Difference between revisions of "Converting to TensorFlow Lite"
| Line 16: | Line 16: | ||
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. | 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. | + | # Converting a GraphDef from session. |
| − | converter = lite.TFLiteConverter.from_session(sess, in_tensors, out_tensors) | + | converter = lite.TFLiteConverter.from_session(sess, in_tensors, out_tensors) |
| − | tflite_model = converter.convert() | + | tflite_model = converter.convert() |
| − | open("converted_model.tflite", "wb").write(tflite_model) | + | open("converted_model.tflite", "wb").write(tflite_model) |
| − | # Converting a GraphDef from file. | + | # Converting a GraphDef from file. |
| − | converter = lite.TFLiteConverter.from_frozen_graph( | + | converter = lite.TFLiteConverter.from_frozen_graph( |
graph_def_file, input_arrays, output_arrays) | graph_def_file, input_arrays, output_arrays) | ||
| − | tflite_model = converter.convert() | + | tflite_model = converter.convert() |
| − | open("converted_model.tflite", "wb").write(tflite_model) | + | open("converted_model.tflite", "wb").write(tflite_model) |
| − | # Converting a SavedModel. | + | # Converting a SavedModel. |
| − | converter = lite.TFLiteConverter.from_saved_model(saved_model_dir) | + | converter = lite.TFLiteConverter.from_saved_model(saved_model_dir) |
| − | tflite_model = converter.convert() | + | tflite_model = converter.convert() |
| − | # Converting a tf.keras model. | + | # Converting a tf.keras model. |
| − | converter = lite.TFLiteConverter.from_keras_model_file(keras_model) | + | converter = lite.TFLiteConverter.from_keras_model_file(keras_model) |
| − | tflite_model = converter.convert() | + | tflite_model = converter.convert() |
<youtube>ICY4Lvhyobk</youtube> | <youtube>ICY4Lvhyobk</youtube> | ||
Revision as of 03:48, 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)
