mindspore.nn.probability.bijector.Exp

class mindspore.nn.probability.bijector.Exp(name='Exp')[source]

Exponential Bijector. This Bijector performs the operation:

\[Y = \exp(x).\]

Parameters: name (str) – The name of the Bijector. Default: ‘Exp’.

Supported Platforms:: Ascend GPU

Examples

>>> import mindspore
>>> import mindspore.nn as nn
>>> from mindspore import Tensor
>>>
>>> # To initialize an Exp bijector.
>>> exp_bijector = nn.probability.bijector.Exp()
>>> value = Tensor([1, 2, 3], dtype=mindspore.float32)
>>> ans1 = exp_bijector.forward(value)
>>> print(ans1.shape)
(3,)
>>> ans2 = exp_bijector.inverse(value)
>>> print(ans2.shape)
(3,)
>>> ans3 = exp_bijector.forward_log_jacobian(value)
>>> print(ans3.shape)
(3,)
>>> ans4 = exp_bijector.inverse_log_jacobian(value)
>>> print(ans4.shape)
(3,)

forward(value)

forward mapping, compute the value after mapping as \(Y = \exp(X)\).

Parameters

value (Tensor) - the value to compute.

Returns

Tensor, the value of output after mapping.

forward_log_jacobian(value)

compute the log value after mapping, namely \(\log(d\exp(x) / dx)\).

Parameters

value (Tensor) - the value to compute.

Returns

Tensor, the log value of forward mapping.

inverse(value)

Inverse mapping, compute the value after inverse mapping as \(X = \log(Y)\).

Parameters

value (Tensor) - the value of output after mapping.

Returns

Tensor, the value to compute.

inverse_log_jacobian(value)

Compute the log value of the inverse mapping, namely \(\log(d\log(x) / dx)\).

Parameters

value (Tensor) - the value of output after mapping.

Returns

Tensor, the log value of the inverse mapping.