本文整理匯總了Python中tensorflow.python.ops.math_ops.log1p方法的典型用法代碼示例。如果您正苦於以下問題：Python math_ops.log1p方法的具體用法？Python math_ops.log1p怎麽用？Python math_ops.log1p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tensorflow.python.ops.math_ops的用法示例。
在下文中一共展示了math_ops.log1p方法的15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: _sample_n
# 需要導入模塊: from tensorflow.python.ops import math_ops [as 別名]
# 或者: from tensorflow.python.ops.math_ops import log1p [as 別名]
def _sample_n(self, n, seed=None):
# Uniform variates must be sampled from the open-interval `(0, 1)` rather
# than `[0, 1)`. To do so, we use `np.finfo(self.dtype.as_numpy_dtype).tiny`
# because it is the smallest, positive, "normal" number. A "normal" number
# is such that the mantissa has an implicit leading 1. Normal, positive
# numbers x, y have the reasonable property that, `x + y >= max(x, y)`. In
# this case, a subnormal number (i.e., np.nextafter) can cause us to sample
# 0.
uniform = random_ops.random_uniform(
shape=array_ops.concat([[n], self.batch_shape_tensor()], 0),
minval=np.finfo(self.dtype.as_numpy_dtype).tiny,
maxval=1.,
dtype=self.dtype,
seed=seed)
sampled = math_ops.log(uniform) - math_ops.log1p(-1. * uniform)
return sampled * self.scale + self.loc 示例2: _sample_n
# 需要導入模塊: from tensorflow.python.ops import math_ops [as 別名]
# 或者: from tensorflow.python.ops.math_ops import log1p [as 別名]
def _sample_n(self, n, seed=None):
# Uniform variates must be sampled from the open-interval `(0, 1)` rather
# than `[0, 1)`. To do so, we use `np.finfo(self.dtype.as_numpy_dtype).tiny`
# because it is the smallest, positive, "normal" number. A "normal" number
# is such that the mantissa has an implicit leading 1. Normal, positive
# numbers x, y have the reasonable property that, `x + y >= max(x, y)`. In
# this case, a subnormal number (i.e., np.nextafter) can cause us to sample
# 0.
sampled = random_ops.random_uniform(
array_ops.concat([[n], array_ops.shape(self._probs)], 0),
minval=np.finfo(self.dtype.as_numpy_dtype).tiny,
maxval=1.,
seed=seed,
dtype=self.dtype)
return math_ops.floor(
math_ops.log(sampled) / math_ops.log1p(-self.probs)) 示例3: _sample_n
# 需要導入模塊: from tensorflow.python.ops import math_ops [as 別名]
# 或者: from tensorflow.python.ops.math_ops import log1p [as 別名]
def _sample_n(self, n, seed=None):
shape = array_ops.concat([[n], self.batch_shape_tensor()], 0)
# Uniform variates must be sampled from the open-interval `(-1, 1)` rather
# than `[-1, 1)`. In the case of `(0, 1)` we'd use
# `np.finfo(self.dtype.as_numpy_dtype).tiny` because it is the smallest,
# positive, "normal" number. However, the concept of subnormality exists
# only at zero; here we need the smallest usable number larger than -1,
# i.e., `-1 + eps/2`.
uniform_samples = random_ops.random_uniform(
shape=shape,
minval=np.nextafter(self.dtype.as_numpy_dtype(-1.),
self.dtype.as_numpy_dtype(0.)),
maxval=1.,
dtype=self.dtype,
seed=seed)
return (self.loc - self.scale * math_ops.sign(uniform_samples) *
math_ops.log1p(-math_ops.abs(uniform_samples))) 開發者ID:PacktPublishing，項目名稱:Serverless-Deep-Learning-with-TensorFlow-and-AWS-Lambda，代碼行數:19，代碼來源:laplace.py
示例4: _log_unnormalized_prob
# 需要導入模塊: from tensorflow.python.ops import math_ops [as 別名]
# 或者: from tensorflow.python.ops.math_ops import log1p [as 別名]
def _log_unnormalized_prob(self, x):
x = self._maybe_assert_valid_sample(x)
return ((self.concentration1 - 1.) * math_ops.log(x)
+ (self.concentration0 - 1.) * math_ops.log1p(-x)) 示例5: _call_log_survival_function
# 需要導入模塊: from tensorflow.python.ops import math_ops [as 別名]
# 或者: from tensorflow.python.ops.math_ops import log1p [as 別名]
def _call_log_survival_function(self, value, name, **kwargs):
with self._name_scope(name, values=[value]):
value = ops.convert_to_tensor(value, name="value")
try:
return self._log_survival_function(value, **kwargs)
except NotImplementedError as original_exception:
try:
return math_ops.log1p(-self.cdf(value, **kwargs))
except NotImplementedError:
raise original_exception 示例6: _log_unnormalized_prob
# 需要導入模塊: from tensorflow.python.ops import math_ops [as 別名]
# 或者: from tensorflow.python.ops.math_ops import log1p [as 別名]
def _log_unnormalized_prob(self, x):
y = (x - self.loc) / self.scale # Abs(scale) superfluous.
return -0.5 * (self.df + 1.) * math_ops.log1p(y**2. / self.df) 示例7: _cdf
# 需要導入模塊: from tensorflow.python.ops import math_ops [as 別名]
# 或者: from tensorflow.python.ops.math_ops import log1p [as 別名]
def _cdf(self, counts):
if self.validate_args:
# We set `check_integer=False` since the CDF is defined on whole real
# line.
counts = math_ops.floor(
distribution_util.embed_check_nonnegative_discrete(
counts, check_integer=False))
counts *= array_ops.ones_like(self.probs)
return array_ops.where(
counts < 0.,
array_ops.zeros_like(counts),
-math_ops.expm1(
(counts + 1) * math_ops.log1p(-self.probs))) 示例8: _log_prob
# 需要導入模塊: from tensorflow.python.ops import math_ops [as 別名]
# 或者: from tensorflow.python.ops.math_ops import log1p [as 別名]
def _log_prob(self, counts):
if self.validate_args:
counts = distribution_util.embed_check_nonnegative_discrete(
counts, check_integer=True)
counts *= array_ops.ones_like(self.probs)
probs = self.probs * array_ops.ones_like(counts)
safe_domain = array_ops.where(
math_ops.equal(counts, 0.),
array_ops.zeros_like(probs),
probs)
return counts * math_ops.log1p(-safe_domain) + math_ops.log(probs) 示例9: _forward
# 需要導入模塊: from tensorflow.python.ops import math_ops [as 別名]
# 或者: from tensorflow.python.ops.math_ops import log1p [as 別名]
def _forward(self, x):
x = self._maybe_assert_valid_x(x)
if self.power == 0.:
return math_ops.exp(x)
# If large x accuracy is an issue, consider using:
# (1. + x * self.power)**(1. / self.power) when x >> 1.
return math_ops.exp(math_ops.log1p(x * self.power) / self.power) 示例10: _inverse
# 需要導入模塊: from tensorflow.python.ops import math_ops [as 別名]
# 或者: from tensorflow.python.ops.math_ops import log1p [as 別名]
def _inverse(self, y):
return math_ops.log(y) - math_ops.log1p(-y) 示例11: _inverse_log_det_jacobian
# 需要導入模塊: from tensorflow.python.ops import math_ops [as 別名]
# 或者: from tensorflow.python.ops.math_ops import log1p [as 別名]
def _inverse_log_det_jacobian(self, y):
return -math_ops.log(y) - math_ops.log1p(-y) 示例12: _log_unnormalized_prob
# 需要導入模塊: from tensorflow.python.ops import math_ops [as 別名]
# 或者: from tensorflow.python.ops.math_ops import log1p [as 別名]
def _log_unnormalized_prob(self, counts):
counts = self._maybe_assert_valid_sample(counts)
return (counts * math_ops.log(self.probs) +
(self.total_count - counts) * math_ops.log1p(-self.probs)) 示例13: _log_unnormalized_prob
# 需要導入模塊: from tensorflow.python.ops import math_ops [as 別名]
# 或者: from tensorflow.python.ops.math_ops import log1p [as 別名]
def _log_unnormalized_prob(self, positive_counts):
if self.validate_args:
positive_counts = distribution_util.embed_check_nonnegative_discrete(
positive_counts, check_integer=True)
return self.total_count * math_ops.log1p(
-self.probs) + positive_counts * math_ops.log(self.probs) 示例14: _log_unnormalized_prob
# 需要導入模塊: from tensorflow.python.ops import math_ops [as 別名]
# 或者: from tensorflow.python.ops.math_ops import log1p [as 別名]
def _log_unnormalized_prob(self, x):
y = (x - self.mu) / self.sigma # Abs(sigma) superfluous.
return -0.5 * (self.df + 1.) * math_ops.log1p(y**2. / self.df) 示例15: _forward
# 需要導入模塊: from tensorflow.python.ops import math_ops [as 別名]
# 或者: from tensorflow.python.ops.math_ops import log1p [as 別名]
def _forward(self, x):
x = self._maybe_assert_valid_x(x)
if self.power == 0.:
return math_ops.exp(x)
# TODO(jvdillon): If large x accuracy is an issue, consider using
# (1. + x * self.power)**(1. / self.power) when x >> 1.
return math_ops.exp(math_ops.log1p(x * self.power) / self.power)