log_softmax#
- class brainpy.math.log_softmax(x, axis=-1)[source]#
Log-Softmax function.
Computes the logarithm of the
softmax
function, which rescales elements to the range \([-\infty, 0)\).\[\mathrm{log\_softmax}(x) = \log \left( \frac{\exp(x_i)}{\sum_j \exp(x_j)} \right)\]- Parameters:
x (ArrayType) – The input array.
axis (int) – The axis or axes along which the
log_softmax
should be computed. Either an integer or a tuple of integers.