Putting it all together

Now let's look at the entire network, now that we understand the parts. The network is shown in the following code for your reference:

def build_network(vocab_size, embedding_dim, sequence_length):    input = Input(shape=(sequence_length,), name="Input")    embedding = Embedding(input_dim=vocab_size,         output_dim=embedding_dim, input_length=sequence_length,          name="embedding")(input)    lstm1 = LSTM(10, activation='tanh', return_sequences=False,       dropout=0.2, recurrent_dropout=0.2, name='lstm1')(embedding)    output = Dense(1, activation='sigmoid', name='sigmoid')(lstm1)    model = Model(inputs=input, outputs=output)    model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])    return model

As we have with other ...

Get Deep Learning Quick Reference now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.