Hi there. I’m working on a model that combines the “Bert-base-uncased” model with a custom decoder that I’m writing myself. I’m running into issues passing my training data to the TFBertTokenizer. The training data being passed to the tokenizer is a scalar tensor of type tf.String.
training_data.element_spec
# ((TensorSpec(shape=(), dtype=tf.string, name=None),
TensorSpec(shape=<unknown>, dtype=tf.int64, name=None)),
TensorSpec(shape=<unknown>, dtype=tf.int64, name=None))
I then create my BertEncoder…
class BertEncoder(layers.Layer):
def __init__(self, projection_dim):
super().__init__()
self.tokenizer = TFBertTokenizer.from_pretrained("bert-base-uncased")
self.bert = TFBertModel.from_pretrained("bert-base-uncased")
def call(self, input):
x = self.tokenizer(input)
x = self.bert(x)
return x
Wrap it my larger model…
class MyCustomModel(keras.Model):
def __init__(self, decoder_stack_height, d_model, h_model, decoder_dropout_rate, n_decoder_vocab):
super().__init__()
self.encoder = BertEncoder(d_model)
self.decoder = MyCustomDecoder(decoder_stack_height,
d_model,
h_model,
decoder_dropout_rate)
# create some additional layers
def call(self, input):
# input is a tuple of `tf.data.Datasets` containing tensors of type `tf.String` and `tf.int32` respectively
bill_text, prebill_series = input
context = self.encoder(bill_text)
# do some more stuff with context to create x
return x
Then I call model.fit
my_model = MyCustomModel(...)
my_model.fit(train_data, batch_size=32, epochs=5, verbose=2)
The error I then get is:
AttributeError Traceback (most recent call last)
Cell In[48], line 1
----> 1 my_model.fit(train_data, batch_size=32, epochs=5, verbose=2)
File ~/miniconda3/envs/WeThePeople/lib/python3.10/site-packages/keras/src/utils/traceback_utils.py:70, in filter_traceback.<locals>.error_handler(*args, **kwargs)
67 filtered_tb = _process_traceback_frames(e.__traceback__)
68 # To get the full stack trace, call:
69 # `tf.debugging.disable_traceback_filtering()`
---> 70 raise e.with_traceback(filtered_tb) from None
71 finally:
72 del filtered_tb
File /var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file359vbblq.py:15, in outer_factory.<locals>.inner_factory.<locals>.tf__train_function(iterator)
13 try:
14 do_return = True
---> 15 retval_ = ag__.converted_call(ag__.ld(step_function), (ag__.ld(self), ag__.ld(iterator)), None, fscope)
16 except:
17 do_return = False
File /var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filel3wen_qt.py:11, in outer_factory.<locals>.inner_factory.<locals>.tf__call(self, input)
9 retval_ = ag__.UndefinedReturnValue()
10 (bill_text, prebill_series) = ag__.ld(input)
---> 11 context = ag__.converted_call(ag__.ld(self).encoder, (ag__.ld(bill_text),), None, fscope)
12 x = ag__.converted_call(ag__.ld(self).embedding, (ag__.ld(prebill_series),), None, fscope)
13 x = ag__.ld(x) + ag__.converted_call(ag__.ld(self).positional_encoding, (ag__.ld(x),), None, fscope)
File /var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileexf83jen.py:10, in outer_factory.<locals>.inner_factory.<locals>.tf__call(self, input)
8 do_return = False
9 retval_ = ag__.UndefinedReturnValue()
---> 10 x = ag__.converted_call(ag__.ld(self).tokenizer, (ag__.ld(input),), None, fscope)
11 x = ag__.converted_call(ag__.ld(self).bert, (ag__.ld(x),), None, fscope)
12 x = ag__.converted_call(ag__.ld(self).broadcaster, (ag__.ld(x).last_hidden_state,), None, fscope)
File /var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileixkodvsj.py:44, in outer_factory.<locals>.inner_factory.<locals>.tf__error_handler(*args, **kwargs)
42 filtered_tb = ag__.Undefined('filtered_tb')
43 filtered_tb = ag__.Undefined('filtered_tb')
---> 44 ag__.if_stmt(ag__.not_(ag__.converted_call(ag__.ld(tf).debugging.is_traceback_filtering_enabled, (), None, fscope)), if_body, else_body, get_state, set_state, ('do_return', 'retval_'), 2)
45 return fscope.ret(retval_, do_return)
File /var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileixkodvsj.py:40, in outer_factory.<locals>.inner_factory.<locals>.tf__error_handler.<locals>.else_body()
38 except Exception as e:
39 filtered_tb = ag__.converted_call(ag__.ld(_process_traceback_frames), (ag__.ld(e).__traceback__,), None, fscope)
---> 40 raise ag__.converted_call(ag__.ld(e).with_traceback, (ag__.ld(filtered_tb),), None, fscope) from None
41 finally:
42 filtered_tb = ag__.Undefined('filtered_tb')
File /var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileixkodvsj.py:34, in outer_factory.<locals>.inner_factory.<locals>.tf__error_handler.<locals>.else_body()
32 try:
33 do_return = True
---> 34 retval_ = ag__.converted_call(ag__.ld(fn), tuple(ag__.ld(args)), dict(**ag__.ld(kwargs)), fscope)
35 except:
36 do_return = False
File /var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileismqzjpj.py:242, in outer_factory.<locals>.inner_factory.<locals>.tf____call__(self, *args, **kwargs)
240 call_context = ag__.Undefined('call_context')
241 namescope_stack = ag__.Undefined('namescope_stack')
--> 242 ag__.if_stmt(ag__.converted_call(ag__.ld(_in_functional_construction_mode), (ag__.ld(self), ag__.ld(inputs), ag__.ld(args), ag__.ld(kwargs), ag__.ld(input_list)), None, fscope), if_body_11, else_body_11, get_state_11, set_state_11, ('do_return', "kwargs['mask']", 'retval_', 'args', 'input_list', 'inputs', 'kwargs'), 3)
243 return fscope.ret(retval_, do_return)
File /var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileismqzjpj.py:187, in outer_factory.<locals>.inner_factory.<locals>.tf____call__.<locals>.else_body_11()
185 ag__.if_stmt(ag__.ld(self)._autocast, if_body_7, else_body_7, get_state_7, set_state_7, ('inputs',), 1)
186 with ag__.ld(autocast_variable).enable_auto_cast_variables(ag__.ld(self)._compute_dtype_object):
--> 187 outputs = ag__.converted_call(ag__.ld(call_fn), (ag__.ld(inputs),) + tuple(ag__.ld(args)), dict(**ag__.ld(kwargs)), fscope)
189 def get_state_8():
190 return ()
File /var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filebwu5sw92.py:162, in outer_factory.<locals>.inner_factory.<locals>.tf__inject_argument_info_in_traceback.<locals>.error_handler(*args, **kwargs)
160 new_e = ag__.Undefined('new_e')
161 ag__.if_stmt(ag__.ld(arguments_context), if_body_5, else_body_5, get_state_6, set_state_6, ('new_e', 'arguments_context'), 1)
--> 162 raise ag__.converted_call(ag__.ld(new_e).with_traceback, (ag__.ld(e).__traceback__,), None, fscope_1) from None
163 finally:
164 signature = ag__.Undefined('signature')
File /var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filebwu5sw92.py:34, in outer_factory.<locals>.inner_factory.<locals>.tf__inject_argument_info_in_traceback.<locals>.error_handler(*args, **kwargs)
32 try:
33 do_return_1 = True
---> 34 retval__1 = ag__.converted_call(ag__.ld(fn), tuple(ag__.ld(args)), dict(**ag__.ld(kwargs)), fscope_1)
35 except:
36 do_return_1 = False
File /var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filez_q7mnw_.py:218, in outer_factory.<locals>.inner_factory.<locals>.tf__call(self, text, text_pair, padding, truncation, max_length, pad_to_multiple_of, return_token_type_ids, return_attention_mask)
216 pass
217 ag__.if_stmt(ag__.ld(text).shape.rank == 2, if_body_13, else_body_13, get_state_13, set_state_13, ('text', 'text_pair'), 2)
--> 218 text = ag__.converted_call(ag__.ld(self).unpaired_tokenize, (ag__.ld(text),), None, fscope)
220 def get_state_16():
221 return (input_ids, token_type_ids, text, text_pair)
File /var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file1sz285hp.py:26, in outer_factory.<locals>.inner_factory.<locals>.tf__unpaired_tokenize(self, texts)
24 pass
25 ag__.if_stmt(ag__.ld(self).do_lower_case, if_body, else_body, get_state, set_state, ('texts',), 1)
---> 26 tokens = ag__.converted_call(ag__.ld(self).tf_tokenizer.tokenize, (ag__.ld(texts),), None, fscope)
27 try:
28 do_return = True
File /var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filetu0cba57.py:29, in outer_factory.<locals>.inner_factory.<locals>.tf__tokenize(self, text_input)
27 do_return = False
28 retval_ = ag__.UndefinedReturnValue()
---> 29 normalized_input = ag__.converted_call(ag__.ld(self)._fast_bert_normalizer.normalize, (ag__.ld(text_input),), None, fscope)
30 try:
31 do_return = True
File /var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file3t60g1pt.py:26, in outer_factory.<locals>.inner_factory.<locals>.tf__normalize(self, input)
24 do_return = False
25 retval_ = ag__.UndefinedReturnValue()
---> 26 (normalized_texts, _) = ag__.converted_call(ag__.ld(self)._normalize_with_offsets_helper, (ag__.ld(input),), dict(get_offsets=False), fscope)
27 try:
28 do_return = True
File /var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file993afsy6.py:158, in outer_factory.<locals>.inner_factory.<locals>.tf___normalize_with_offsets_helper(self, input, get_offsets)
156 normalized_texts = ag__.Undefined('normalized_texts')
157 row_splits = ag__.Undefined('row_splits')
--> 158 ag__.if_stmt(ag__.ld(rank) == 0, if_body_6, else_body_6, get_state_6, set_state_6, ('do_return', 'retval_', 'input'), 2)
159 return fscope.ret(retval_, do_return)
File /var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file993afsy6.py:53, in outer_factory.<locals>.inner_factory.<locals>.tf___normalize_with_offsets_helper.<locals>.if_body_6()
51 try:
52 do_return = True
---> 53 retval_ = (ag__.ld(normalized_texts).values, ag__.if_exp(ag__.ld(get_offsets), lambda : ag__.ld(offsets).values, lambda : None, 'get_offsets'))
54 except:
55 do_return = False
AttributeError: in user code:
File "/Users/tomi/miniconda3/envs/WeThePeople/lib/python3.10/site-packages/keras/src/engine/training.py", line 1401, in train_function *
return step_function(self, iterator)
File "/Users/tomi/miniconda3/envs/WeThePeople/lib/python3.10/site-packages/keras/src/engine/training.py", line 1384, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/Users/tomi/miniconda3/envs/WeThePeople/lib/python3.10/site-packages/keras/src/engine/training.py", line 1373, in run_step **
outputs = model.train_step(data)
File "/Users/tomi/miniconda3/envs/WeThePeople/lib/python3.10/site-packages/keras/src/engine/training.py", line 1150, in train_step
y_pred = self(x, training=True)
File "/Users/tomi/miniconda3/envs/WeThePeople/lib/python3.10/site-packages/keras/src/utils/traceback_utils.py", line 70, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filel3wen_qt.py", line 11, in tf__call
context = ag__.converted_call(ag__.ld(self).encoder, (ag__.ld(bill_text),), None, fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileexf83jen.py", line 10, in tf__call
x = ag__.converted_call(ag__.ld(self).tokenizer, (ag__.ld(input),), None, fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileixkodvsj.py", line 44, in tf__error_handler
ag__.if_stmt(ag__.not_(ag__.converted_call(ag__.ld(tf).debugging.is_traceback_filtering_enabled, (), None, fscope)), if_body, else_body, get_state, set_state, ('do_return', 'retval_'), 2)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileixkodvsj.py", line 40, in else_body
raise ag__.converted_call(ag__.ld(e).with_traceback, (ag__.ld(filtered_tb),), None, fscope) from None
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileixkodvsj.py", line 34, in else_body
retval_ = ag__.converted_call(ag__.ld(fn), tuple(ag__.ld(args)), dict(**ag__.ld(kwargs)), fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileismqzjpj.py", line 242, in tf____call__
ag__.if_stmt(ag__.converted_call(ag__.ld(_in_functional_construction_mode), (ag__.ld(self), ag__.ld(inputs), ag__.ld(args), ag__.ld(kwargs), ag__.ld(input_list)), None, fscope), if_body_11, else_body_11, get_state_11, set_state_11, ('do_return', "kwargs['mask']", 'retval_', 'args', 'input_list', 'inputs', 'kwargs'), 3)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileismqzjpj.py", line 187, in else_body_11
outputs = ag__.converted_call(ag__.ld(call_fn), (ag__.ld(inputs),) + tuple(ag__.ld(args)), dict(**ag__.ld(kwargs)), fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filebwu5sw92.py", line 162, in error_handler
raise ag__.converted_call(ag__.ld(new_e).with_traceback, (ag__.ld(e).__traceback__,), None, fscope_1) from None
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filebwu5sw92.py", line 34, in error_handler
retval__1 = ag__.converted_call(ag__.ld(fn), tuple(ag__.ld(args)), dict(**ag__.ld(kwargs)), fscope_1)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filez_q7mnw_.py", line 218, in tf__call
text = ag__.converted_call(ag__.ld(self).unpaired_tokenize, (ag__.ld(text),), None, fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file1sz285hp.py", line 26, in tf__unpaired_tokenize
tokens = ag__.converted_call(ag__.ld(self).tf_tokenizer.tokenize, (ag__.ld(texts),), None, fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filetu0cba57.py", line 29, in tf__tokenize
normalized_input = ag__.converted_call(ag__.ld(self)._fast_bert_normalizer.normalize, (ag__.ld(text_input),), None, fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file3t60g1pt.py", line 26, in tf__normalize
(normalized_texts, _) = ag__.converted_call(ag__.ld(self)._normalize_with_offsets_helper, (ag__.ld(input),), dict(get_offsets=False), fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file993afsy6.py", line 158, in tf___normalize_with_offsets_helper
ag__.if_stmt(ag__.ld(rank) == 0, if_body_6, else_body_6, get_state_6, set_state_6, ('do_return', 'retval_', 'input'), 2)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file993afsy6.py", line 53, in if_body_6
retval_ = (ag__.ld(normalized_texts).values, ag__.if_exp(ag__.ld(get_offsets), lambda : ag__.ld(offsets).values, lambda : None, 'get_offsets'))
AttributeError: Exception encountered when calling layer 'my_custom_model_2' (type MyCustomModel).
in user code:
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/ipykernel_83321/3228993956.py", line 31, in call *
context = self.encoder(bill_text)
File "/Users/tomi/miniconda3/envs/WeThePeople/lib/python3.10/site-packages/keras/src/utils/traceback_utils.py", line 70, in error_handler **
raise e.with_traceback(filtered_tb) from None
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileexf83jen.py", line 10, in tf__call
x = ag__.converted_call(ag__.ld(self).tokenizer, (ag__.ld(input),), None, fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileixkodvsj.py", line 44, in tf__error_handler
ag__.if_stmt(ag__.not_(ag__.converted_call(ag__.ld(tf).debugging.is_traceback_filtering_enabled, (), None, fscope)), if_body, else_body, get_state, set_state, ('do_return', 'retval_'), 2)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileixkodvsj.py", line 40, in else_body
raise ag__.converted_call(ag__.ld(e).with_traceback, (ag__.ld(filtered_tb),), None, fscope) from None
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileixkodvsj.py", line 34, in else_body
retval_ = ag__.converted_call(ag__.ld(fn), tuple(ag__.ld(args)), dict(**ag__.ld(kwargs)), fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileismqzjpj.py", line 242, in tf____call__
ag__.if_stmt(ag__.converted_call(ag__.ld(_in_functional_construction_mode), (ag__.ld(self), ag__.ld(inputs), ag__.ld(args), ag__.ld(kwargs), ag__.ld(input_list)), None, fscope), if_body_11, else_body_11, get_state_11, set_state_11, ('do_return', "kwargs['mask']", 'retval_', 'args', 'input_list', 'inputs', 'kwargs'), 3)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_fileismqzjpj.py", line 187, in else_body_11
outputs = ag__.converted_call(ag__.ld(call_fn), (ag__.ld(inputs),) + tuple(ag__.ld(args)), dict(**ag__.ld(kwargs)), fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filebwu5sw92.py", line 162, in error_handler
raise ag__.converted_call(ag__.ld(new_e).with_traceback, (ag__.ld(e).__traceback__,), None, fscope_1) from None
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filebwu5sw92.py", line 34, in error_handler
retval__1 = ag__.converted_call(ag__.ld(fn), tuple(ag__.ld(args)), dict(**ag__.ld(kwargs)), fscope_1)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filez_q7mnw_.py", line 218, in tf__call
text = ag__.converted_call(ag__.ld(self).unpaired_tokenize, (ag__.ld(text),), None, fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file1sz285hp.py", line 26, in tf__unpaired_tokenize
tokens = ag__.converted_call(ag__.ld(self).tf_tokenizer.tokenize, (ag__.ld(texts),), None, fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filetu0cba57.py", line 29, in tf__tokenize
normalized_input = ag__.converted_call(ag__.ld(self)._fast_bert_normalizer.normalize, (ag__.ld(text_input),), None, fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file3t60g1pt.py", line 26, in tf__normalize
(normalized_texts, _) = ag__.converted_call(ag__.ld(self)._normalize_with_offsets_helper, (ag__.ld(input),), dict(get_offsets=False), fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file993afsy6.py", line 158, in tf___normalize_with_offsets_helper
ag__.if_stmt(ag__.ld(rank) == 0, if_body_6, else_body_6, get_state_6, set_state_6, ('do_return', 'retval_', 'input'), 2)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file993afsy6.py", line 53, in if_body_6
retval_ = (ag__.ld(normalized_texts).values, ag__.if_exp(ag__.ld(get_offsets), lambda : ag__.ld(offsets).values, lambda : None, 'get_offsets'))
AttributeError: Exception encountered when calling layer 'bert_encoder_2' (type BertEncoder).
in user code:
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/ipykernel_83321/3228993956.py", line 10, in call *
x = self.tokenizer(input)
File "/Users/tomi/miniconda3/envs/WeThePeople/lib/python3.10/site-packages/tf_keras/src/engine/base_layer.py", line 998, in error_handler *
return fn(*args, **kwargs)
File "/Users/tomi/miniconda3/envs/WeThePeople/lib/python3.10/site-packages/tf_keras/src/engine/base_layer.py", line 1136, in __call__ *
outputs = call_fn(inputs, *args, **kwargs)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filebwu5sw92.py", line 162, in error_handler **
raise ag__.converted_call(ag__.ld(new_e).with_traceback, (ag__.ld(e).__traceback__,), None, fscope_1) from None
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filebwu5sw92.py", line 34, in error_handler
retval__1 = ag__.converted_call(ag__.ld(fn), tuple(ag__.ld(args)), dict(**ag__.ld(kwargs)), fscope_1)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filez_q7mnw_.py", line 218, in tf__call **
text = ag__.converted_call(ag__.ld(self).unpaired_tokenize, (ag__.ld(text),), None, fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file1sz285hp.py", line 26, in tf__unpaired_tokenize **
tokens = ag__.converted_call(ag__.ld(self).tf_tokenizer.tokenize, (ag__.ld(texts),), None, fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_filetu0cba57.py", line 29, in tf__tokenize **
normalized_input = ag__.converted_call(ag__.ld(self)._fast_bert_normalizer.normalize, (ag__.ld(text_input),), None, fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file3t60g1pt.py", line 26, in tf__normalize **
(normalized_texts, _) = ag__.converted_call(ag__.ld(self)._normalize_with_offsets_helper, (ag__.ld(input),), dict(get_offsets=False), fscope)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file993afsy6.py", line 158, in tf___normalize_with_offsets_helper **
ag__.if_stmt(ag__.ld(rank) == 0, if_body_6, else_body_6, get_state_6, set_state_6, ('do_return', 'retval_', 'input'), 2)
File "/var/folders/tt/ptdq0zld5qvg2z3pqs7lctf00000gn/T/__autograph_generated_file993afsy6.py", line 53, in if_body_6
retval_ = (ag__.ld(normalized_texts).values, ag__.if_exp(ag__.ld(get_offsets), lambda : ag__.ld(offsets).values, lambda : None, 'get_offsets'))
AttributeError: Exception encountered when calling layer 'tf_bert_tokenizer_3' (type TFBertTokenizer).
in user code:
File "/Users/tomi/miniconda3/envs/WeThePeople/lib/python3.10/site-packages/transformers/models/bert/tokenization_bert_tf.py", line 214, in call *
text = self.unpaired_tokenize(text)
File "/Users/tomi/miniconda3/envs/WeThePeople/lib/python3.10/site-packages/transformers/models/bert/tokenization_bert_tf.py", line 172, in unpaired_tokenize *
tokens = self.tf_tokenizer.tokenize(texts)
File "/Users/tomi/miniconda3/envs/WeThePeople/lib/python3.10/site-packages/tensorflow_text/python/ops/fast_bert_tokenizer.py", line 159, in tokenize *
normalized_input = self._fast_bert_normalizer.normalize(text_input)
File "/Users/tomi/miniconda3/envs/WeThePeople/lib/python3.10/site-packages/tensorflow_text/python/ops/fast_bert_normalizer.py", line 93, in normalize *
normalized_texts, _ = self._normalize_with_offsets_helper(
File "/Users/tomi/miniconda3/envs/WeThePeople/lib/python3.10/site-packages/tensorflow_text/python/ops/fast_bert_normalizer.py", line 157, in _normalize_with_offsets_helper *
offsets.values if get_offsets else None)
AttributeError: 'SymbolicTensor' object has no attribute 'values'
Call arguments received by layer 'tf_bert_tokenizer_3' (type TFBertTokenizer):
• text=tf.Tensor(shape=(), dtype=string)
• text_pair=None
• padding=None
• truncation=None
• max_length=None
• pad_to_multiple_of=None
• return_token_type_ids=None
• return_attention_mask=None
Call arguments received by layer 'bert_encoder_2' (type BertEncoder):
• input=tf.Tensor(shape=(), dtype=string)
Call arguments received by layer 'my_custom_model_2' (type MyCustomModel):
• input=('tf.Tensor(shape=(), dtype=string)', 'tf.Tensor(shape=<unknown>, dtype=int64)')
Could anyone explain what’s going on/how to fix? Does TFBertTokenizer even work with tf.tensors at all?