python - How do i convert tensorflow 2.0 estimator model to tensorflow lite?

Question

THe following code i have below produce the regular tensorflow model but when i try to convert it to tensorflow lite it doesn't work, i followed the following documentations.

https://www.tensorflow.org/tutorials/estimator/linear 1 https://www.tensorflow.org/lite/guide/get_started

export_dir = "tmp"
serving_input_fn = tf.estimator.export.build_parsing_serving_input_receiver_fn(
  tf.feature_column.make_parse_example_spec(feat_cols))

estimator.export_saved_model(export_dir, serving_input_fn)

# Convert the model.
converter = tf.lite.TFLiteConverter.from_saved_model("tmp/1571728920/saved_model.pb")
tflite_model = converter.convert()

Error Message

Traceback (most recent call last):
  File "C:/Users/Dacorie Smith/PycharmProjects/JamaicaClassOneNotifableModels/ClassOneModels.py", line 208, in <module>
    tflite_model = converter.convert()
  File "C:\Users\Dacorie Smith\PycharmProjects\JamaicaClassOneNotifableModels\venv\lib\site-packages\tensorflow_core\lite\python\lite.py", line 400, in convert
    raise ValueError("This converter can only convert a single "
ValueError: This converter can only convert a single ConcreteFunction. Converting multiple functions is under development.

Extract from Documentation

TensorFlow Lite converter The TensorFlow Lite converter is a tool available as a Python API that converts trained TensorFlow models into the TensorFlow Lite format. It can also introduce optimizations, which are covered in section 4, Optimize your model.

The following example shows a TensorFlow SavedModel being converted into the TensorFlow Lite format:

import tensorflow as tf

converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir) tflite_model = converter.convert() open("converted_model.tflite", "wb").write(tflite_model)

Do you get any error? What is the expected behavior, and what are you getting instead? Can you also include the link or preferably the extract of the documentation that you are referring to? — Guillermo Gutiérrez
have you tried setting the saved model location like this: converter = tf.lite.TFLiteConverter.from_saved_model("tmp/1571728920") or like this: converter = tf.lite.TFLiteConverter.from_saved_model("./tmp/1571728920") — Jorge Jiménez
I add the error messages and more details to the question @GuillermoGutiérrez — DacorieS

Trayan Momkov Trayan Momkov · Accepted Answer · 2020-01-29T15:05:57

Try to use a concrete function:

export_dir = "tmp"
serving_input_fn = tf.estimator.export.build_parsing_serving_input_receiver_fn(
  tf.feature_column.make_parse_example_spec(feat_cols))

estimator.export_saved_model(export_dir, serving_input_fn)

# Convert the model.
saved_model_obj = tf.saved_model.load(export_dir="tmp/1571728920/")
concrete_func = saved_model_obj.signatures['serving_default']

converter = tf.lite.TFLiteConverter.from_concrete_functions([concrete_func])

# print(saved_model_obj.signatures.keys())
# converter.optimizations = [tf.lite.Optimize.DEFAULT]
# converter.experimental_new_converter = True

tflite_model = converter.convert()

serving_default is the default key for signatures in a SavedModels.

If not working try to uncomment converter.experimental_new_converter = True and the two lines above it.

Short explanation

Based on Concrete functions guide

Eager execution in TensorFlow 2 evaluates operations immediately, without building graphs. To save the model you need graph/s which is wrapped in a python callables: a concrete functions.

python - How do i convert tensorflow 2.0 estimator model to tensorflow lite?

1 Answers