Keras RNN +编码器/解码器+注意中的图断开推理

时间:2019-03-14 02:11:35

标签: keras recurrent-neural-network inference attention-model encoder-decoder

我已成功使用以下示例,使用编码器/解码器结构+注意+手套在Keras中训练了一个模型,其中最著名的是this onethis one。它基于对机器翻译的修改。这是一个聊天机器人,所以输入是单词,输出也是。但是,我一直在努力正确地设置推理(预测),无法弄清楚如何克服图断开。我的嵌入式RNN双向编码器/解码器训练得很好。我尝试过修改解码器,但感觉到我看不到明显的东西。

这是基本模型:

from keras.models import Model
from keras.layers.recurrent import LSTM
from keras.layers import Dense, Input, Embedding, Bidirectional, RepeatVector, concatenate, Concatenate

## PARAMETERS
HIDDEN_UNITS = 100
encoder_max_seq_length = 1037 # maximum size of input sequence
decoder_max_seq_length = 187 # maximum size of output sequence
num_encoder_tokens = 6502 # a.k.a the size of the input vocabulary
num_decoder_tokens = 4802 # a.k.a the size of the output vocabulary

## ENCODER
encoder_inputs = Input(shape=(encoder_max_seq_length, ), name='encoder_inputs')
encoder_embedding = Embedding(input_dim = num_encoder_tokens, 
                              output_dim = HIDDEN_UNITS,
                              input_length = encoder_max_seq_length,
                              weights = [embedding_matrix],
                              name='encoder_embedding')(encoder_inputs)

encoder_lstm = Bidirectional(LSTM(units = HIDDEN_UNITS,
                                  return_sequences=True,
                                  name='encoder_lstm'))(encoder_embedding)
## ATTENTION
attention = AttentionL(encoder_max_seq_length)(encoder_lstm)
attention = RepeatVector(decoder_max_seq_length)(attention)

## DECODER
decoder_inputs = Input(shape = (decoder_max_seq_length, num_decoder_tokens),
                       name='decoder_inputs')

merge = concatenate([attention, decoder_inputs])

decoder_lstm = Bidirectional(LSTM(units = HIDDEN_UNITS*2,
                    return_sequences = True,
                    name='decoder_lstm'))(merge)

decoder_dense = Dense(units=num_decoder_tokens, 
                      activation='softmax', 
                      name='decoder_dense')(decoder_lstm)

decoder_outputs = decoder_dense

## Configure the model
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)
model.load_weights('trained_models/viable-2/word-weights.h5')
encoder_model = Model(encoder_inputs, attention)
model.compile(loss='categorical_crossentropy', optimizer='adam')

它看起来像这样: enter image description here

这是我遇到麻烦的地方:

## INFERENCE decoder setup
decoder_inputs_2 = Concatenate()([decoder_inputs, attention])
decoder_lstm = Bidirectional(LSTM(units=HIDDEN_UNITS*2, return_state = True, name='decoder_lstm'))
decoder_outputs, forward_h, forward_c, backward_h, backward_c= decoder_lstm(decoder_inputs_2)
state_h = Concatenate()([forward_h, backward_h])
state_c = Concatenate()([forward_c, backward_c])
decoder_states = [state_h, state_c]
decoder_dense = Dense(units=num_decoder_tokens, activation='softmax', name='decoder_dense')
decoder_outputs = decoder_dense(decoder_outputs)

decoder_model = Model([decoder_inputs, attention], [decoder_outputs] + decoder_states)

这会产生图形断开错误:图形断开:无法在“ encoder_inputs”层获得张量Tensor(“ encoder_inputs_61:0”,shape =(?, 1037),dtype = float32)的值。可以顺利访问以下先前的图层:[]

应该可以进行推断like this,但我无法克服这个错误。对于我来说,不可能简单地将解码器输出和注意力加在一起,因为它们的形状不同。

0 个答案:

没有答案