saved_model_to_tflite.py

saved_model_to_tflite.py

graph_def_file = “model_name.pb”
input_arrays = [“input_tensor_name”] # this array can have more than one input name if the model requires multiple inputs
output_arrays = [“output_tensor_name”] # this array can have more than one input name if the model has multiple outputs


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)