erf¶

paddle.fluid.layers.erf(x)[source]

Erf Operator For more details, see [Error function](https://en.wikipedia.org/wiki/Error_function).

Equation:

\[out = \frac{2}{\sqrt{\pi}} \int_{0}^{x}e^{- \eta^{2}}d\eta\]

Parameters

x (Variable) – The input of Erf op, Tensor or LoDTensor, dtype: float32 or float64.

Returns

The output of Erf op, Tensor or LoDTensor, dtype: float32 or float64, the same as the input, shape: the same as the input.

Return type

Variable

Examples

# declarative mode
import numpy as np
from paddle import fluid

x = fluid.data(name="x", shape=(-1, 3), dtype="float32")
y = fluid.layers.erf(x)

place = fluid.CPUPlace()
exe = fluid.Executor(place)
start = fluid.default_startup_program()
main = fluid.default_main_program()

data = np.random.randn(2, 3).astype("float32")
exe.run(start)

y_np, = exe.run(main, feed={"x": data}, fetch_list=[y])

data
# array([[ 0.4643714 , -1.1509596 ,  1.2538221 ],
#        [ 0.34369683,  0.27478245,  1.1805398 ]], dtype=float32)
y_np
# array([[ 0.48863927, -0.8964121 ,  0.9237998 ],
#        [ 0.37307587,  0.30242872,  0.9049887 ]], dtype=float32)

# imperative mode
import numpy as np
from paddle import fluid
import paddle.fluid.dygraph as dg

data = np.random.randn(2, 3).astype("float32")
place = fluid.CPUPlace()
with dg.guard(place) as g:
    x = dg.to_variable(data)
    y = fluid.layers.erf(x)
    y_np = y.numpy()
data
# array([[ 0.4643714 , -1.1509596 ,  1.2538221 ],
#        [ 0.34369683,  0.27478245,  1.1805398 ]], dtype=float32)
y_np
# array([[ 0.48863927, -0.8964121 ,  0.9237998 ],
#        [ 0.37307587,  0.30242872,  0.9049887 ]], dtype=float32)