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