Why am I getting the " 'NoneType' object is not callable " error when I apply model.fit in tensorflow? - tensorflow

Question

I'm getting the following error why I apply model.fit. I've described my model and other variables after this error.
--------------------------------------------------------------------------- TypeError Traceback (most recent call
last) in
----> 1 results = model.fit({'title_input': sequences_matrix_train_t, 'body_input': sequences_matrix_train_b},
2 {'main_output': y_train, 'aux_output': y_train},
3 validation_data=[{'title_input': sequences_matrix_test_t, 'body_input': sequences_matrix_test_b},
4 {'main_output': y_test, 'aux_output': y_test}],
5 epochs=5, batch_size=800)
~/Library/Python/3.8/lib/python/site-packages/tensorflow/python/keras/engine/training.py
in _method_wrapper(self, *args, **kwargs)
106 def _method_wrapper(self, *args, **kwargs):
107 if not self._in_multi_worker_mode(): # pylint: disable=protected-access
--> 108 return method(self, *args, **kwargs)
109
110 # Running inside run_distribute_coordinator already.
~/Library/Python/3.8/lib/python/site-packages/tensorflow/python/keras/engine/training.py
in fit(self, x, y, batch_size, epochs, verbose, callbacks,
validation_split, validation_data, shuffle, class_weight,
sample_weight, initial_epoch, steps_per_epoch, validation_steps,
validation_batch_size, validation_freq, max_queue_size, workers,
use_multiprocessing) 1096 batch_size=batch_size):
1097 callbacks.on_train_batch_begin(step)
-> 1098 tmp_logs = train_function(iterator) 1099 if data_handler.should_sync: 1100
context.async_wait()
~/Library/Python/3.8/lib/python/site-packages/tensorflow/python/eager/def_function.py
in call(self, *args, **kwds)
778 else:
779 compiler = "nonXla"
--> 780 result = self._call(*args, **kwds)
781
782 new_tracing_count = self._get_tracing_count()
~/Library/Python/3.8/lib/python/site-packages/tensorflow/python/eager/def_function.py
in _call(self, *args, **kwds)
805 # In this case we have created variables on the first call, so we run the
806 # defunned version which is guaranteed to never create variables.
--> 807 return self._stateless_fn(*args, **kwds) # pylint: disable=not-callable
808 elif self._stateful_fn is not None:
809 # Release the lock early so that multiple threads can perform the call
TypeError: 'NoneType' object is not callable
Getting the above error when I fit my model. The model is described below:-
def RNN():
# RNN part for the title column
title_input = Input(name='title_input',shape=[max_len_of_title_tokens])
title_Embed = Embedding(vocab_len_t+1,2000,input_length=max_len_of_title_tokens,mask_zero=True,name='title_Embed')(title_input)
gru_out_t = GRU(300)(title_Embed)
# Using dense method for auxillary output to smoothen the effects of the GRU
auxiliary_output = Dense(10, activation='sigmoid', name='aux_output')(gru_out_t)
# RNN part for the body column
body_input = Input(name='body_input',shape=[max_len_of_body_tokens])
body_Embed = Embedding(vocab_len_b+1,170,input_length=max_len_of_body_tokens,mask_zero=True,name='body_Embed')(body_input)
gru_out_b = GRU(200)(body_Embed)
# combining these two
combined = concatenate([gru_out_t, gru_out_b])
# Feeding combined to our remaining two dense layers
dense1 = Dense(400,activation='relu')(combined)
dropout = Dropout(0.5)(dense1)
batchNormalizer = BatchNormalization()(dropout)
dense2 = Dense(150,activation='relu')(batchNormalizer)
main_output = Dense(10, activation='sigmoid', name='main_output')(dense2)
model = Model(inputs=[title_input, body_input],outputs=[main_output, auxiliary_output])
return model
#python function ends, stack overflow wouldn't let me indent lol.
#below is the code outside the 'RNN' function.
model = RNN() #this 'model' variable is the one over which I apply the 'fit' method.
#Here's how I'm applying the fit method:-
results = model.fit({'title_input': sequences_matrix_train_t, 'body_input': sequences_matrix_train_b},
{'main_output': y_train, 'aux_output': y_train},
validation_data=[{'title_input': sequences_matrix_test_t, 'body_input': sequences_matrix_test_b},
{'main_output': y_test, 'aux_output': y_test}],
epochs=5, batch_size=800)
Can someone please look over my error and help me figure out why it's being caused.
Here's my jupyter notebook for more info – https://github.com/datares/teamRed/blob/main/post_classification.ipynb