Method get_batch

chatbotv4/seq2seq_model.py:259–317

Get a random batch of data from the specified bucket, prepare for step. To feed data in step(..) it must be a list of batch-major vectors, while data here contains single length-major cases. So the main logic of this function is to re-index data cases to be in the proper format for feed

(self, data, bucket_id)

      return None, outputs[0], outputs[1:]  # No gradient norm, loss, outputs.

  def get_batch(self, data, bucket_id):
    """Get a random batch of data from the specified bucket, prepare for step.

    To feed data in step(..) it must be a list of batch-major vectors, while
    data here contains single length-major cases. So the main logic of this
    function is to re-index data cases to be in the proper format for feeding.

    Args:
      data: a tuple of size len(self.buckets) in which each element contains
        lists of pairs of input and output data that we use to create a batch.
      bucket_id: integer, which bucket to get the batch for.

    Returns:
      The triple (encoder_inputs, decoder_inputs, target_weights) for
      the constructed batch that has the proper format to call step(...) later.
    """
    encoder_size, decoder_size = self.buckets[bucket_id]
    encoder_inputs, decoder_inputs = [], []

    # Get a random batch of encoder and decoder inputs from data,
    # pad them if needed, reverse encoder inputs and add GO to decoder.
    for _ in xrange(self.batch_size):
      encoder_input, decoder_input = random.choice(data[bucket_id])

      # Encoder inputs are padded and then reversed.
      encoder_pad = [data_utils.PAD_ID] * (encoder_size - len(encoder_input))
      encoder_inputs.append(list(reversed(encoder_input + encoder_pad)))

      # Decoder inputs get an extra "GO" symbol, and are padded then.
      decoder_pad_size = decoder_size - len(decoder_input) - 1
      decoder_inputs.append([data_utils.GO_ID] + decoder_input +
                            [data_utils.PAD_ID] * decoder_pad_size)

    # Now we create batch-major vectors from the data selected above.
    batch_encoder_inputs, batch_decoder_inputs, batch_weights = [], [], []

    # Batch encoder inputs are just re-indexed encoder_inputs.
    for length_idx in xrange(encoder_size):
      batch_encoder_inputs.append(
          np.array([encoder_inputs[batch_idx][length_idx]
                    for batch_idx in xrange(self.batch_size)], dtype=np.int32))

    # Batch decoder inputs are re-indexed decoder_inputs, we create weights.
    for length_idx in xrange(decoder_size):
      batch_decoder_inputs.append(
          np.array([decoder_inputs[batch_idx][length_idx]
                    for batch_idx in xrange(self.batch_size)], dtype=np.int32))

      # Create target_weights to be 0 for targets that are padding.
      batch_weight = np.ones(self.batch_size, dtype=np.float32)
      for batch_idx in xrange(self.batch_size):
        # We set weight to 0 if the corresponding target is a PAD symbol.
        # The corresponding target is decoder_input shifted by 1 forward.
        if length_idx < decoder_size - 1:
          target = decoder_inputs[batch_idx][length_idx + 1]
        if length_idx == decoder_size - 1 or target == data_utils.PAD_ID:
          batch_weight[batch_idx] = 0.0
      batch_weights.append(batch_weight)