Multiple Features at the Input Layer Keras Python

Question

I am implementing a simple LSTM network. I would like to include multiple features at the input layer. These features are a pre-trained word embeddings and a vector to flag a specific word in the given sentence.

For example:

Sentence = "I have a question"
feature_vector_1 = [4, 2, 281, 5201] #word2index which will be passed to the embedding layer
feature_vector_2 = [0, 1, 0, 0]

final features= [feature_vector_1 + feature_vector_2]

suppose that:

embedding is of dim = 100
index_flag is of dim = 50 
max sentence length = 50

My network code is:

input= Input(shape=(None,))
embedded_layer_input=Embedding(input_dim=embedding_matrix.shape[0], output_dim=embedding_matrix.shape[1],
                     input_length=tweet_max_length, weights= [embedding_matrix], trainable=False)(input)
lstm_layer=Bidirectional(LSTM(64))(embedded_layer_input)
output_layer=Dense(1,activation='sigmoid')(lstm_layer)

model=Model(input, output_layer)

#complie and train
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['acc'])  

# Summarize the model
print(model.summary()) 

# Fit the model
model.fit(padded_train_x, y_train, epochs=epochs, batch_size=batch_size, shuffle=False, verbose=1, validation_data=(padded_dev_x,y_dev))

My question is how and where to include the new feature vector? I looked at Concatenate but I am not sure how to prepare feature vector 2.

nuric · Accepted Answer · 2019-03-17 22:18:16Z

2

You can add a second input just like the first one and concatenate afterwards:

input= Input(shape=(None,))
flag_in = Input(shape=(None,)) ##
embedded_layer_input=Embedding(input_dim=embedding_matrix.shape[0], output_dim=embedding_matrix.shape[1],
                     input_length=tweet_max_length, weights= [embedding_matrix], trainable=False)(input)
combined = Concatenate()([embedded_layer_input, flag_in])
lstm_layer=Bidirectional(LSTM(64))(combined)
output_layer=Dense(1,activation='sigmoid')(lstm_layer)
# From now on you pass a list as your input to your model
model=Model([input, flag_in], output_layer)
# ...
model.fit([padded_xtrain, x_flag_inputs], ...)

answered Mar 17, 2019 at 22:18

nuric

11.3k3 gold badges29 silver badges43 bronze badges

Sign up to request clarification or add additional context in comments.

6 Comments

Omnia Over a year ago

Thanks a lot, @nuric for your prompt reply. I got an error at the Concatenate line saying:

ValueError: A 'Concatenate' layer requires inputs with matching shapes except for the concat axis. Got inputs shapes: [(None, 50, 100), (None, None)]

although I added axis = -1

Omnia Over a year ago

I solved the error above by removing the input_length from the embedding layer. But I got another error while fitting the model which is ValueError: Error when checking input: expected input_2 to have 3 dimensions, but got array with shape (1573, 50) where 1573 is the number of sentences in the training set and 50 is the number of words in each sentence. The shape of padded_xtrain is also (1573,50) so I am not sure what is the problem here?

nuric Over a year ago

You need to expand_dims your numpy array of flags. So it is (1573, 50, 1) which means every input has 50 words each with 1 feature that you can concatenate. Hope that helps.

Omnia Over a year ago

Thanks a lot, @nuric. I used expand_dims(x_flag_inputs, axis=-1) so the shape of flags is (1573,50,1) but I got another error while fitting the model ValueError: Error when checking input: expected input_2 to have shape (None, 50) but got array with shape (50, 1)

nuric Over a year ago

Oh, you also need to change flag_in = Input(shape=(None, 1)) so the input has the extra dimension.

|

Collectives™ on Stack Overflow

Multiple Features at the Input Layer Keras Python

1 Answer 1

6 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

6 Comments

Your Answer

Sign up or log in

Post as a guest

Related