jax.nn.softmax

Contents

jax.nn.softmax#

jax.nn.softmax(x, axis=-1, where=None, initial=_UNSPECIFIED)[source]#

Softmax function.

Computes the function which rescales elements to the range \([0, 1]\) such that the elements along axis sum to \(1\).

\[\mathrm{softmax}(x) = \frac{\exp(x_i)}{\sum_j \exp(x_j)}\]
Parameters:
  • x (ArrayLike) – input array

  • axis (int | tuple[int, ...] | None) – the axis or axes along which the softmax should be computed. The softmax output summed across these dimensions should sum to \(1\). Either an integer or a tuple of integers.

  • where (ArrayLike | None) – Elements to include in the softmax.

  • initial (ArrayLike | None | Unspecified)

Returns:

An array.

Return type:

Array

Note

If any input values are +inf, the result will be all NaN: this reflects the fact that inf / inf is not well-defined in the context of floating-point math.

See also

log_softmax()