本文整理汇总了Python中tensorflow.compat.v1.assert_less_equal方法的典型用法代码示例。如果您正苦于以下问题：Python v1.assert_less_equal方法的具体用法？Python v1.assert_less_equal怎么用？Python v1.assert_less_equal使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类tensorflow.compat.v1的用法示例。
在下文中一共展示了v1.assert_less_equal方法的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: demidify
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import assert_less_equal [as 别名]
def demidify(pitches):
"""Transforms MIDI pitches [21,108] to [0, 88)."""
assertions = [
tf.assert_greater_equal(pitches, 21),
tf.assert_less_equal(pitches, 108)
]
with tf.control_dependencies(assertions):
return pitches - 21 示例2: remidify
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import assert_less_equal [as 别名]
def remidify(pitches):
"""Transforms [0, 88) to MIDI pitches [21, 108]."""
assertions = [
tf.assert_greater_equal(pitches, 0),
tf.assert_less_equal(pitches, 87)
]
with tf.control_dependencies(assertions):
return pitches + 21 示例3: maybe_split_sequence_lengths
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import assert_less_equal [as 别名]
def maybe_split_sequence_lengths(sequence_length, num_splits, total_length):
"""Validates and splits `sequence_length`, if necessary.
Returned value must be used in graph for all validations to be executed.
Args:
sequence_length: A batch of sequence lengths, either sized `[batch_size]`
and equal to either 0 or `total_length`, or sized
`[batch_size, num_splits]`.
num_splits: The scalar number of splits of the full sequences.
total_length: The scalar total sequence length (potentially padded).
Returns:
sequence_length: If input shape was `[batch_size, num_splits]`, returns the
same Tensor. Otherwise, returns a Tensor of that shape with each input
length in the batch divided by `num_splits`.
Raises:
ValueError: If `sequence_length` is not shaped `[batch_size]` or
`[batch_size, num_splits]`.
tf.errors.InvalidArgumentError: If `sequence_length` is shaped
`[batch_size]` and all values are not either 0 or `total_length`.
"""
if sequence_length.shape.ndims == 1:
if total_length % num_splits != 0:
raise ValueError(
'`total_length` must be evenly divisible by `num_splits`.')
with tf.control_dependencies(
[tf.Assert(
tf.reduce_all(
tf.logical_or(tf.equal(sequence_length, 0),
tf.equal(sequence_length, total_length))),
data=[sequence_length])]):
sequence_length = (
tf.tile(tf.expand_dims(sequence_length, axis=1), [1, num_splits]) //
num_splits)
elif sequence_length.shape.ndims == 2:
with tf.control_dependencies([
tf.assert_less_equal(
sequence_length,
tf.constant(total_length // num_splits, tf.int32),
message='Segment length cannot be more than '
'`total_length / num_splits`.')]):
sequence_length = tf.identity(sequence_length)
sequence_length.set_shape([sequence_length.shape[0], num_splits])
else:
raise ValueError(
'Sequence lengths must be given as a vector or a 2D Tensor whose '
'second dimension size matches its initial hierarchical split. Got '
'shape: %s' % sequence_length.shape.as_list())
return sequence_length