Question

我试图了解注意力模型，并自己建立一个。经过多次搜索，我遇到了this website，它有一个用keras编码的衰减模型，看起来也很简单。但是，当我尝试在自己的机器上构建相同的模型时，会出现多个参数错误。该错误是由于在类Attention中传递了不匹配的参数所致。在网站的关注类中，它要求一个参数，但它会使用两个参数来启动关注对象。

import tensorflow as tf

max_len = 200
rnn_cell_size = 128
vocab_size=250

class Attention(tf.keras.Model):
    def __init__(self, units):
        super(Attention, self).__init__()
        self.W1 = tf.keras.layers.Dense(units)
        self.W2 = tf.keras.layers.Dense(units)
        self.V = tf.keras.layers.Dense(1)
    def call(self, features, hidden):
        hidden_with_time_axis = tf.expand_dims(hidden, 1)
        score = tf.nn.tanh(self.W1(features) + self.W2(hidden_with_time_axis))
        attention_weights = tf.nn.softmax(self.V(score), axis=1)
        context_vector = attention_weights * features
        context_vector = tf.reduce_sum(context_vector, axis=1)
        return context_vector, attention_weights

sequence_input = tf.keras.layers.Input(shape=(max_len,), dtype='int32')

embedded_sequences = tf.keras.layers.Embedding(vocab_size, 128, input_length=max_len)(sequence_input)

lstm = tf.keras.layers.Bidirectional(tf.keras.layers.LSTM
                                     (rnn_cell_size,
                                      dropout=0.3,
                                      return_sequences=True,
                                      return_state=True,
                                      recurrent_activation='relu',
                                      recurrent_initializer='glorot_uniform'), name="bi_lstm_0")(embedded_sequences)

lstm, forward_h, forward_c, backward_h, backward_c = tf.keras.layers.Bidirectional \
    (tf.keras.layers.LSTM
     (rnn_cell_size,
      dropout=0.2,
      return_sequences=True,
      return_state=True,
      recurrent_activation='relu',
      recurrent_initializer='glorot_uniform'))(lstm)

state_h = tf.keras.layers.Concatenate()([forward_h, backward_h])
state_c = tf.keras.layers.Concatenate()([forward_c, backward_c])

#  PROBLEM IN THIS LINE
context_vector, attention_weights = Attention(lstm, state_h)

output = keras.layers.Dense(1, activation='sigmoid')(context_vector)

model = keras.Model(inputs=sequence_input, outputs=output)

# summarize layers
print(model.summary())

如何使该模型正常工作？

Answer 1

注意层现在是Tensorflow（2.1）的Keras API的一部分。但是它输出的张量与“查询”张量相同。

这是使用Luong风格的注意力的方法：

query_attention = tf.keras.layers.Attention()([query, value])

还有Bahdanau风格的关注：

query_attention = tf.keras.layers.AdditiveAttention()([query, value])

改编版本：

attention_weights = tf.keras.layers.Attention()([lstm, state_h])

请访问原始网站以获取更多信息：https://www.tensorflow.org/api_docs/python/tf/keras/layers/Attention https://www.tensorflow.org/api_docs/python/tf/keras/layers/AdditiveAttention

Answer 2

初始化attention layer和传递参数的方式存在问题。您应该在该位置指定attention layer单位的数量，并修改参数的传递方式：

context_vector, attention_weights = Attention(32)(lstm, state_h)

结果：

__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_1 (InputLayer)            (None, 200)          0                                            
__________________________________________________________________________________________________
embedding (Embedding)           (None, 200, 128)     32000       input_1[0][0]                    
__________________________________________________________________________________________________
bi_lstm_0 (Bidirectional)       [(None, 200, 256), ( 263168      embedding[0][0]                  
__________________________________________________________________________________________________
bidirectional (Bidirectional)   [(None, 200, 256), ( 394240      bi_lstm_0[0][0]                  
                                                                 bi_lstm_0[0][1]                  
                                                                 bi_lstm_0[0][2]                  
                                                                 bi_lstm_0[0][3]                  
                                                                 bi_lstm_0[0][4]                  
__________________________________________________________________________________________________
concatenate (Concatenate)       (None, 256)          0           bidirectional[0][1]              
                                                                 bidirectional[0][3]              
__________________________________________________________________________________________________
attention (Attention)           [(None, 256), (None, 16481       bidirectional[0][0]              
                                                                 concatenate[0][0]                
__________________________________________________________________________________________________
dense_3 (Dense)                 (None, 1)            257         attention[0][0]                  
==================================================================================================
Total params: 706,146
Trainable params: 706,146
Non-trainable params: 0
__________________________________________________________________________________________________
None

Answer 3

为回答Arman的特定查询-这些库使用2018年后的查询，值和键的语义。要将语义映射回Bahdanau或Luong的论文，可以将“查询”视为最后一个解码器隐藏状态。 “值”将是编码器输出的集合-编码器的所有隐藏状态。 “查询”“参与”所有“值”。

无论使用哪种版本的代码或库，请始终注意，“查询”将在时间轴上展开，以为随后的后续添加做准备。该值（正在扩展）将始终是RNN的最后一个隐藏状态。另一个值将始终是需要注意的值-编码器端的所有隐藏状态。可以通过对代码的这种简单检查来确定映射到哪个“查询”和“值”，而与所使用的库或代码无关。

您可以参考https://towardsdatascience.com/create-your-own-custom-attention-layer-understand-all-flavours-2201b5e8be9e以少于6行的代码编写自己的自定义注意层

如何用keras建立注意力模型？

3 个答案: