Question

Tensorflow在构造RNN层时通过使用参数：'sequence_length'来支持动态长度序列，其中模型在序列大小='sequence_length'之后不学习序列，即返回零向量。

然而，如何修改https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/ops/seq2seq.py#L890处的成本函数以遇到屏蔽序列，从而仅根据实际序列而不是整个填充序列计算成本和困惑？

def sequence_loss_by_example(logits, targets, weights, average_across_timesteps=True,  softmax_loss_function=None, name=None):

    if len(targets) != len(logits) or len(weights) != len(logits):
        raise ValueError("Lengths of logits, weights, and targets must be the same "
                         "%d, %d, %d." % (len(logits), len(weights), len(targets)))
      with ops.op_scope(logits + targets + weights, name,
                        "sequence_loss_by_example"):
        log_perp_list = []
        for logit, target, weight in zip(logits, targets, weights):
          if softmax_loss_function is None:
            # TODO(irving,ebrevdo): This reshape is needed because
            # sequence_loss_by_example is called with scalars sometimes, which
            # violates our general scalar strictness policy.
            target = array_ops.reshape(target, [-1])
            crossent = nn_ops.sparse_softmax_cross_entropy_with_logits(
                logit, target)
          else:
            crossent = softmax_loss_function(logit, target)
          log_perp_list.append(crossent * weight)
        log_perps = math_ops.add_n(log_perp_list)
        if average_across_timesteps:
          total_size = math_ops.add_n(weights)
          total_size += 1e-12  # Just to avoid division by 0 for all-0 weights.
          log_perps /= total_size
    return log_perps

Answer 1

此功能已支持通过使用权重计算动态序列长度的成本。只要你确保“填充目标”的权重为0，那么对于这些步骤，交叉熵将被推到0：

log_perp_list.append(crossent * weight)

，总大小也只反映非填充步骤：

total_size = math_ops.add_n(weights)

如果你用零填充，推导权重的一种方法如下：

weights = tf.sign(tf.abs(model.targets))

（请注意，您可能需要将其转换为与目标相同的类型）

如何修改填充向量的seq2seq成本函数？

1 个答案: