TensorFlow: Using CRF for NER (shape-mismatch) [tensorflow_addons]

Question

I am trying to build a Bi-LSTM CRF model for NER on CoNLL-2003 dataset

I have encoded the words using char embedding and GloVe embedding, for each token I have an embedding of size 341

This is my model:

def get_model(embed_size, max_seq_len, num_labels):

    #model
    input = Input(shape=(max_seq_len,embed_size), name="Input_Layer")
    model = Bidirectional(LSTM(units=75, return_sequences=True), name="Bi-LSTM")(input)  # variational biLSTM
    model = TimeDistributed(Dense(75, activation="relu"), name="Bi-LSTM-out")(model)  # a dense layer as suggested by neuralNer
    crf = CRF(num_labels, name='CRF-layer')  # CRF layer
    out = crf(model)  # output
    model = Model(input, out)
    model.summary(line_length=150)

    f1 = tfa.metrics.F1Score(num_classes=num_labels)

    model.compile(optimizer="adam", loss='categorical_crossentropy', metrics=['accuracy', f1])

    return model

model = get_model(embed_size=341, max_seq_len=16, num_labels=9)
model.fit(
        train_x, train_y
    )

Model Summary:

______________________________________________________________________________________________________________________________________________________
Layer (type)                                                       Output Shape                                                Param #                
======================================================================================================================================================
Input_Layer (InputLayer)                                           [(None, 16, 341)]                                           0                      
______________________________________________________________________________________________________________________________________________________
Bi-LSTM (Bidirectional)                                            (None, 16, 150)                                             250200                 
______________________________________________________________________________________________________________________________________________________
Bi-LSTM-out (TimeDistributed)                                      (None, 16, 75)                                              11325                  
______________________________________________________________________________________________________________________________________________________
CRF-layer (CRF)                                                    [(None, 16), (None, 16, 9), (None,), (9, 9)]                783                    
======================================================================================================================================================
Total params: 262,308
Trainable params: 262,308
Non-trainable params: 0
______________________________________________________________________________________________________________________________________________________

Input shape: x is ((3250, 16, 341) and y is (3250, 16, 9)) I am training on 3250 data points each seq of length 16, each token is embedded in 341 dimensions and there are 9 labels possible

Now the error I am getting is:

ValueError: Shapes (None, 16, 9) and (None, 16) are incompatible

which I believe is because the CRF output is [(None, 16), (None, 16, 9), (None,), (9, 9)]

Is there a way to just get the second element of the output?

OR any other way this can be fixed?

I am using tf 2.0 + and CRF from from tensorflow_addons.layers import CRF

I have already implemented this in tf 1.15 using CRF from keras-contrib [Don't want that]

Adding Trace-Back based on @MyStackRunnethOver comments:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-15-f0e6bf499704> in <module>()
     18 model = get_model(embed_size=341, max_seq_len=16, num_labels=9)
     19 model.fit(
---> 20         valid_x, valid_y
     21     )

9 frames
/usr/local/lib/python3.7/dist-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)
   1098                 _r=1):
   1099               callbacks.on_train_batch_begin(step)
-> 1100               tmp_logs = self.train_function(iterator)
   1101               if data_handler.should_sync:
   1102                 context.async_wait()

/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
    826     tracing_count = self.experimental_get_tracing_count()
    827     with trace.Trace(self._name) as tm:
--> 828       result = self._call(*args, **kwds)
    829       compiler = "xla" if self._experimental_compile else "nonXla"
    830       new_tracing_count = self.experimental_get_tracing_count()

/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
    869       # This is the first call of __call__, so we have to initialize.
    870       initializers = []
--> 871       self._initialize(args, kwds, add_initializers_to=initializers)
    872     finally:
    873       # At this point we know that the initialization is complete (or less

/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
    724     self._concrete_stateful_fn = (
    725         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
--> 726             *args, **kwds))
    727 
    728     def invalid_creator_scope(*unused_args, **unused_kwds):

/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
   2967       args, kwargs = None, None
   2968     with self._lock:
-> 2969       graph_function, _ = self._maybe_define_function(args, kwargs)
   2970     return graph_function
   2971 

/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
   3359 
   3360           self._function_cache.missed.add(call_context_key)
-> 3361           graph_function = self._create_graph_function(args, kwargs)
   3362           self._function_cache.primary[cache_key] = graph_function
   3363 

/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3204             arg_names=arg_names,
   3205             override_flat_arg_shapes=override_flat_arg_shapes,
-> 3206             capture_by_value=self._capture_by_value),
   3207         self._function_attributes,
   3208         function_spec=self.function_spec,

/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
    988         _, original_func = tf_decorator.unwrap(python_func)
    989 
--> 990       func_outputs = python_func(*func_args, **func_kwargs)
    991 
    992       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/def_function.py in wrapped_fn(*args, **kwds)
    632             xla_context.Exit()
    633         else:
--> 634           out = weak_wrapped_fn().__wrapped__(*args, **kwds)
    635         return out
    636 

/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
    975           except Exception as e:  # pylint:disable=broad-except
    976             if hasattr(e, "ag_error_metadata"):
--> 977               raise e.ag_error_metadata.to_exception(e)
    978             else:
    979               raise

ValueError: in user code:

    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:805 train_function  *
        return step_function(self, iterator)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:795 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:1259 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:2730 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:3417 _call_for_each_replica
        return fn(*args, **kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:788 run_step  **
        outputs = model.train_step(data)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:756 train_step
        y, y_pred, sample_weight, regularization_losses=self.losses)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/compile_utils.py:203 __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/losses.py:152 __call__
        losses = call_fn(y_true, y_pred)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/losses.py:256 call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
        return target(*args, **kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/losses.py:1537 categorical_crossentropy
        return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
        return target(*args, **kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/backend.py:4833 categorical_crossentropy
        target.shape.assert_is_compatible_with(output.shape)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/tensor_shape.py:1134 assert_is_compatible_with
        raise ValueError("Shapes %s and %s are incompatible" % (self, other))

    ValueError: Shapes (None, 16, 9) and (None, 16) are incompatible

Finally I will be checking and implementing this question and all the possible/proposed solutions between 8AM to 8PM [IST] until it's solved, so please help!