def testBijectiveAndFinite32bit(self):
with self.test_session():
bijector = Softplus(event_ndims=0)
x = np.linspace(-20., 20., 100).astype(np.float32)
y = np.logspace(-10, 10, 100).astype(np.float32)
assert_bijective_and_finite(
bijector, x, y, rtol=1e-2, atol=1e-2)
def testBijectiveAndFinite(self):
with self.test_session():
bijector = PowerTransform(
power=0.2, event_ndims=0, validate_args=True)
x = np.linspace(-4.999, 10, num=10).astype(np.float32)
y = np.logspace(0.001, 10, num=10).astype(np.float32)
assert_bijective_and_finite(bijector, x, y, rtol=1e-3)
def testBijectiveAndFiniteWithPositiveHingeSoftness32Bit(self):
with self.cached_session():
bijector = Softplus(hinge_softness=1.23)
x = np.linspace(-20., 20., 100).astype(np.float32)
y = np.logspace(-10, 10, 100).astype(np.float32)
assert_bijective_and_finite(
bijector, x, y, event_ndims=0, rtol=1e-2, atol=1e-2)
def testBijectiveAndFinite(self):
with self.cached_session():
bijector = Softsign(validate_args=True)
x = np.linspace(-20., 20., 100).astype(np.float32)
y = np.linspace(-0.99, 0.99, 100).astype(np.float32)
assert_bijective_and_finite(
bijector, x, y, event_ndims=0, rtol=1e-3, atol=1e-3)
def testBijectiveAndFinite(self):
with self.cached_session():
x = np.linspace(-7., 7., 100).astype(np.float32)
eps = 1e-3
y = np.linspace(eps, 1. - eps, 100).astype(np.float32)
assert_bijective_and_finite(
Sigmoid(), x, y, event_ndims=0, atol=0., rtol=1e-4)
def testBijectiveAndFinite(self):
permutation = np.int32([2, 0, 1])
x = np.random.randn(4, 2, 3)
y = x[..., permutation]
with self.test_session():
bijector = Permute(permutation=permutation, validate_args=True)
assert_bijective_and_finite(bijector, x, y, rtol=1e-6, atol=0)
def testBijectiveAndFiniteSkewness1Tailweight3(self):
with self.test_session():
bijector = tfb.SinhArcsinh(skewness=1., tailweight=3., validate_args=True)
x = np.concatenate((-np.logspace(-2, 5, 1000), [0], np.logspace(
-2, 5, 1000))).astype(np.float32)
assert_bijective_and_finite(
bijector, x, x, event_ndims=0, rtol=1e-3)
def testBijectiveAndFinite(self):
with self.test_session():
bijector = tfb.Softsign(validate_args=True)
x = np.linspace(-20., 20., 100).astype(np.float32)
y = np.linspace(-0.99, 0.99, 100).astype(np.float32)
assert_bijective_and_finite(
bijector, x, y, event_ndims=0, rtol=1e-3, atol=1e-3)
def testBijectiveAndFiniteSkewness1Tailweight3(self):
with self.test_session():
bijector = tfb.SinhArcsinh(skewness=1., tailweight=3., validate_args=True)
x = np.concatenate((-np.logspace(-2, 5, 1000), [0], np.logspace(
-2, 5, 1000))).astype(np.float32)
assert_bijective_and_finite(
bijector, x, x, event_ndims=0, rtol=1e-3)
def testBijectiveAndFinite(self):
with self.test_session():
x = np.linspace(-7., 7., 100).astype(np.float32)
eps = 1e-3
y = np.linspace(eps, 1. - eps, 100).astype(np.float32)
assert_bijective_and_finite(
tfb.Sigmoid(), x, y, event_ndims=0, atol=0., rtol=1e-4)
def testBijectiveAndFiniteWithNegativeHingeSoftness32Bit(self):
with self.test_session():
bijector = Softplus(event_ndims=0, hinge_softness=-0.7)
x = np.linspace(-20., 20., 100).astype(np.float32)
y = -np.logspace(-10, 10, 100).astype(np.float32)
assert_bijective_and_finite(
bijector, x, y, rtol=1e-2, atol=1e-2)
def testBijectiveAndFinite(self):
x = np.random.randn(4, 2, 3)
y = np.reshape(x, [4, 1, 2, 3])
with self.test_session():
bijector = tfb.Reshape(
event_shape_in=[2, 3], event_shape_out=[1, 2, 3], validate_args=True)
assert_bijective_and_finite(
bijector, x, y, event_ndims=2, rtol=1e-6, atol=0)
def testBijectiveAndFinite(self):
x = np.random.randn(4, 2, 3)
y = np.reshape(x, [4, 1, 2, 3])
with self.test_session():
bijector = Reshape(event_shape_in=[2, 3],
event_shape_out=[1, 2, 3],
validate_args=True)
assert_bijective_and_finite(bijector, x, y, rtol=1e-6, atol=0)
def testBijectiveAndFiniteSkewnessNeg1Tailweight0p5(self):
with self.test_session():
bijector = SinhArcsinh(skewness=-1., tailweight=0.5, validate_args=True)
# Increasing upper logspace limit to 10 results in Inf due to y**2 being
# Inf.
x = np.concatenate((-np.logspace(-2, 9, 1000), [0], np.logspace(
-2, 9, 1000))).astype(np.float32)
assert_bijective_and_finite(bijector, x, x, rtol=1e-3)
def testBijectiveAndFinite(self):
with self.test_session():
bijector = tfb.Weibull(scale=20., concentration=2., validate_args=True)
x = np.linspace(1., 8., num=10).astype(np.float32)
y = np.linspace(
-np.expm1(-1 / 400.),
-np.expm1(-16), num=10).astype(np.float32)
assert_bijective_and_finite(bijector, x, y, event_ndims=0, rtol=1e-3)
def testBijectiveAndFiniteSkewnessNeg1Tailweight0p5(self):
with self.test_session():
bijector = SinhArcsinh(skewness=-1.,
tailweight=0.5,
validate_args=True)
x = np.concatenate((-np.logspace(-2, 10, 1000), [0],
np.logspace(-2, 10, 1000))).astype(np.float32)
assert_bijective_and_finite(bijector, x, x, rtol=1e-3)
def testBijectiveAndFinite(self):
permutation = np.int32([2, 0, 1])
x = np.random.randn(4, 2, 3)
y = x[..., permutation]
with self.test_session():
bijector = Permute(permutation=permutation, validate_args=True)
assert_bijective_and_finite(
bijector, x, y, event_ndims=1, rtol=1e-6, atol=0)
def testBijectiveAndFinite(self):
with self.test_session():
bijector = Gumbel(loc=0.,
scale=3.0,
event_ndims=0,
validate_args=True)
x = np.linspace(-10., 10., num=10).astype(np.float32)
y = np.linspace(0.01, 0.99, num=10).astype(np.float32)
assert_bijective_and_finite(bijector, x, y, rtol=1e-3)
def testBijectiveAndFinite(self):
with self.cached_session():
bijector = Weibull(
scale=20., concentration=2., validate_args=True)
x = np.linspace(1., 8., num=10).astype(np.float32)
y = np.linspace(
-np.expm1(-1 / 400.),
-np.expm1(-16), num=10).astype(np.float32)
assert_bijective_and_finite(bijector, x, y, event_ndims=0, rtol=1e-3)
def testBijectiveAndFinite16bit(self):
with self.test_session():
bijector = Softplus(event_ndims=0)
# softplus(-20) is zero, so we can't use such a large range as in 32bit.
x = np.linspace(-10., 20., 100).astype(np.float16)
# Note that float16 is only in the open set (0, inf) for a smaller
# logspace range. The actual range was (-7, 4), so use something smaller
# for the test.
y = np.logspace(-6, 3, 100).astype(np.float16)
assert_bijective_and_finite(bijector, x, y, rtol=1e-1, atol=1e-3)
def testBijectorEndpoints(self):
with self.test_session():
for dtype in (np.float32, np.float64):
bijector = SinhArcsinh(
skewness=dtype(0.), tailweight=dtype(1.), validate_args=True)
bounds = np.array(
[np.finfo(dtype).min, np.finfo(dtype).max], dtype=dtype)
# Note that the above bijector is the identity bijector. Hence, the
# log_det_jacobian will be 0. Because of this we use atol.
assert_bijective_and_finite(bijector, bounds, bounds, atol=2e-6)
def testBijectiveAndFiniteSkewnessNeg1Tailweight0p5(self):
with self.test_session():
bijector = SinhArcsinh(skewness=-1.,
tailweight=0.5,
validate_args=True)
# Increasing upper logspace limit to 10 results in Inf due to y**2 being
# Inf.
x = np.concatenate((-np.logspace(-2, 9, 1000), [0],
np.logspace(-2, 9, 1000))).astype(np.float32)
assert_bijective_and_finite(bijector, x, x, rtol=1e-3)
def testBijectiveAndFiniteWithPositiveHingeSoftness32Bit(self):
with self.cached_session():
bijector = Softplus(hinge_softness=1.23)
x = np.linspace(-20., 20., 100).astype(np.float32)
y = np.logspace(-10, 10, 100).astype(np.float32)
assert_bijective_and_finite(bijector,
x,
y,
event_ndims=0,
rtol=1e-2,
atol=1e-2)
def testBijectiveAndFiniteAxis(self):
permutation = np.int32([1, 0])
x = np.random.randn(4, 2, 3)
y = x[..., permutation, :]
with self.test_session():
bijector = tfb.Permute(
permutation=permutation,
axis=-2,
validate_args=True)
assert_bijective_and_finite(
bijector, x, y, event_ndims=2, rtol=1e-6, atol=0)
def testBijectiveAndFiniteWithNegativeHingeSoftness32Bit(self):
with self.test_session():
bijector = tfb.Softplus(hinge_softness=-0.7)
x = np.linspace(-20., 20., 100).astype(np.float32)
y = -np.logspace(-10, 10, 100).astype(np.float32)
assert_bijective_and_finite(bijector,
x,
y,
event_ndims=0,
rtol=1e-2,
atol=1e-2)
def testBijectiveAndFinite32bit(self):
with self.test_session():
bijector = tfb.Softplus()
x = np.linspace(-20., 20., 100).astype(np.float32)
y = np.logspace(-10, 10, 100).astype(np.float32)
assert_bijective_and_finite(bijector,
x,
y,
event_ndims=0,
rtol=1e-2,
atol=1e-2)
def testBijectiveAndFinite16bit(self):
with self.test_session():
bijector = Softplus(event_ndims=0)
# softplus(-20) is zero, so we can't use such a large range as in 32bit.
x = np.linspace(-10., 20., 100).astype(np.float16)
# Note that float16 is only in the open set (0, inf) for a smaller
# logspace range. The actual range was (-7, 4), so use something smaller
# for the test.
y = np.logspace(-6, 3, 100).astype(np.float16)
assert_bijective_and_finite(
bijector, x, y, rtol=1e-1, atol=1e-3)
def testBijectiveAndFinite(self):
with self.test_session():
softmax = tfb.SoftmaxCentered()
x = np.linspace(-50, 50, num=10).reshape(5, 2).astype(np.float32)
# Make y values on the simplex with a wide range.
y_0 = np.ones(5).astype(np.float32)
y_1 = (1e-5 * rng.rand(5)).astype(np.float32)
y_2 = (1e1 * rng.rand(5)).astype(np.float32)
y = np.array([y_0, y_1, y_2])
y /= y.sum(axis=0)
y = y.T # y.shape = [5, 3]
assert_bijective_and_finite(softmax, x, y, event_ndims=1)
def testBijectiveAndFinite(self):
with self.test_session():
concentration1 = 1.2
concentration0 = 2.
bijector = Kumaraswamy(concentration1=concentration1,
concentration0=concentration0,
validate_args=True)
# Omitting the endpoints 0 and 1, since idlj will be infinity at these
# endpoints.
y = np.linspace(.01, 0.99, num=10).astype(np.float32)
x = 1 - (1 - y**concentration1)**concentration0
assert_bijective_and_finite(bijector, x, y, rtol=1e-3)
def testBijectiveAndFinite(self):
with self.test_session():
softmax = SoftmaxCentered(event_ndims=1)
x = np.linspace(-50, 50, num=10).reshape(5, 2).astype(np.float32)
# Make y values on the simplex with a wide range.
y_0 = np.ones(5).astype(np.float32)
y_1 = (1e-5 * rng.rand(5)).astype(np.float32)
y_2 = (1e1 * rng.rand(5)).astype(np.float32)
y = np.array([y_0, y_1, y_2])
y /= y.sum(axis=0)
y = y.T # y.shape = [5, 3]
assert_bijective_and_finite(softmax, x, y)
def testBijectiveAndFinite(self):
with self.test_session():
concentration1 = 1.2
concentration0 = 2.
bijector = Kumaraswamy(
concentration1=concentration1,
concentration0=concentration0, validate_args=True)
# Omitting the endpoints 0 and 1, since idlj will be infinity at these
# endpoints.
y = np.linspace(.01, 0.99, num=10).astype(np.float32)
x = 1 - (1 - y ** concentration1) ** concentration0
assert_bijective_and_finite(bijector, x, y, rtol=1e-3)
def testBijectiveAndFiniteSkewnessNeg1Tailweight0p5(self):
with self.test_session():
bijector = SinhArcsinh(skewness=-1., tailweight=0.5, validate_args=True)
x = np.concatenate((-np.logspace(-2, 10, 1000), [0], np.logspace(
-2, 10, 1000))).astype(np.float32)
assert_bijective_and_finite(bijector, x, x, rtol=1e-3)
def testBijectiveAndFinite(self):
with self.test_session():
bijector = Gumbel(loc=0., scale=3.0, validate_args=True)
x = np.linspace(-10., 10., num=10).astype(np.float32)
y = np.linspace(0.01, 0.99, num=10).astype(np.float32)
assert_bijective_and_finite(bijector, x, y, event_ndims=0, rtol=1e-3)
def testBijectiveAndFinite(self):
with self.test_session():
bijector = tfb.Exp()
x = np.linspace(-10, 10, num=10).astype(np.float32)
y = np.logspace(-10, 10, num=10).astype(np.float32)
assert_bijective_and_finite(bijector, x, y, event_ndims=0)
def testBijectiveAndFinite(self):
with self.test_session():
bijector = tfb.Exp()
x = np.linspace(-10, 10, num=10).astype(np.float32)
y = np.logspace(-10, 10, num=10).astype(np.float32)
assert_bijective_and_finite(bijector, x, y, event_ndims=0)
def testBijectiveAndFinite(self):
with self.test_session():
ordered = Ordered()
x = np.sort(self._rng.randn(3, 10), axis=-1).astype(np.float32)
y = (self._rng.randn(3, 10)).astype(np.float32)
assert_bijective_and_finite(ordered, x, y, event_ndims=1)
