本文整理匯總了Python中tensor2tensor.layers.common_attention.get_layer_timing_signal_learned_1d方法的典型用法代碼示例。如果您正苦於以下問題：Python common_attention.get_layer_timing_signal_learned_1d方法的具體用法？Python common_attention.get_layer_timing_signal_learned_1d怎麽用？Python common_attention.get_layer_timing_signal_learned_1d使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類tensor2tensor.layers.common_attention的用法示例。
在下文中一共展示了common_attention.get_layer_timing_signal_learned_1d方法的2個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: add_step_timing_signal
# 需要導入模塊: from tensor2tensor.layers import common_attention [as 別名]
# 或者: from tensor2tensor.layers.common_attention import get_layer_timing_signal_learned_1d [as 別名]
def add_step_timing_signal(x, step, hparams):
"""Add n-dimensional embedding as the step (vertical) timing signal.
Args:
x: a tensor with shape [batch, length, depth]
step: step
hparams: model hyper parameters
Returns:
a Tensor with the same shape as x.
"""
num_steps = (
hparams.act_max_steps
if hparams.recurrence_type == "act" else hparams.num_rec_steps)
channels = common_layers.shape_list(x)[-1]
if hparams.step_timing_signal_type == "learned":
signal = common_attention.get_layer_timing_signal_learned_1d(
channels, step, num_steps)
elif hparams.step_timing_signal_type == "sinusoid":
signal = common_attention.get_layer_timing_signal_sinusoid_1d(
channels, step, num_steps)
if hparams.add_or_concat_timing_signal == "add":
x_with_timing = x + signal
elif hparams.add_or_concat_timing_signal == "concat":
batch_size = common_layers.shape_list(x)[0]
length = common_layers.shape_list(x)[1]
signal_tiled = tf.tile(signal, [batch_size, length, 1])
x_with_timing = tf.concat((x, signal_tiled), axis=-1)
return x_with_timing 示例2: add_step_timing_signal
# 需要導入模塊: from tensor2tensor.layers import common_attention [as 別名]
# 或者: from tensor2tensor.layers.common_attention import get_layer_timing_signal_learned_1d [as 別名]
def add_step_timing_signal(x, step, hparams):
"""Add n-dimensional embedding as the step (vertical) timing signal.
Args:
x: a tensor with shape [batch, length, depth]
step: step
hparams: model hyper parameters
Returns:
a Tensor with the same shape as x.
"""
if hparams.recurrence_type == "act":
num_steps = hparams.act_max_steps
else:
num_steps = hparams.num_rec_steps
channels = common_layers.shape_list(x)[-1]
if hparams.step_timing_signal_type == "learned":
signal = common_attention.get_layer_timing_signal_learned_1d(
channels, step, num_steps)
elif hparams.step_timing_signal_type == "sinusoid":
signal = common_attention.get_layer_timing_signal_sinusoid_1d(
channels, step, num_steps)
if hparams.add_or_concat_timing_signal == "add":
x_with_timing = x + common_layers.cast_like(signal, x)
elif hparams.add_or_concat_timing_signal == "concat":
batch_size = common_layers.shape_list(x)[0]
length = common_layers.shape_list(x)[1]
signal_tiled = tf.tile(signal, [batch_size, length, 1])
x_with_timing = tf.concat((x, signal_tiled), axis=-1)
return x_with_timing