1

我正在尝试在这段代码中测试注意力机制（基于 MajorTal 的工作）：

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(CONFIG.input_layers):
        model.add(LSTM(CONFIG.hidden_size, kernel_initializer=CONFIG.initialization,
                                 return_sequences=layer_number + 1 < CONFIG.input_layers, input_shape=(None, len(chars))))
        model.add(Dropout(CONFIG.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(CONFIG.output_layers):
        model.add(LSTM(CONFIG.hidden_size, return_sequences=True, kernel_initializer=CONFIG.initialization))
        model.add(Dropout(CONFIG.amount_of_dropout))

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

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

有人可以告诉我如何用注意力机制替换这个实现的解码器吗？提前致谢。

4

0 回答 0