- ak.softmax(x, axis=None, keepdims=False, mask_identity=False)¶
x – the data on which to compute the softmax.
weight – data that can be broadcasted to
xto give each value a weight. Weighting values equally is the same as no weights; weighting some values higher increases the significance of those values. Weights can be zero or negative.
axis (None or int) – If None, combine all values from the array into a single scalar result; if an int, group by that axis:
0is the outermost,
1is the first level of nested lists, etc., and negative
axiscounts from the innermost:
-1is the innermost,
-2is the next level up, etc.
keepdims (bool) – If False, this function decreases the number of dimensions by 1; if True, the output values are wrapped in a new length-1 dimension so that the result of this operation may be broadcasted with the original array.
mask_identity (bool) – If True, the application of this function on empty lists results in None (an option type); otherwise, the calculation is followed through with the reducers’ identities, usually resulting in floating-point
Computes the softmax in each group of elements from
types supported, including all Awkward Arrays and Records). The grouping
is performed the same way as for reducers, though this operation is not a
reducer and has no identity.
This function has no NumPy equivalent.
Passing all arguments to the reducers, the softmax is calculated as
np.exp(x) / ak.sum(np.exp(x))