Use of LSTM layer inside CNN provides ValueError-CodePudding

I have a problem. I want to use LSTM inside my CNN for a NLP problem. But unfortunately what I got is the following error ValueError: Input 0 of layer "conv1d_37" is incompatible with the layer: expected min_ndim=3, found ndim=2. Full shape received: (None, 128). How can I use the LSTM layer?

from keras.models import Sequential
from keras.layers import Input, Embedding, Dense, GlobalMaxPooling1D, Conv2D, MaxPool2D, LSTM, Bidirectional, Lambda, Conv1D, MaxPooling1D, GlobalMaxPooling1D

model_lstm = Sequential()

model_lstm.add(
        Embedding(vocab_size
                ,embed_size
                ,weights = [embedding_matrix] #Supplied embedding matrix created from glove
                ,input_length = maxlen
                ,trainable=True)
         )
model_lstm.add(SpatialDropout1D(rate = 0.4))
model_lstm.add(Conv1D(256, 7, activation="relu"))
model_lstm.add(MaxPooling1D())
model_lstm.add(LSTM(128, dropout=0.2, recurrent_dropout=0.2))
model_lstm.add(Conv1D(128, 5, activation="relu"))
model_lstm.add(MaxPooling1D())
model_lstm.add(GlobalMaxPooling1D())
model_lstm.add(Dropout(0.3))
model_lstm.add(Dense(128, activation="relu")))
model_lstm.add(Dense(4, activation='softmax'))
print(model_lstm.summary())

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Input In [481], in <cell line: 25>()
     23 model_lstm.add(MaxPooling1D())
     24 model_lstm.add(LSTM(128, dropout=0.2, recurrent_dropout=0.2))
---> 25 model_lstm.add(Conv1D(128, 5, activation="relu"))
     26 model_lstm.add(MaxPooling1D())
     27 #model_lstm.add(Flatten())

File ~\Anaconda3\lib\site-packages\tensorflow\python\training\tracking\base.py:587, in no_automatic_dependency_tracking.<locals>._method_wrapper(self, *args, **kwargs)
    585 self._self_setattr_tracking = False  # pylint: disable=protected-access
    586 try:
--> 587   result = method(self, *args, **kwargs)
    588 finally:
    589   self._self_setattr_tracking = previous_value  # pylint: disable=protected-access

File ~\Anaconda3\lib\site-packages\keras\utils\traceback_utils.py:67, in filter_traceback.<locals>.error_handler(*args, **kwargs)
     65 except Exception as e:  # pylint: disable=broad-except
     66   filtered_tb = _process_traceback_frames(e.__traceback__)
---> 67   raise e.with_traceback(filtered_tb) from None
     68 finally:
     69   del filtered_tb

File ~\Anaconda3\lib\site-packages\keras\engine\input_spec.py:228, in assert_input_compatibility(input_spec, inputs, layer_name)
    226   ndim = x.shape.rank
    227   if ndim is not None and ndim < spec.min_ndim:
--> 228     raise ValueError(f'Input {input_index} of layer "{layer_name}" '
    229                      'is incompatible with the layer: '
    230                      f'expected min_ndim={spec.min_ndim}, '
    231                      f'found ndim={ndim}. '
    232                      f'Full shape received: {tuple(shape)}')
    233 # Check dtype.
    234 if spec.dtype is not None:

ValueError: Input 0 of layer "conv1d_37" is incompatible with the layer: expected min_ndim=3, found ndim=2. Full shape received: (None, 128)

CodePudding user response：

May be try using return_sequences=True . It may resolve the error.

Bcz the dimensions LSTM is expecting is (None, 1, 128) but right now it is getting only 2 dimensions which are (None, 128).

CodePudding user response：

The problem is that you are passing only the output of the first LSTM layer not the hidden states information to the next LSTM Layer for that you must set return_sequences = True