python之如何使用 Tensorflow v1.1 seq2seq.dynamic_decode

我正在尝试使用 seq2seq.dynamic_decode从 Tensorflow 构建序列到序列模型。我已经完成了编码器部分。 我对解码器感到困惑，因为 decoder_outputs 似乎返回 [batch_size x sequence_length x embedding_size] 但我需要实际的单词索引来正确计算我的损失 [batch_size x sequence_length]。 我想知道我输入的某个形状是否不正确，或者我只是忘记了什么。
解码器和编码器单元是 rnn.BasicLSTMCell()。

# Variables 
cell_size = 100 
decoder_vocabulary_size = 7 
batch_size = 2 
decoder_max_sentence_len = 7 
# Part of the encoder 
_, encoder_state = tf.nn.dynamic_rnn( 
          cell=encoder_cell, 
          inputs=features, 
          sequence_length=encoder_sequence_lengths, 
          dtype=tf.float32) 
# ---- END Encoder ---- # 
# ---- Decoder ---- # 
# decoder_sequence_lengths = _sequence_length(features) 
embedding = tf.get_variable( 
     "decoder_embedding", [decoder_vocabulary_size, cell_size]) 
helper = seq2seq.GreedyEmbeddingHelper( 
     embedding=embedding, 
     start_tokens=tf.tile([GO_SYMBOL], [batch_size]), 
     end_token=END_SYMBOL) 
decoder = seq2seq.BasicDecoder( 
     cell=decoder_cell, 
     helper=helper, 
     initial_state=encoder_state) 
decoder_outputs, _ = seq2seq.dynamic_decode( 
     decoder=decoder, 
     output_time_major=False, 
     impute_finished=True, 
     maximum_iterations=self.decoder_max_sentence_len) 
# I need labels (decoder_outputs) to be indices 
losses = nn_ops.sparse_softmax_cross_entropy_with_logits( 
        labels=labels, logits=logits) 
loss = tf.reduce_mean(losses) 

请您参考如下方法:

我发现解决方案是:

from tensorflow.python.layers.core import Dense 
decoder = seq2seq.BasicDecoder( 
      cell=decoder_cell, 
      helper=helper, 
      initial_state=encoder_state, 
      output_layer=Dense(decoder_vocabulary_size)) 
... 
logits = decoder_outputs[0] 

您必须指定一个 Dense 层以从 cell_size 投影到词汇表大小。