def sequence_loss_by_batch(logits, targets, weights, average_across_timesteps=True,
softmax_loss_function=None, name=None):
"""Weighted cross-entropy loss for a sequence of logits, batch-collapsed (averaged).
Args:
logits: List of 2D Tensors of shape [batch_size x num_decoder_symbols].
targets: List of 1D batch-sized int32 Tensors of the same length as logits.
weights: List of 1D batch-sized float-Tensors of the same length as logits.
average_across_timesteps: If set, divide the returned cost by the total
label weight.
average_across_batch: If set, divide the returned cost by the batch size.
softmax_loss_function: Function (inputs-batch, labels-batch) -> loss-batch
to be used instead of the standard softmax (the default if this is None).
name: Optional name for this operation, defaults to "sequence_loss".
Returns:
A scalar float Tensor: The average log-perplexity per symbol (weighted).
Raises:
ValueError: If len(logits) is different from len(targets) or len(weights).
"""
with ops.op_scope(logits + targets + weights, name, "sequence_loss_by_batch"):
cost = math_ops.reduce_sum(sequence_loss_by_example(
logits, targets, weights,
average_across_timesteps=average_across_timesteps,
softmax_loss_function=softmax_loss_function))
batch_size = array_ops.shape(targets[0])[0]
return cost / math_ops.cast(batch_size, dtypes.float32)
评论列表
文章目录
