Transformer

def shift_left_3d(x, pad_value=None):
  """Shift the second dimension of x right by one."""
  if pad_value is None:
    shifted_targets = tf.pad(x, [[0, 0], [1, 0], [0, 0]])[:, :-1, :]
  else:
    shifted_targets = tf.concat([pad_value, x], axis=1)[:, :-1, :]
  return shifted_targets

def transformer_prepare_decoder(targets, hparams):
  """Prepare one shard of the model for the decoder.

  Args:
    targets: a Tensor.
    hparams: run hyperparameters

  Returns:
    decoder_input: a Tensor, bottom of decoder stack
    decoder_self_attention_bias: a Tensor, containing large negative values
    to implement masked attention and possibly baises for diagonal alignments
  """
  decoder_self_attention_bias = (
      common_attention.attention_bias_lower_triangle(tf.shape(targets)[1]))
  decoder_input = common_layers.shift_left_3d(targets)
  if hparams.pos == "timing":
    decoder_input = common_attention.add_timing_signal_1d(decoder_input)
  return (decoder_input, decoder_self_attention_bias)

  def bottom_simple(self, x, name, reuse):
    with tf.variable_scope(name, reuse=reuse):
      # Squeeze out the channels dimension.
      x = tf.squeeze(x, axis=3)
      var = self._get_weights()
      ret = tf.gather(var, x)
      if self._model_hparams.multiply_embedding_mode == "sqrt_depth":
        ret *= self._body_input_depth**0.5
      ret *= tf.expand_dims(tf.to_float(tf.not_equal(x, 0)), -1)
      return ret

  def bottom(self, x):
    if self._model_hparams.shared_embedding_and_softmax_weights:
      return self.bottom_simple(x, "shared", reuse=None)
    else:
      return self.bottom_simple(x, "input_emb", reuse=None)

  def targets_bottom(self, x):
    if self._model_hparams.shared_embedding_and_softmax_weights:
      return self.bottom_simple(x, "shared", reuse=True)
    else:
      return self.bottom_simple(x, "target_emb", reuse=None)

  def _get_weights(self):
    """Create or get concatenated embedding or softmax variable.

    Returns:
       a list of self._num_shards Tensors.
    """
    num_shards = self._model_hparams.symbol_modality_num_shards
    shards = []
    for i in xrange(num_shards):
      shard_size = (self._vocab_size // num_shards) + (
          1 if i < self._vocab_size % num_shards else 0)
      var_name = "weights_%d" % i
      shards.append(
          tf.get_variable(
              var_name, [shard_size, self._body_input_depth],
              initializer=tf.random_normal_initializer(
                  0.0, self._body_input_depth**-0.5)))
    if num_shards == 1:
      ret = shards[0]
    else:
      ret = tf.concat(shards, 0)
    ret = eu.ConvertGradientToTensor(ret)
    return ret

      multiply_embedding_mode="sqrt_depth",
      norm_type="none",  # "batch", layer", "noam", "none".
      layer_norm_epsilon=1e-6,
      symbol_modality_num_shards=16,