通过了与initial_state`不兼容的Keras双向LSTM：`cell.state_size
通过了与initial_state`不兼容的Keras双向LSTM：`cell.state_size
提问于 2019-07-24 20:28:20
我试图在Keras中构建一个堆叠的双向LSTM seq2seq模型，但是当将编码器的输出状态传递给解码器的输入状态时，我遇到了一个问题。基于这个拉请求，这看起来应该是可能的。最终，我希望保留encoder_output向量，用于其他下游任务。
错误信息：
ValueError: An `initial_state` was passed that is not compatible with `cell.state_size`. Received `state_spec`=[InputSpec(shape=(None, 100), ndim=2)]; however `cell.state_size` is (100, 100)我的模特：
MAX_SEQUENCE_LENGTH = 50
EMBEDDING_DIM = 250
latent_size_1 = 100
latent_size_2 = 50
latent_size_3 = 250
embedding_layer = Embedding(num_words,
EMBEDDING_DIM,
embeddings_initializer=Constant(embedding_matrix),
input_length=MAX_SEQUENCE_LENGTH,
trainable=False,
mask_zero=True)
encoder_inputs = Input(shape=(MAX_SEQUENCE_LENGTH,), name="encoder_input")
encoder_emb = embedding_layer(encoder_inputs)
encoder_lstm_1 = Bidirectional(LSTM(latent_size_1, return_sequences=True),
merge_mode="concat",
name="encoder_lstm_1")(encoder_emb)
encoder_outputs, forward_h, forward_c, backward_h, backward_c = Bidirectional(LSTM(latent_size_2, return_state=True),
merge_mode="concat"
name="encoder_lstm_2")(encoder_lstm_1)
state_h = Concatenate()([forward_h, backward_h])
state_c = Concatenate()([forward_c, backward_c])
encoder_states = [state_h, state_c]
decoder_inputs = Input(shape=(MAX_SEQUENCE_LENGTH,), name="decoder_input")
decoder_emb = embedding_layer(decoder_inputs)
decoder_lstm_1 = Bidirectional(LSTM(latent_size_1, return_sequences=True),
merge_mode="concat",
name="decoder_lstm_1")(decoder_emb, initial_state=encoder_states)
decoder_lstm_2 = Bidirectional(LSTM(latent_size_3, return_sequences=True),
merge_mode="concat",
name="decoder_lstm_2")(decoder_lstm_1)
decoder_outputs = Dense(num_words, activation='softmax', name="Dense_layer")(decoder_lstm_2)
seq2seq_Model = Model([encoder_inputs, decoder_inputs], decoder_outputs)非常感谢您的任何帮助/建议/指导！
回答 1
Stack Overflow用户
回答已采纳
发布于 2019-07-24 23:21:54
你的代码有两个问题，
- 正如@Daniel所指出的，您不应该连接
encoder_states中的状态(而应该使用encoder_states = [forward_h, forward_c, backward_h, backward_c])。 - 编码器返回的状态是大小为
latent_size_2(而不是latent_size_1)。因此，如果您希望这样做，作为您的解码器初始状态，您的解码器应该是latent_size_2。
您可以在下面找到带有这些更正的代码。
from tensorflow.keras.layers import Embedding, Input, Bidirectional, LSTM, Dense, Concatenate
from tensorflow.keras.initializers import Constant
from tensorflow.keras.models import Model
MAX_SEQUENCE_LENGTH = 50
EMBEDDING_DIM = 250
latent_size_1 = 100
latent_size_2 = 50
latent_size_3 = 250
num_words = 5000
embedding_layer = Embedding(num_words,
EMBEDDING_DIM,
embeddings_initializer=Constant(1.0),
input_length=MAX_SEQUENCE_LENGTH,
trainable=False,
mask_zero=True)
encoder_inputs = Input(shape=(MAX_SEQUENCE_LENGTH,), name="encoder_input")
encoder_emb = embedding_layer(encoder_inputs)
encoder_lstm_1 = Bidirectional(LSTM(latent_size_1, return_sequences=True),
merge_mode="concat",
name="encoder_lstm_1")(encoder_emb)
encoder_outputs, forward_h, forward_c, backward_h, backward_c = Bidirectional(LSTM(latent_size_2, return_state=True),
merge_mode="concat", name="encoder_lstm_2")(encoder_lstm_1)
encoder_states = [forward_h, forward_c, backward_h, backward_c]
decoder_inputs = Input(shape=(MAX_SEQUENCE_LENGTH,), name="decoder_input")
decoder_emb = embedding_layer(decoder_inputs)
decoder_lstm_1 = Bidirectional(
LSTM(latent_size_2, return_sequences=True),
merge_mode="concat", name="decoder_lstm_1")(decoder_emb, initial_state=encoder_states)
decoder_lstm_2 = Bidirectional(LSTM(latent_size_3, return_sequences=True),
merge_mode="concat",
name="decoder_lstm_2")(decoder_lstm_1)
decoder_outputs = Dense(num_words, activation='softmax', name="Dense_layer")(decoder_lstm_2)
seq2seq_Model = Model([encoder_inputs, decoder_inputs], decoder_outputs)页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/57190769
复制相关文章
相似问题
腾讯云开发者
