def grad(self, inp, grads):
"""
"""
x, = inp
gz, = grads
cst = numpy.asarray(-2. / numpy.sqrt(numpy.pi),
dtype=upcast(x.type.dtype, gz.type.dtype))
return gz * (cst + 2. * x * exp(-x * x) * erfcx(x)),
def grad(self, inp, grads):
x, = inp
gz, = grads
if x.type in complex_types:
raise NotImplementedError()
elif x.type in float_types:
cst = numpy.asarray(numpy.sqrt(numpy.pi) / 2.0, dtype=upcast(x.type.dtype, gz.type.dtype))
return (gz * cst * exp(erfinv(x) ** 2),)
else:
return (None,)
def grad(self, inp, grads):
x, = inp
gz, = grads
if x.type in complex_types:
raise NotImplementedError()
elif x.type in float_types:
cst = numpy.asarray(2. / numpy.sqrt(numpy.pi),dtype=upcast(x.type.dtype,gz.type.dtype))
return - gz * cst * exp(-x*x),
else:
return None,
def grad(self, inp, grads):
x, = inp
gz, = grads
if x.type in complex_types:
raise NotImplementedError()
if self(x).type in discrete_types:
if x.type in discrete_types:
return [x.zeros_like(dtype=theano.config.floatX)]
else:
return [x.zeros_like()]
cst = numpy.asarray(2.0 / numpy.sqrt(numpy.pi), dtype=upcast(x.type.dtype, gz.type.dtype))
return (-gz * cst * exp(-x * x),)
def grad(self, inp, grads):
x, = inp
gz, = grads
if x.type in complex_types:
raise NotImplementedError()
if self(x).type in discrete_types:
if x.type in discrete_types:
return [x.zeros_like(dtype=theano.config.floatX)]
else:
return [x.zeros_like()]
cst = numpy.asarray(2. / numpy.sqrt(numpy.pi),
dtype=upcast(x.type.dtype, gz.type.dtype))
return gz * cst * exp(-x * x),
def L_op(self, inputs, outputs, grads):
x, = inputs
gz, = grads
if x.type in complex_types:
raise NotImplementedError()
if outputs[0].type in discrete_types:
if x.type in discrete_types:
return [x.zeros_like(dtype=theano.config.floatX)]
else:
return [x.zeros_like()]
cst = np.asarray(2. / np.sqrt(np.pi),
dtype=upcast(x.type.dtype, gz.type.dtype))
return -gz * cst * exp(-x * x),
def L_op(self, inputs, outputs, grads):
x, = inputs
gz, = grads
if x.type in complex_types:
raise NotImplementedError()
if outputs[0].type in discrete_types:
if x.type in discrete_types:
return [x.zeros_like(dtype=theano.config.floatX)]
else:
return [x.zeros_like()]
cst = np.asarray(2. / np.sqrt(np.pi),
dtype=upcast(x.type.dtype, gz.type.dtype))
return - gz * cst * exp(-x * x),
def L_op(self, inputs, outputs, grads):
(x, ) = inputs
(gz, ) = grads
if x.type in complex_types:
raise NotImplementedError()
if outputs[0].type in discrete_types:
if x.type in discrete_types:
return [x.zeros_like(dtype=theano.config.floatX)]
else:
return [x.zeros_like()]
cst = np.asarray(np.sqrt(np.pi) / 2.0,
dtype=upcast(x.type.dtype, gz.type.dtype))
return (-gz * cst * exp(erfcinv(x)**2), )
def L_op(self, inputs, outputs, grads):
x, = inputs
gz, = grads
if x.type in complex_types:
raise NotImplementedError()
if outputs[0].type in discrete_types:
if x.type in discrete_types:
return [x.zeros_like(dtype=theano.config.floatX)]
else:
return [x.zeros_like()]
cst = numpy.asarray(2. / numpy.sqrt(numpy.pi),
dtype=upcast(x.type.dtype, gz.type.dtype))
return gz * (-cst + (2. * x) * erfcx(x)),
def L_op(self, inputs, outputs, grads):
x, = inputs
gz, = grads
if x.type in complex_types:
raise NotImplementedError()
if outputs[0].type in discrete_types:
if x.type in discrete_types:
return [x.zeros_like(dtype=theano.config.floatX)]
else:
return [x.zeros_like()]
cst = numpy.asarray(numpy.sqrt(numpy.pi) / 2.,
dtype=upcast(x.type.dtype, gz.type.dtype))
return gz * cst * exp(erfinv(x) ** 2),
def L_op(self, inputs, outputs, grads):
(x, ) = inputs
(gz, ) = grads
if x.type in complex_types:
raise NotImplementedError()
if outputs[0].type in discrete_types:
if x.type in discrete_types:
return [x.zeros_like(dtype=config.floatX)]
else:
return [x.zeros_like()]
cst = np.asarray(2.0 / np.sqrt(np.pi),
dtype=upcast(x.type.dtype, gz.type.dtype))
return (gz * (-cst + (2.0 * x) * erfcx(x)), )
grad_rtol=div_grad_rtol,
inplace=True,
)
TestInvInplaceBroadcast = makeBroadcastTester(
op=inv_inplace,
expected=lambda x: _numpy_true_div(np.int8(1), x),
good=_good_inv_inplace,
bad_runtime=_bad_runtime_inv,
grad_rtol=div_grad_rtol,
inplace=True,
)
TestModInplaceBroadcast = makeBroadcastTester(
op=mod_inplace,
expected=lambda x, y: np.asarray(x % y, dtype=upcast(x.dtype, y.dtype)),
good=copymod(_good_broadcast_div_mod_normal_float_inplace,
["complex1", "complex2"]),
grad_eps=1e-5,
inplace=True,
)
TestPowInplaceBroadcast = makeBroadcastTester(
op=pow_inplace,
expected=lambda x, y: x**y,
good=_good_broadcast_pow_normal_float_pow,
inplace=True,
mode=ignore_isfinite_mode,
)
TestNegInplaceBroadcast = makeBroadcastTester(
