Tensorflow在构建RNN层时通过使用参数'sequence_length'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。
但是，如何修改https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/ops/seq2seq.py#L890中的cost函数以遇到被屏蔽的序列，从而计算出cost和困惑度仅在实际序列上，而不是整个填充序列上？
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
该功能已经支持通过使用权重来计算动态序列长度的成本。只要确保“填充目标”的权重为0，这些步骤的交叉熵将被推为0：
log_perp_list.append(crossent * weight)
并且总大小也将仅反映非填充步骤：
total_size = math_ops.add_n(weights)
如果使用零填充，则导出权重的一种方法如下：
weights = tf.sign(tf.abs(model.targets))
（请注意，您可能需要将此类型转换为与目标相同的类型）
本文收集自互联网，转载请注明来源。
如有侵权，请联系[email protected] 删除。
我来说两句