tensorflow学习笔记（二十四）：Bucketing

def model_with_buckets(encoder_inputs,
                       decoder_inputs,
                       targets,
                       weights,
                       buckets,
                       seq2seq,
                       softmax_loss_function=None,
                       per_example_loss=False,
                       name=None):
  """Create a sequence-to-sequence model with support for bucketing.
  The seq2seq argument is a function that defines a sequence-to-sequence model,
  e.g., seq2seq = lambda x, y: basic_rnn_seq2seq(x, y, rnn_cell.GRUCell(24))
  Args:
    encoder_inputs: A list of Tensors to feed the encoder; first seq2seq input.
    decoder_inputs: A list of Tensors to feed the decoder; second seq2seq input.
    targets: A list of 1D batch-sized int32 Tensors (desired output sequence).
    weights: List of 1D batch-sized float-Tensors to weight the targets.
    buckets: A list of pairs of (input size, output size) for each bucket.
    seq2seq: A sequence-to-sequence model function; it takes 2 input that
      agree with encoder_inputs and decoder_inputs, and returns a pair
      consisting of outputs and states (as, e.g., basic_rnn_seq2seq).
    softmax_loss_function: Function (inputs-batch, labels-batch) -> loss-batch
      to be used instead of the standard softmax (the default if this is None).
    per_example_loss: Boolean. If set, the returned loss will be a batch-sized
      tensor of losses for each sequence in the batch. If unset, it will be
      a scalar with the averaged loss from all examples.
    name: Optional name for this operation, defaults to "model_with_buckets".
  Returns:
    A tuple of the form (outputs, losses), where:
      outputs: The outputs for each bucket. Its j'th element consists of a list
        of 2D Tensors. The shape of output tensors can be either
        [batch_size x output_size] or [batch_size x num_decoder_symbols]
        depending on the seq2seq model used.
      losses: List of scalar Tensors, representing losses for each bucket, or,
        if per_example_loss is set, a list of 1D batch-sized float Tensors.
  Raises:
    ValueError: If length of encoder_inputsut, targets, or weights is smaller
      than the largest (last) bucket.
  """
  if len(encoder_inputs) < buckets[-1][0]:
    raise ValueError("Length of encoder_inputs (%d) must be at least that of la"
                     "st bucket (%d)." % (len(encoder_inputs), buckets[-1][0]))
  if len(targets) < buckets[-1][1]:
    raise ValueError("Length of targets (%d) must be at least that of last"
                     "bucket (%d)." % (len(targets), buckets[-1][1]))
  if len(weights) < buckets[-1][1]:
    raise ValueError("Length of weights (%d) must be at least that of last"
                     "bucket (%d)." % (len(weights), buckets[-1][1]))

  all_inputs = encoder_inputs + decoder_inputs + targets + weights
  losses = []
  outputs = []
  with ops.name_scope(name, "model_with_buckets", all_inputs):
    for j, bucket in enumerate(buckets):
      with variable_scope.variable_scope(
          variable_scope.get_variable_scope(), reuse=True if j > 0 else None):
        bucket_outputs, _ = seq2seq(encoder_inputs[:bucket[0]],
                                    decoder_inputs[:bucket[1]])
        outputs.append(bucket_outputs)
        if per_example_loss:
          losses.append(
              sequence_loss_by_example(
                  outputs[-1],
                  targets[:bucket[1]],
                  weights[:bucket[1]],
                  softmax_loss_function=softmax_loss_function))
        else:
          losses.append(
              sequence_loss(
                  outputs[-1],
                  targets[:bucket[1]],
                  weights[:bucket[1]],
                  softmax_loss_function=softmax_loss_function))

  return outputs, losses

if len(encoder_inputs) < buckets[-1][0]:
  raise ValueError("Length of encoder_inputs (%d) must be at least that of la"
                   "st bucket (%d)." % (len(encoder_inputs), buckets[-1][0]))
if len(targets) < buckets[-1][1]:
  raise ValueError("Length of targets (%d) must be at least that of last"
                   "bucket (%d)." % (len(targets), buckets[-1][1]))
if len(weights) < buckets[-1][1]:
  raise ValueError("Length of weights (%d) must be at least that of last"
                   "bucket (%d)." % (len(weights), buckets[-1][1]))
#可以看出，输入数据必须填充为最大长度

for j, bucket in enumerate(buckets):#对每个bucket创建一个模型
  with variable_scope.variable_scope(
      variable_scope.get_variable_scope(), reuse=True if j > 0 else None):
    bucket_outputs, _ = seq2seq(encoder_inputs[:bucket[0]],
                                decoder_inputs[:bucket[1]])
    outputs.append(bucket_outputs)
    if per_example_loss:
      losses.append(
          sequence_loss_by_example(
              outputs[-1],
              targets[:bucket[1]],
              weights[:bucket[1]],
              softmax_loss_function=softmax_loss_function))
    else:#所有模型的loss都被保存起来
      losses.append(
          sequence_loss(
              outputs[-1],
              targets[:bucket[1]],
              weights[:bucket[1]],
              softmax_loss_function=softmax_loss_function))