Creates an operation representing the computation required for a softmax layer.
The inputs to the softmax function.
The operation.
import std.math : approxEqual; import dopt.core : evaluate; auto y = float32([1, 5], [1.0f, 2.0f, 3.0f, 1.0f, 2.0f]).softmax(); assert(approxEqual( y.evaluate().get!float, [0.0674508, 0.18335, 0.498398, 0.0674508, 0.18335] ));
See Implementation
Creates an operation representing the computation required for a softmax layer.