keras_spell.py 文件源码

def generate_model(output_len, chars=None):
    """Generate the model"""
    print('Build model...')
    chars = chars or CHARS
    model = Sequential()
    # "Encode" the input sequence using an RNN, producing an output of HIDDEN_SIZE
    # note: in a situation where your input sequences have a variable length,
    # use input_shape=(None, nb_feature).
    for layer_number in range(INPUT_LAYERS):
        model.add(recurrent.LSTM(HIDDEN_SIZE, input_shape=(None, len(chars)), init=INITIALIZATION,
                                 return_sequences=layer_number + 1 < INPUT_LAYERS))
        model.add(Dropout(AMOUNT_OF_DROPOUT))
    # For the decoder's input, we repeat the encoded input for each time step
    model.add(RepeatVector(output_len))
    # The decoder RNN could be multiple layers stacked or a single layer
    for _ in range(OUTPUT_LAYERS):
        model.add(recurrent.LSTM(HIDDEN_SIZE, return_sequences=True, init=INITIALIZATION))
        model.add(Dropout(AMOUNT_OF_DROPOUT))

    # For each of step of the output sequence, decide which character should be chosen
    model.add(TimeDistributed(Dense(len(chars), init=INITIALIZATION)))
    model.add(Activation('softmax'))

    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model