sigmoid¶

paddle.nn.functional. sigmoid ( x, name=None ) [source]

Sigmoid Activation

\(out = \frac{1}{1 + e^{-x}}\)

Parameters

• x (Tensor) – Input of Sigmoid operator, an N-D Tensor, with data type float32, float64 or float16.

• with_quant_attr (BOOLEAN) – Whether the operator has attributes used by quantization.

• name (str, optional) – Name for the operation (optional, default is None). For more information, please refer to Name.

Returns

Output of Sigmoid operator, a Tensor with shape same as input.

Return type

out (Tensor)

Examples

import paddle
import paddle.nn.functional as F

x = paddle.to_tensor([-0.4, -0.2, 0.1, 0.3])
out = F.sigmoid(x)
print(out)
# [0.40131234 0.450166   0.52497919 0.57444252]