Keras Deep Learning Cookbook

Model creation

1. Define the hyperparameters of the model:

RNN = layers.LSTMHIDDEN_SIZE = 128BATCH_SIZE = 128LAYERS = 1

2. Next, we define the sequential model and add various layers to it, as follows:

print('Build model:')model = Sequential()# "Encode" the input sequence using an RNN, producing an output of HIDDEN_SIZE.# Note: For situation where input sequences have a variable length,# use input_shape=(None, num_feature).model.add(RNN(HIDDEN_SIZE, input_shape=(MAXLEN, len(chars))))model.add(layers.RepeatVector(DIGITS + 1))for _ in range(LAYERS): model.add(RNN(HIDDEN_SIZE, return_sequences=True))model.add(layers.TimeDistributed(layers.Dense(len(chars))))model.add(layers.Activation('softmax'))

3. An input to the first LSTM layer of input HIDDEN_SIZE ...