megengine.functional.exp

exp(x)[source]

Element-wise \(e^x\) function.

Calculates an approximation to the exponential function for each element \(x_i\) of the input tensor \(x\) (\(e\) raised to the power of \(x_i\), where \(e\) is the base of the natural logarithm).

This function has domain [-infinity, +infinity] and codomain [+0, +infinity].

Parameters

x – input tensor. Should have a floating-point data type.

Returns

a tensor containing the evaluated exponential function result for each element in \(x\). The returned tensor must have a floating-point data type determined by Type promotion rules.

Special cases

For floating-point operands,

  • If \(x_i\) is NaN, the result is NaN.

  • If \(x_i\) is +0, the result is 1.

  • If \(x_i\) is -0, the result is 1.

  • If \(x_i\) is +infinity, the result is +infinity.

  • If \(x_i\) is -infinity, the result is +0.

Examples

>>> F.exp([0, F.log(2)])
Tensor([1. 2.], device=xpux:0)

previous

megengine.functional.clip

next

megengine.functional.expm1