def _log_abs_determinant(self):
if self._is_spd:
diag = array_ops.matrix_diag_part(self._chol)
return 2 * math_ops.reduce_sum(math_ops.log(diag), reduction_indices=[-1])
if self.dtype.is_complex:
abs_det = math_ops.complex_abs(self.determinant())
else:
abs_det = math_ops.abs(self.determinant())
return math_ops.log(abs_det)
def _assert_non_singular(self):
if self.dtype.is_complex:
should_be_nonzero = math_ops.complex_abs(self._diag)
else:
should_be_nonzero = self._diag
nonzero_diag = math_ops.reduce_all(
math_ops.logical_not(math_ops.equal(should_be_nonzero, 0)))
return control_flow_ops.Assert(
nonzero_diag,
data=["Singular operator: diag contained zero values.", self._diag])
def _assert_non_singular(self):
if self.dtype.is_complex:
should_be_nonzero = math_ops.complex_abs(self._diag)
else:
should_be_nonzero = self._diag
nonzero_diag = math_ops.reduce_all(
math_ops.logical_not(math_ops.equal(should_be_nonzero, 0)))
return control_flow_ops.Assert(
nonzero_diag,
data=[
"Singular operator: diag contained zero values.", self._diag
])
def _testGrad(self, shape, dtype=None, max_error=None, bias=None, sigma=None):
np.random.seed(7)
if dtype in (dtypes.complex64, dtypes.complex128):
value = math_ops.complex(
self._biasedRandN(shape, bias=bias, sigma=sigma), self._biasedRandN(shape, bias=bias, sigma=sigma)
)
else:
value = ops.convert_to_tensor(self._biasedRandN(shape, bias=bias), dtype=dtype)
with self.test_session(use_gpu=True):
if dtype in (dtypes.complex64, dtypes.complex128):
output = math_ops.complex_abs(value)
else:
output = math_ops.abs(value)
error = gradient_checker.compute_gradient_error(value, shape, output, output.get_shape().as_list())
self.assertLess(error, max_error)
def _testGrad(self, shape, dtype=None, max_error=None, bias=None, sigma=None):
np.random.seed(7)
if dtype in (dtypes.complex64, dtypes.complex128):
value = math_ops.complex(
self._biasedRandN(
shape, bias=bias, sigma=sigma),
self._biasedRandN(
shape, bias=bias, sigma=sigma))
else:
value = ops.convert_to_tensor(
self._biasedRandN(
shape, bias=bias), dtype=dtype)
with self.test_session(use_gpu=True):
if dtype in (dtypes.complex64, dtypes.complex128):
output = math_ops.complex_abs(value)
else:
output = math_ops.abs(value)
error = gradient_checker.compute_gradient_error(
value, shape, output, output.get_shape().as_list())
self.assertLess(error, max_error)
def assert_no_entries_with_modulus_zero(
x, message=None, name="assert_no_entries_with_modulus_zero"):
"""Returns `Op` that asserts Tensor `x` has no entries with modulus zero.
Args:
x: Numeric `Tensor`, real, integer, or complex.
message: A string message to prepend to failure message.
name: A name to give this `Op`.
Returns:
An `Op` that asserts `x` has no entries with modulus zero.
"""
with ops.name_scope(name, values=[x]):
x = ops.convert_to_tensor(x, name="x")
dtype = x.dtype.base_dtype
if dtype.is_complex:
should_be_nonzero = math_ops.complex_abs(x)
else:
should_be_nonzero = math_ops.abs(x)
zero = ops.convert_to_tensor(0, dtype=dtype.real_dtype)
return check_ops.assert_less(zero, should_be_nonzero, message=message)
def assert_no_entries_with_modulus_zero(
x, message=None, name="assert_no_entries_with_modulus_zero"):
"""Returns `Op` that asserts Tensor `x` has no entries with modulus zero.
Args:
x: Numeric `Tensor`, real, integer, or complex.
message: A string message to prepend to failure message.
name: A name to give this `Op`.
Returns:
An `Op` that asserts `x` has no entries with modulus zero.
"""
with ops.name_scope(name, values=[x]):
x = ops.convert_to_tensor(x, name="x")
dtype = x.dtype.base_dtype
if dtype.is_complex:
should_be_nonzero = math_ops.complex_abs(x)
else:
should_be_nonzero = math_ops.abs(x)
zero = ops.convert_to_tensor(0, dtype=dtype.real_dtype)
return check_ops.assert_less(zero, should_be_nonzero, message=message)
