"tuple index out of range" when using self attention layer in imdb dataset

[Larry King]

Hi, I followed the steps to use self-attention layer just as README.md did but I got an error when I created my own model.
Here is my code:

from keras.datasets import imdb # the dataset I used
# ....
review_input = Input(shape=(MAX_WORDS_PER_REVIEW,), dtype='int32')
embedding_layer = Embedding(MAX_WORDS, EMBEDDING_DIM, input_length=MAX_WORDS_PER_REVIEW)
embedding_review = embedding_layer(review_input)
lstm = LSTM(100)(embedding_review)
att_lstm = SelfAttention(units=100, attention_activation="sigmoid")(lstm)  # I used Attention Layer after LSTM layer
preds = Dense(1, activation='sigmoid')(att_lstm)

model = Model(review_input, preds)
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

Here is the error:

"self_attention.py", line 106, in **_build_additive_attention**
    feature_dim = int(input_shape[2])
IndexError: tuple index out of range

It seems that the dimension is not suitable, but I don't know why this happened, since the code worked without the attention layer.

[CyberZHG]

See #22.

[stale]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[Ahmed ElSheikh]

@CyberZHG the solution you proposed in #22 , by using SeqWeightedAttention() does not solve the problem, do you have any other suggestions?

[Lukas]

You need to add return_sequences=True to the LSTM layer

[Ahmed ElSheikh]

Already tried it, yet not working

[NamraRehman]

I'm also having errors on model building using Keras-self-attention.
error:

Note: This error only occurs when I run code on goggle colab. and it runs fine with accurate output on my Local machine using anaconda spyder.

[statcom]

I am having the exact same problem. And I think there is another problem in communications regarding this issue. I tried two solutions provided: "SeqWeightedAttention" or "return_sequence=True in the previous LSTM layer", and both didn't work. SeqWeightedAttention gave the exact same error and I don't have LSTM layer so the second solution doesn't even make any sense.