def testScalarCongruency(self):
with self.test_session():
bijector = bijectors.Invert(bijectors.Exp())
assert_scalar_congruency(bijector,
lower_x=1e-3,
upper_x=1.5,
rtol=0.05)
def testBijector(self):
with self.test_session():
for fwd in [
bijectors.Identity(),
bijectors.Exp(event_ndims=1),
bijectors.Affine(shift=[0., 1.],
scale_diag=[2., 3.],
event_ndims=1),
bijectors.Softplus(event_ndims=1),
bijectors.SoftmaxCentered(event_ndims=1),
bijectors.SigmoidCentered(),
]:
rev = bijectors.Invert(fwd)
self.assertEqual("_".join(["invert", fwd.name]), rev.name)
x = [[[1., 2.], [2., 3.]]]
self.assertAllClose(
fwd.inverse(x).eval(),
rev.forward(x).eval())
self.assertAllClose(
fwd.forward(x).eval(),
rev.inverse(x).eval())
self.assertAllClose(
fwd.forward_log_det_jacobian(x).eval(),
rev.inverse_log_det_jacobian(x).eval())
self.assertAllClose(
fwd.inverse_log_det_jacobian(x).eval(),
rev.forward_log_det_jacobian(x).eval())
def testBijector(self):
x = np.float32(np.random.randn(3, 4, 4))
y = x.copy()
for i in range(x.shape[0]):
np.fill_diagonal(y[i, :, :], np.exp(np.diag(x[i, :, :])))
exp = bijectors.Exp()
b = bijectors.TransformDiagonal(diag_bijector=exp)
y_ = self.evaluate(b.forward(x))
self.assertAllClose(y, y_)
x_ = self.evaluate(b.inverse(y))
self.assertAllClose(x, x_)
fldj = self.evaluate(b.forward_log_det_jacobian(x, event_ndims=2))
ildj = self.evaluate(b.inverse_log_det_jacobian(y, event_ndims=2))
self.assertAllEqual(
fldj,
self.evaluate(exp.forward_log_det_jacobian(
np.array([np.diag(x_mat) for x_mat in x]),
event_ndims=1)))
self.assertAllEqual(
ildj,
self.evaluate(exp.inverse_log_det_jacobian(
np.array([np.diag(y_mat) for y_mat in y]),
event_ndims=1)))
def testDocstringExample(self):
with self.cached_session():
exp_gamma_distribution = (
transformed_distribution_lib.TransformedDistribution(
distribution=gamma_lib.Gamma(concentration=1., rate=2.),
bijector=bijectors.Invert(bijectors.Exp())))
self.assertAllEqual(
[], array_ops.shape(exp_gamma_distribution.sample()).eval())
def testComputesCorrectValues(self):
shift = 1.61803398875
x = np.float32(np.array([-1, .5, 2]))
y = np.float32(
np.array([[np.exp(2) + shift, 0.], [.5, np.exp(-1) + shift]]))
b = bijectors.ScaleTriL(diag_bijector=bijectors.Exp(),
diag_shift=shift)
y_ = self.evaluate(b.forward(x))
self.assertAllClose(y, y_, rtol=1e-4)
x_ = self.evaluate(b.inverse(y))
self.assertAllClose(x, x_, rtol=1e-4)
def __init__(
self,
temperature,
logits=None,
probs=None,
dtype=None,
validate_args=False,
allow_nan_stats=True,
name="RelaxedOneHotCategorical"):
"""Initialize RelaxedOneHotCategorical using class log-probabilities.
Args:
temperature: An 0-D `Tensor`, representing the temperature
of a set of RelaxedOneHotCategorical distributions. The temperature
should be positive.
logits: An N-D `Tensor`, `N >= 1`, representing the log probabilities
of a set of RelaxedOneHotCategorical distributions. The first
`N - 1` dimensions index into a batch of independent distributions and
the last dimension represents a vector of logits for each class. Only
one of `logits` or `probs` should be passed in.
probs: An N-D `Tensor`, `N >= 1`, representing the probabilities
of a set of RelaxedOneHotCategorical distributions. The first `N - 1`
dimensions index into a batch of independent distributions and the last
dimension represents a vector of probabilities for each class. Only one
of `logits` or `probs` should be passed in.
dtype: The type of the event samples (default: inferred from
logits/probs).
validate_args: Unused in this distribution.
allow_nan_stats: Python `bool`, default `True`. If `False`, raise an
exception if a statistic (e.g. mean/mode/etc...) is undefined for any
batch member. If `True`, batch members with valid parameters leading to
undefined statistics will return NaN for this statistic.
name: A name for this distribution (optional).
"""
dist = ExpRelaxedOneHotCategorical(temperature,
logits=logits,
probs=probs,
dtype=dtype,
validate_args=validate_args,
allow_nan_stats=allow_nan_stats)
super(RelaxedOneHotCategorical, self).__init__(dist,
bijectors.Exp(),
name=name)
