where the TensorFlow Lite interpreter handles them
24on-device. This is represented in the following diagram:
25
26![drawing](https://storage.googleapis.com/download.tensorflow.org/example_images/tensorflow_landscape.svg)
27