LogSoftmax

Contents

LogSoftmax#

class brainstate.nn.LogSoftmax(dim=None)#

Applies the \(\log(\text{Softmax}(x))\) function to an n-dimensional input Tensor.

The LogSoftmax formulation can be simplified as:

\[\text{LogSoftmax}(x_{i}) = \log\left(\frac{\exp(x_i) }{ \sum_j \exp(x_j)} \right)\]
Parameters:

  • dim (int | None) – A dimension along which LogSoftmax will be computed.

  • Shape

  • -----

  • Input (-)

  • Output (-)

Returns:

A Tensor of the same dimension and shape as the input with values in the range [-inf, 0)

Return type:

Tensor

Examples

>>> import brainstate.nn as nn
>>> import brainstate
>>> m = nn.LogSoftmax(dim=1)
>>> x = brainstate.random.randn(2, 3)
>>> output = m(x)
Contents