CODEWITHSUNDEEP
keras
Seanny123
Seanny123

Reputation: 9346

Two inputs into RNN

If I want to put the inputs of two networks into an RNN in Keras, how do I accomplish this? For example, assume I have two RNNs A and B with their outputs going into RNN C.

Upvotes: 1

Views: 440

Answers (1)

Seanny123
Seanny123

Reputation: 9346

Using keras.layers.merge.concatenate is required. See the example below:

def build_rnn(x_train, y_train, in_len):
    epochs = 100
    batch_size = 300
    hidden_units = 256

    vec_dims = 1
    in_shape = (in_len, vec_dims)

    inputs = [Input(shape=in_shape, name="input_a"), Input(shape=in_shape, name="input_b")]
    merge_outs = []

    for inp in inputs:
        # stack a few RNNs
        net = SimpleRNN(hidden_units, return_sequences=True)(inp)
        merge_outs.append(SimpleRNN(hidden_units, return_sequences=True)(net))

    merged = Concatenate(axis=-1)(merge_outs)
    merged = SimpleRNN(hidden_units, input_shape=(in_len, 2*vec_dims, ), return_sequences=False,
                       name="pre_out")(merged)
    output = Dense(vec_dims, input_shape=(vec_dims,), name='output')(merged)

    model = Model(inputs=inputs, outputs=[output])
    return model

Upvotes: 1

Related Questions