如何在Keras中声明多个输入LSTM模型？

Question

I have a Keras' code of declaring LSTM. But I noticed Container class has already been removed in the latest version. https://keras.io/layers/containers/

How do I declare multiple inputs for LSTM in the latest format? I want to concatenate all inputs for the LSTM inputs.

Although I noticed a similar post, what I want to do is declaration of the model. How to work with multiple inputs for LSTM in Keras?

• keras 1.2.2
• Python 3.5.2 (Anaconda 4.1.1, 64bit)

```

g = Graph()
g.add_input(
    name='i1',
    input_shape=(None, i1_size)
)
g.add_input(
    name='i2',
    input_shape=(None, i2_size)
)
g.add_node(
    LSTM(
        n_hidden,
        return_sequences=True,
        activation='tanh'
    ),
    name='h1',
    inputs=[
        'i1',
        'i2'
    ]
)

```

Oh, May I just set input_shape as (i1_size+i2_size) like below?

model = Sequential()
model.add(LSTM(n_hidden, input_shape=(None, i1_size+i2_size), activation='tanh', return_sequences=True))

Answer 1

You asked:

Oh, May I just set input_shape as (i1_size+i2_size) like below?

 model = Sequential() model.add(LSTM(n_hidden, input_shape=(None, i1_size+i2_size), activation='tanh', return_sequences=True)) 

Yes, Jef. Just keep in mind that your None in (None, i1_size+i2_size) is the number of RNN time steps/input_length and there are caveats to when you can skip defining it. Please see the description for input_length at https://keras.io/layers/recurrent/ for details.

And just FYI input_shape=(None, i1_size+i2_size) can also be written as input_dim=i1_size+i2_size (assuming you don't include input_length ).