Initializing LSTM hidden state Tensorflow/Keras

Tommy picture Tommy · Feb 23, 2017 · Viewed 11.7k times · Source

Can someone explain how can I initialize hidden state of LSTM in tensorflow? I am trying to build LSTM recurrent auto-encoder, so after i have that model trained i want to transfer learned hidden state of unsupervised model to hidden state of supervised model. Is that even possible with current API? This is paper I am trying to recreate:

http://papers.nips.cc/paper/5949-semi-supervised-sequence-learning.pdf

Answer

Marcin Możejko picture Marcin Możejko · Feb 23, 2017

Yes - this is possible but truly cumbersome. Let's go through an example.

  1. Defining a model:

    from keras.layers import LSTM, Input
    from keras.models import Model
    
    input = Input(batch_shape=(32, 10, 1))
    lstm_layer = LSTM(10, stateful=True)(input)
    
    model = Model(input, lstm_layer)
    model.compile(optimizer="adam", loss="mse")
    

    It's important to build and compile model first as in compilation the initial states are reset. Moreover - you need to specify a batch_shape where batch_size is specified as in this scenario our network should be stateful (which is done by setting a stateful=True mode.

  2. Now we could set the values of initial states:

    import numpy
    import keras.backend as K
    
    hidden_states = K.variable(value=numpy.random.normal(size=(32, 10)))
    cell_states = K.variable(value=numpy.random.normal(size=(32, 10)))
    
    model.layers[1].states[0] = hidden_states
    model.layers[1].states[1] = cell_states 
    

    Note that you need to provide states as a keras variables. states[0] holds hidden states and states[1] holds cell states.

Hope that helps.