Issue with tf.ParseExampleV2 when converting to Tensorflow Lite : "op is neither a custom op nor a flex op"

Question

excuse my english.

I've been trying to handle Estimators API of tensorflow (v2.x), but when i'm trying to convert a model from tf.estimators to tflite with this code :

import tensorflow as tf

import numpy as np

feature_name = "features"
feature_columns = [tf.feature_column.numeric_column(feature_name, shape=[2])]

classifier = tf.estimator.LinearClassifier(
    feature_columns=feature_columns,
    n_classes=2,
    model_dir="Z:\\tests\\iris")

feature_spec = {'features': tf.io.FixedLenFeature(shape=[2], dtype=np.float32)}
serving_fn = tf.estimator.export.build_parsing_serving_input_receiver_fn(feature_spec)
classifier.export_saved_model(export_dir_base='Z:\\tests\\iris\\', serving_input_receiver_fn=serving_fn)

saved_model_obj = tf.saved_model.load("Z:\\tests\\iris\\1613055608")
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()

with open('Z:\\tests\\model.tflite_estimators', 'wb') as f:
    f.write(tflite_model)

I got the following error :

ConverterError: C:\Users\\.....\tensorflow\python\saved_model\load.py:909:0: error: 'tf.ParseExampleV2' op is neither a custom op nor a flex op
C:\Users\\.....\tensorflow\python\saved_model\load.py:859:0: note: called from
P:\\.....\sanstitre3.py:19:0: note: called from
C:\Users\\.....\AppData\Local\Continuum\anaconda3\lib\site-packages\spyder_kernels\customize\spydercustomize.py:465:0: note: called from
C:\Users\\.....\AppData\Local\Continuum\anaconda3\lib\site-packages\spyder_kernels\customize\spydercustomize.py:578:0: note: called from
<ipython-input-115-f30bf3b642d5>:1:0: note: called from
C:\Users\\.....\AppData\Local\Continuum\anaconda3\lib\site-packages\IPython\core\interactiveshell.py:3343:0: note: called from
C:\Users\\.....\AppData\Local\Continuum\anaconda3\lib\site-packages\IPython\core\interactiveshell.py:3263:0: note: called from
C:\Users\\.....\AppData\Local\Continuum\anaconda3\lib\site-packages\IPython\core\interactiveshell.py:3072:0: note: called from
C:\Users\\.....\AppData\Local\Continuum\anaconda3\lib\site-packages\IPython\core\async_helpers.py:68:0: note: called from
<unknown>:0: error: failed while converting: 'main': Ops that can be supported by the flex runtime (enabled via setting the -emit-select-tf-ops flag):
    tf.ParseExampleV2 {dense_shapes = [#tf.shape<2>], device = "", num_sparse = 0 : i64, result_segment_sizes = dense<[0, 0, 0, 1, 0, 0]> : vector<6xi32>}

Some guy on the internet already proposed to add those 2 lines under converter.experimental_new_converter = True :

converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS,
                                      tf.lite.OpsSet.SELECT_TF_OPS]

It compiles without errors, just warnings, but when i put the TFLite model on my STM32, it gaves me the error TOOL ERROR/ Unknown layer type FlexParseExampleV2, stopping.

Can someone help me on this ?

Have a nice day

Answer 1

TensorFlow Lite Micro doesn't support Flex delegate, so Selece TF ops can't be run on MCUs. You can try restructuring your model with (for example) keras sequential API instead to make it converted only with TFLite ops.

context: https://github.com/tensorflow/tensorflow/issues/34350#issuecomment-579027135