mindspore.Tensor.sigmoid

Tensor.sigmoid() → Tensor

Computes Sigmoid of self element-wise. The Sigmoid function is defined as:

\[\text{sigmoid}(x_i) = \frac{1}{1 + \exp(-x_i)}\]

where \(x_i\) is an element of x.

Sigmoid Function Graph:

../../../_images/Sigmoid.png
Returns

Tensor, with the same type and shape as the self.

Raises

  • TypeError – If dtype of self is not float16, float32, float64, complex64 or complex128.

  • TypeError – If self is not a Tensor.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor
>>> input = Tensor(np.array([1, 2, 3, 4, 5]), mindspore.float32)
>>> output = Tensor.sigmoid(input)
>>> print(output)
[0.7310586  0.880797   0.95257413 0.98201376 0.9933072 ]