4ce9a9d078d41af1a960f0e5bf16e373f69d5117,open_seq2seq/encoders/rnn_encoders.py,BidirectionalRNNEncoderWithEmbedding,_encode,#BidirectionalRNNEncoderWithEmbedding#Any#,204

Before Change

      dtype=tf.float32
    )

    cell_params = copy.deepcopy(self.params)
    cell_params["num_units"] = self.params["encoder_cell_units"]

    if self._mode == "train":
      dp_input_keep_prob = self.params["encoder_dp_input_keep_prob"]
      dp_output_keep_prob = self.params["encoder_dp_output_keep_prob"]

After Change

                  dp_output_keep_prob=dp_output_keep_prob,
                  residual_connections=self.params["encoder_use_skip_connections"]
                  ) for _ in range(self.params["encoder_layers"])]
    bwd_cells = [
      single_cell(cell_class=self.params["core_cell"],
                  cell_params=self.params.get("core_cell_params", {}),
                  dp_input_keep_prob=dp_input_keep_prob,
                  dp_output_keep_prob=dp_output_keep_prob,
                  residual_connections=self.params["encoder_use_skip_connections"]
                  ) for _ in range(self.params["encoder_layers"])]


    with tf.variable_scope("FW"):
      self._encoder_cell_fw = tf.contrib.rnn.MultiRNNCell(fwd_cells)

    with tf.variable_scope("BW"):
      self._encoder_cell_bw = tf.contrib.rnn.MultiRNNCell(bwd_cells)

    embedded_inputs = tf.cast(tf.nn.embedding_lookup(
      self.enc_emb_w,
      source_sequence,

Instances