本文整理汇总了Python中tensorflow.python.ops.math_ops.conj函数的典型用法代码示例。如果您正苦于以下问题：Python conj函数的具体用法？Python conj怎么用？Python conj使用的例子？那么恭喜您, 这里精选的函数代码示例或许可以为您提供帮助。
在下文中一共展示了conj函数的15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: _ReciprocalGradGrad
def _ReciprocalGradGrad(op, grad):
b = op.inputs[1]
# op.output[0]: y = -b * conj(a)^2
with ops.control_dependencies([grad]):
ca = math_ops.conj(op.inputs[0])
cg = math_ops.conj(grad)
return cg * -2.0 * b * ca, gen_math_ops.reciprocal_grad(ca, grad)示例2: _SigmoidGradGrad
def _SigmoidGradGrad(op, grad):
with ops.control_dependencies([grad.op]):
a = math_ops.conj(op.inputs[0])
b = math_ops.conj(op.inputs[1])
gb = grad * b
# pylint: disable=protected-access
return gb - 2.0 * gb * a, gen_math_ops._sigmoid_grad(a, grad)示例3: _ReciprocalGradGrad
def _ReciprocalGradGrad(op, grad):
b = op.inputs[1]
# op.output[0]: y = -b * conj(a)^2
with ops.control_dependencies([grad.op]):
ca = math_ops.conj(op.inputs[0])
cg = math_ops.conj(grad)
# pylint: disable=protected-access
return cg * -2.0 * b * ca, gen_math_ops._reciprocal_grad(ca, grad)示例4: _RsqrtGradGrad
def _RsqrtGradGrad(op, grad):
"""Returns backprop gradient for f(a,b) = -0.5 * b * conj(a)^3."""
a = op.inputs[0] # a = x^{-1/2}
b = op.inputs[1] # backprop gradient for a
with ops.control_dependencies([grad]):
ca = math_ops.conj(a)
cg = math_ops.conj(grad)
grad_a = -1.5 * cg * b * math_ops.square(ca)
grad_b = gen_math_ops.rsqrt_grad(ca, grad)
return grad_a, grad_b示例5: _DivGrad
def _DivGrad(op, grad):
x = op.inputs[0]
y = op.inputs[1]
sx = array_ops.shape(x)
sy = array_ops.shape(y)
rx, ry = gen_array_ops._broadcast_gradient_args(sx, sy) # pylint: disable=protected-access
x = math_ops.conj(x)
y = math_ops.conj(y)
return (array_ops.reshape(math_ops.reduce_sum(grad / y, rx), sx),
array_ops.reshape(math_ops.reduce_sum(grad *
(-x / math_ops.square(y)), ry), sy))示例6: _MulGrad
def _MulGrad(op, grad):
"""The gradient of scalar multiplication."""
x = op.inputs[0]
y = op.inputs[1]
assert x.dtype.base_dtype == y.dtype.base_dtype, (x.dtype, " vs. ", y.dtype)
sx = array_ops.shape(x)
sy = array_ops.shape(y)
rx, ry = gen_array_ops._broadcast_gradient_args(sx, sy)
x = math_ops.conj(x)
y = math_ops.conj(y)
return (array_ops.reshape(math_ops.reduce_sum(grad * y, rx), sx),
array_ops.reshape(math_ops.reduce_sum(x * grad, ry), sy))示例7: _FloorModGrad
def _FloorModGrad(op, grad):
"""Returns grad * (1, -floor(x/y))."""
x = math_ops.conj(op.inputs[0])
y = math_ops.conj(op.inputs[1])
sx = array_ops.shape(x)
sy = array_ops.shape(y)
rx, ry = gen_array_ops.broadcast_gradient_args(sx, sy)
floor_xy = math_ops.floor_div(x, y)
gx = array_ops.reshape(math_ops.reduce_sum(grad, rx), sx)
gy = array_ops.reshape(
math_ops.reduce_sum(grad * math_ops.negative(floor_xy), ry), sy)
return gx, gy示例8: _DivGrad
def _DivGrad(op, grad):
"""The gradient for the Div operator."""
x = op.inputs[0]
y = op.inputs[1]
sx = array_ops.shape(x)
sy = array_ops.shape(y)
rx, ry = gen_array_ops.broadcast_gradient_args(sx, sy)
x = math_ops.conj(x)
y = math_ops.conj(y)
return (array_ops.reshape(math_ops.reduce_sum(math_ops.div(grad, y), rx), sx),
array_ops.reshape(
math_ops.reduce_sum(grad * math_ops.div(math_ops.div(-x, y), y),
ry), sy))示例9: _MulGrad
def _MulGrad(op, grad):
x = op.inputs[0]
y = op.inputs[1]
assert x.dtype.base_dtype == y.dtype.base_dtype, (x.dtype, " vs. ", y.dtype)
sx = array_ops.shape(x)
sy = array_ops.shape(y)
rx, ry = gen_array_ops._broadcast_gradient_args(sx, sy)
if x.dtype.base_dtype == dtypes.complex64:
return (array_ops.reshape(math_ops.reduce_sum(grad * math_ops.conj(y), rx), sx),
array_ops.reshape(math_ops.reduce_sum(math_ops.conj(x) * grad, ry), sy))
else:
return (array_ops.reshape(math_ops.reduce_sum(grad * y, rx), sx),
array_ops.reshape(math_ops.reduce_sum(x * grad, ry), sy))示例10: _DivGrad
def _DivGrad(op, grad):
"""The gradient for the Div operator."""
x = op.inputs[0]
y = op.inputs[1]
sx = array_ops.shape(x)
sy = array_ops.shape(y)
# pylint: disable=protected-access
rx, ry = gen_array_ops._broadcast_gradient_args(sx, sy)
# pylint: enable=protected-access
x = math_ops.conj(x)
y = math_ops.conj(y)
return (array_ops.reshape(math_ops.reduce_sum(math_ops.div(grad, y), rx), sx),
array_ops.reshape(math_ops.reduce_sum(
grad * math_ops.div(-x, math_ops.square(y)), ry), sy))示例11: _DivNoNanGrad
def _DivNoNanGrad(op, grad):
"""DivNoNan op gradient."""
x = op.inputs[0]
y = op.inputs[1]
sx = array_ops.shape(x)
sy = array_ops.shape(y)
rx, ry = gen_array_ops.broadcast_gradient_args(sx, sy)
x = math_ops.conj(x)
y = math_ops.conj(y)
return (array_ops.reshape(
math_ops.reduce_sum(math_ops.div_no_nan(grad, y), rx), sx),
array_ops.reshape(
math_ops.reduce_sum(
grad * math_ops.div_no_nan(math_ops.div_no_nan(-x, y), y),
ry), sy))示例12: _ZetaGrad
def _ZetaGrad(op, grad):
"""Returns gradient of zeta(x, q) with respect to x and q."""
# TODO(tillahoffmann): Add derivative with respect to x
x = op.inputs[0]
q = op.inputs[1]
# Broadcast gradients
sx = array_ops.shape(x)
sq = array_ops.shape(q)
unused_rx, rq = gen_array_ops._broadcast_gradient_args(sx, sq)
# Evaluate gradient
with ops.control_dependencies([grad.op]):
x = math_ops.conj(x)
q = math_ops.conj(q)
partial_q = -x * math_ops.zeta(x + 1, q)
return (None,
array_ops.reshape(math_ops.reduce_sum(partial_q * grad, rq), sq))示例13: _TanhGrad
def _TanhGrad(op, grad):
"""Returns grad * (1 - tanh(x) * tanh(x))."""
y = op.outputs[0] # y = tanh(x)
with ops.control_dependencies([grad.op]):
y = math_ops.conj(y)
# pylint: disable=protected-access
return gen_math_ops._tanh_grad(y, grad)示例14: _SquareGrad
def _SquareGrad(op, grad):
x = op.inputs[0]
# Added control dependencies to prevent 2*x from being computed too early.
with ops.control_dependencies([grad]):
x = math_ops.conj(x)
y = constant_op.constant(2.0, dtype=x.dtype)
return math_ops.multiply(grad, math_ops.multiply(x, y))示例15: _CosGrad
def _CosGrad(op, grad):
"""Returns grad * -sin(x)."""
x = op.inputs[0]
with ops.control_dependencies([grad.op]):
if x.dtype.is_complex:
x = math_ops.conj(x)
return -grad * math_ops.sin(x)