A. Unique TensorFlower 7e59a2ab28 Qualify uses of std::string
PiperOrigin-RevId: 317683481
Change-Id: I3f6bb93d67e18623bf5d049ae0cc03bd2f937e5f
2020-06-22 11:45:26 -07:00
..
2020-06-17 18:02:32 -07:00
2020-06-17 10:25:14 -07:00
2020-06-19 09:21:51 -07:00
2020-06-17 09:54:59 -07:00
2020-06-17 09:54:59 -07:00
2020-06-17 09:54:59 -07:00
2020-06-17 09:54:59 -07:00
2020-06-17 09:54:59 -07:00
2020-01-24 07:44:13 +01:00
2020-06-17 09:54:59 -07:00
2020-06-17 09:54:59 -07:00
2020-06-17 09:54:59 -07:00
2020-06-17 09:54:59 -07:00
2020-06-17 09:54:59 -07:00
2020-06-17 09:54:59 -07:00
2020-06-17 09:54:59 -07:00
2020-06-17 09:54:59 -07:00
2020-06-17 09:54:59 -07:00
2020-06-17 09:54:59 -07:00
2020-06-17 09:54:59 -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