Question

我正在尝试使用Tensorflow中的seq2seq.dynamic_decode来构建序列模型。我已经完成了编码器部分。我对解码器感到困惑，因为[batch_size x sequence_length x embedding_size]似乎返回[batch_size x sequence_length]，但我需要实际的单词索引来正确计算我的损失rnn.BasicLSTMCell()。我想知道我的一个形状输入是不正确的还是我忘记了什么解码器和编码器单元为# 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)。

function woocommerce_quantity_input($data) {
    global $product;
  $defaults = array(
    'input_name'    => $data['input_name'],
    'input_value'   => $data['input_value'],
    'max_value'   => apply_filters( 'woocommerce_quantity_input_max', '', $product ),
    'min_value'   => apply_filters( 'woocommerce_quantity_input_min', '', $product ),
    'step'    => apply_filters( 'woocommerce_quantity_input_step', '1', $product ),
    'style'   => apply_filters( 'woocommerce_quantity_style', 'float:left; margin-right:10px;', $product )
  );
  if ( ! empty( $defaults['min_value'] ) )
    $min = $defaults['min_value'];
  else $min = 1;
  if ( ! empty( $defaults['max_value'] ) )
    $max = $defaults['max_value'];
  else $max = 20;
  if ( ! empty( $defaults['step'] ) )
    $step = $defaults['step'];
  else $step = 1;
  $options = '';
  for ( $count = $min; $count <= $max; $count = $count+$step ) {
    $selected = $count === $defaults['input_value'] ? ' selected' : '';
    $options .= '<option value="' . $count . '"'.$selected.'>' . $count . '</option>';
  }
  echo '<div class="quantity_select" style="' . $defaults['style'] . '"><select name="' . esc_attr( $defaults['input_name'] ) . '" title="' . _x( 'Qty', 'Product quantity input tooltip', 'woocommerce' ) . '" class="qty">' . $options . '</select></div>';
}

Answer 1

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图层，以便从cell_size投射到词汇量大小。

如何使用Tensorflow v1.1 seq2seq.dynamic_decode？

1 个答案: