Difference between revisions of "Converting to TensorFlow Lite"
| Line 13: | Line 13: | ||
== TensorFlow Lite converter: lite.TFLiteConverter == | == TensorFlow Lite converter: lite.TFLiteConverter == | ||
| − | * [http://www.tensorflow.org/lite/ | + | * [http://www.tensorflow.org/api_docs/python/tf/lite/TFLiteConverter lite.TFLiteConverter | TensorFlow] |
| − | The TensorFlow Lite converter is used to convert TensorFlow models into an optimized FlatBuffer format, so that they can be used by the TensorFlow Lite interpreter. | + | The TensorFlow Lite converter is used to convert TensorFlow models; GraphDef or SavedModel into an optimized FlatBuffer format, so that they can be used by the TensorFlow Lite interpreter or graph visualization. |
| + | |||
| + | # Converting a GraphDef from session. | ||
| + | converter = lite.TFLiteConverter.from_session(sess, in_tensors, out_tensors) | ||
| + | tflite_model = converter.convert() | ||
| + | open("converted_model.tflite", "wb").write(tflite_model) | ||
| + | |||
| + | # Converting a GraphDef from file. | ||
| + | converter = lite.TFLiteConverter.from_frozen_graph( | ||
| + | graph_def_file, input_arrays, output_arrays) | ||
| + | tflite_model = converter.convert() | ||
| + | open("converted_model.tflite", "wb").write(tflite_model) | ||
| + | |||
| + | # Converting a SavedModel. | ||
| + | converter = lite.TFLiteConverter.from_saved_model(saved_model_dir) | ||
| + | tflite_model = converter.convert() | ||
| + | |||
| + | # Converting a tf.keras model. | ||
| + | converter = lite.TFLiteConverter.from_keras_model_file(keras_model) | ||
| + | tflite_model = converter.convert() | ||
<youtube>ICY4Lvhyobk</youtube> | <youtube>ICY4Lvhyobk</youtube> | ||
Revision as of 03:45, 27 June 2019
Youtube search... ...Google search
TensorFlow Lite converter: lite.TFLiteConverter
The TensorFlow Lite converter is used to convert TensorFlow models; GraphDef or SavedModel into an optimized FlatBuffer format, so that they can be used by the TensorFlow Lite interpreter or graph visualization.
- Converting a GraphDef from session.
converter = lite.TFLiteConverter.from_session(sess, in_tensors, out_tensors) tflite_model = converter.convert() open("converted_model.tflite", "wb").write(tflite_model)
- Converting a GraphDef from file.
converter = lite.TFLiteConverter.from_frozen_graph(
graph_def_file, input_arrays, output_arrays)
tflite_model = converter.convert() open("converted_model.tflite", "wb").write(tflite_model)
- Converting a SavedModel.
converter = lite.TFLiteConverter.from_saved_model(saved_model_dir) tflite_model = converter.convert()
- Converting a tf.keras model.
converter = lite.TFLiteConverter.from_keras_model_file(keras_model) tflite_model = converter.convert()
TocoConverter (THIS FUNCTION IS DEPRECATED)
