我想创建一个由嵌入层组成的Keras模型，然后是两个带有dropout 0.5的LSTM，最后是一个带有softmax激活的密集层 .
第一个LSTM应该将顺序输出传播到第二层，而在第二个层中，我只对处理整个序列后获取LSTM的隐藏状态感兴趣 .
我尝试了以下方法：
sentence_indices = Input(input_shape, dtype = 'int32')
embedding_layer = pretrained_embedding_layer(word_to_vec_map, word_to_index)
embeddings = embedding_layer(sentence_indices)
# Propagate the embeddings through an LSTM layer with 128-dimensional hidden state
X = LSTM(128, return_sequences=True, dropout = 0.5)(embeddings)
# Propagate X trough another LSTM layer with 128-dimensional hidden state
X = LSTM(128, return_sequences=False, return_state=True, dropout = 0.5)(X)
# Propagate X through a Dense layer with softmax activation to get back a batch of 5-dimensional vectors.
X = Dense(5, activation='softmax')(X)
# Create Model instance which converts sentence_indices into X.
model = Model(inputs=[sentence_indices], outputs=[X])
但是我收到以下错误：
ValueError: Layer dense_5 expects 1 inputs, but it received 3 input tensors. Input received: [<tf.Tensor 'lstm_10/TensorArrayReadV3:0' shape=(?, 128) dtype=float32>, <tf.Tensor 'lstm_10/while/Exit_2:0' shape=(?, 128) dtype=float32>, <tf.Tensor 'lstm_10/while/Exit_3:0' shape=(?, 128) dtype=float32>]
很明显，LSTM没有返回我期望的形状的输出 . 我该如何解决？
1 回答
如果设置
return_state=True，则LSTM(...)(X)将返回三个内容：输出，最后隐藏状态和最后一个单元状态 .所以不是
X = LSTM(128, return_sequences=False, return_state=True, dropout = 0.5)(X)，而是X, h, c = LSTM(128, return_sequences=False, return_state=True, dropout = 0.5)(X)有关示例，请参阅here .