tensorflow: TF2.3 converter.convert ValueError: Input 0 of node StatefulPartitionedCall/functional_1/resnet50/conv1_bn/AssignNewValue was passed float from Func/StatefulPartitionedCall/input/_5:0 incompatible with expected resource.

System information

• OS Platform and Distribution (Ubuntu 18.04, cuda 10.1):
• TensorFlow installed from (binary):
• TensorFlow version (TF 2.3):

Here is the part of my code.

       export_path './test_model'
        tf.saved_model.save(model, export_path)
        converter = tf.lite.TFLiteConverter.from_saved_model(export_path)
        converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS]
        tflite_model = converter.convert()
        open("./converted_model.tflite", "wb").write(tflite_model)

Here is my model summary, which is a typical image classification model using pre_trained ResNet50 model for transfer-learning.

Model: "functional_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_2 (InputLayer)         [(None, 160, 160, 3)]     0         
_________________________________________________________________
sequential (Sequential)      (None, 160, 160, 3)       0         
_________________________________________________________________
tf_op_layer_RealDiv (TensorF [(None, 160, 160, 3)]     0         
_________________________________________________________________
tf_op_layer_Sub (TensorFlowO [(None, 160, 160, 3)]     0         
_________________________________________________________________
resnet50 (Functional)        (None, 5, 5, 2048)        23587712  
_________________________________________________________________
global_average_pooling2d (Gl (None, 2048)              0         
_________________________________________________________________
dropout (Dropout)            (None, 2048)              0         
_________________________________________________________________
dense (Dense)                (None, 3)                 6147      
=================================================================
Total params: 23,593,859
Trainable params: 23,540,739
Non-trainable params: 53,120
_________________________________________________________________

Here is the failure errors.

Traceback (most recent call last):
  File "/home/ktatc/anaconda3/envs/HHproject/lib/python3.7/site-packages/tensorflow/python/framework/importer.py", line 497, in _import_graph_def_internal
    graph._c_graph, serialized, options)  # pylint: disable=protected-access
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input 0 of node StatefulPartitionedCall/functional_1/resnet50/conv1_bn/AssignNewValue was passed float from Func/StatefulPartitionedCall/input/_5:0 incompatible with expected resource.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):

  File "main.py", line 321, in <module>
    main(train='lite')
  File "main.py", line 210, in main
    tflite_model = converter.convert()
  File "/home/ktatc/anaconda3/envs/HHproject/lib/python3.7/site-packages/tensorflow/lite/python/lite.py", line 1076, in convert
    return super(TFLiteConverterV2, self).convert()
  File "/home/ktatc/anaconda3/envs/HHproject/lib/python3.7/site-packages/tensorflow/lite/python/lite.py", line 878, in convert
    self._funcs[0], lower_control_flow=False))
  File "/home/ktatc/anaconda3/envs/HHproject/lib/python3.7/site-packages/tensorflow/python/framework/convert_to_constants.py", line 1109, in convert_variables_to_constants_v2_as_graph
    converted_input_indices)
  File "/home/ktatc/anaconda3/envs/HHproject/lib/python3.7/site-packages/tensorflow/python/framework/convert_to_constants.py", line 1001, in _construct_concrete_function
    new_output_names)
  File "/home/ktatc/anaconda3/envs/HHproject/lib/python3.7/site-packages/tensorflow/python/eager/wrap_function.py", line 650, in function_from_graph_def
    wrapped_import = wrap_function(_imports_graph_def, [])
  File "/home/ktatc/anaconda3/envs/HHproject/lib/python3.7/site-packages/tensorflow/python/eager/wrap_function.py", line 628, in wrap_function
    collections={}),
  File "/home/ktatc/anaconda3/envs/HHproject/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py", line 986, in func_graph_from_py_func
    func_outputs = python_func(*func_args, **func_kwargs)
  File "/home/ktatc/anaconda3/envs/HHproject/lib/python3.7/site-packages/tensorflow/python/eager/wrap_function.py", line 87, in __call__
    return self.call_with_variable_creator_scope(self._fn)(*args, **kwargs)
  File "/home/ktatc/anaconda3/envs/HHproject/lib/python3.7/site-packages/tensorflow/python/eager/wrap_function.py", line 93, in wrapped
    return fn(*args, **kwargs)
  File "/home/ktatc/anaconda3/envs/HHproject/lib/python3.7/site-packages/tensorflow/python/eager/wrap_function.py", line 648, in _imports_graph_def
    importer.import_graph_def(graph_def, name="")
  File "/home/ktatc/anaconda3/envs/HHproject/lib/python3.7/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
    return func(*args, **kwargs)
  File "/home/ktatc/anaconda3/envs/HHproject/lib/python3.7/site-packages/tensorflow/python/framework/importer.py", line 405, in import_graph_def
    producer_op_list=producer_op_list)
  File "/home/ktatc/anaconda3/envs/HHproject/lib/python3.7/site-packages/tensorflow/python/framework/importer.py", line 501, in _import_graph_def_internal
    raise ValueError(str(e))
**ValueError: Input 0 of node StatefulPartitionedCall/functional_1/resnet50/conv1_bn/AssignNewValue was passed float from Func/StatefulPartitionedCall/input/_5:0 incompatible with expected resource.**

How can i solve it? I don’t know the reason why these kind of error happen. please let me know in detail. Thanks in advance.