本文整理汇总了Python中tensorflow.python.ops.math_ops.conj方法的典型用法代码示例。如果您正苦于以下问题：Python math_ops.conj方法的具体用法？Python math_ops.conj怎么用？Python math_ops.conj使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类tensorflow.python.ops.math_ops的用法示例。
在下文中一共展示了math_ops.conj方法的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: _ZetaGrad
# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import conj [as 别名]
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)
# TODO(b/36815900): Mark None return values as NotImplemented
return (None,
array_ops.reshape(math_ops.reduce_sum(partial_q * grad, rq), sq)) 示例2: _RealDivGrad
# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import conj [as 别名]
def _RealDivGrad(op, grad):
"""RealDiv op gradient."""
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.realdiv(grad, y), rx),
sx), array_ops.reshape(
math_ops.reduce_sum(grad * math_ops.realdiv(math_ops.realdiv(-x, y), y),
ry), sy)) 示例3: _MatMulGrad
# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import conj [as 别名]
def _MatMulGrad(op, grad):
"""Gradient for MatMul."""
t_a = op.get_attr("transpose_a")
t_b = op.get_attr("transpose_b")
a = math_ops.conj(op.inputs[0])
b = math_ops.conj(op.inputs[1])
if not t_a and not t_b:
grad_a = math_ops.matmul(grad, b, transpose_b=True)
grad_b = math_ops.matmul(a, grad, transpose_a=True)
elif not t_a and t_b:
grad_a = math_ops.matmul(grad, b)
grad_b = math_ops.matmul(grad, a, transpose_a=True)
elif t_a and not t_b:
grad_a = math_ops.matmul(b, grad, transpose_b=True)
grad_b = math_ops.matmul(a, grad)
elif t_a and t_b:
grad_a = math_ops.matmul(b, grad, transpose_a=True, transpose_b=True)
grad_b = math_ops.matmul(grad, a, transpose_a=True, transpose_b=True)
return grad_a, grad_b 示例4: _ZetaGrad
# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import conj [as 别名]
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5: _PolygammaGrad
# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import conj [as 别名]
def _PolygammaGrad(op, grad):
"""Returns gradient of psi(n, x) with respect to n and x."""
# TODO(tillahoffmann): Add derivative with respect to n
n = op.inputs[0]
x = op.inputs[1]
# Broadcast gradients
sn = array_ops.shape(n)
sx = array_ops.shape(x)
unused_rn, rx = gen_array_ops._broadcast_gradient_args(sn, sx)
# Evaluate gradient
with ops.control_dependencies([grad.op]):
n = math_ops.conj(n)
x = math_ops.conj(x)
partial_x = math_ops.polygamma(n + 1, x)
return (None,
array_ops.reshape(math_ops.reduce_sum(partial_x * grad, rx), sx)) 示例6: _Expm1Grad
# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import conj [as 别名]
def _Expm1Grad(op, grad):
"""Returns grad * exp(x)."""
x = op.inputs[0]
with ops.control_dependencies([grad.op]):
x = math_ops.conj(x)
y = math_ops.exp(x)
return grad * y 示例7: _InvGradGrad
# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import conj [as 别名]
def _InvGradGrad(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8: _ReciprocalGradGrad
# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import conj [as 别名]
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9: _SquareGrad
# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import conj [as 别名]
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.op]):
x = math_ops.conj(x)
return grad * (2.0 * x) 示例10: _SqrtGradGrad
# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import conj [as 别名]
def _SqrtGradGrad(op, grad):
a = op.inputs[0]
y = op.outputs[0] # y = 0.5 * b / conj(a)
with ops.control_dependencies([grad.op]):
ga = grad / a
return -math_ops.conj(ga) * y, 0.5 * ga 示例11: _RsqrtGrad
# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import conj [as 别名]
def _RsqrtGrad(op, grad):
"""Returns -0.5 * grad * conj(y)^3."""
y = op.outputs[0] # y = x^(-1/2)
return gen_math_ops._rsqrt_grad(y, grad) 示例12: _ExpGrad
# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import conj [as 别名]
def _ExpGrad(op, grad):
"""Returns grad * exp(x)."""
y = op.outputs[0] # y = e^x
with ops.control_dependencies([grad.op]):
y = math_ops.conj(y)
return grad * y 示例13: _LogGrad
# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import conj [as 别名]
def _LogGrad(op, grad):
"""Returns grad * (1/x)."""
x = op.inputs[0]
with ops.control_dependencies([grad.op]):
x = math_ops.conj(x)
return grad * math_ops.reciprocal(x) 示例14: _Log1pGrad
# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import conj [as 别名]
def _Log1pGrad(op, grad):
"""Returns grad * (1/(1 + x))."""
x = op.inputs[0]
with ops.control_dependencies([grad.op]):
x = math_ops.conj(x)
return grad * math_ops.reciprocal(1 + x) 示例15: _TanhGrad
# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import conj [as 别名]
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)