Softmax activation function using math library

Question

I am trying to develop a softmax function in python for my backpropagation and gradient descent program. I am calling the softmax function after I get my outputs of the output layer (2 outputs), the outputs are in a vector-like so [0.844521, 0.147048], and my current softmax function I have implemented is like this:

import math

vector = [0.844521, 0.147048]
def soft_max(x):
    e = math.exp(x)
    return e / e.sum()
print(soft_max(vector))

However, when i run it i get the following error

TypeError: must be real number, not list

Note: I only want to use the math library and no others

Answer 1

The function math.exp only works on scalars, and you can not apply it to the whole array. If you only want to use math than you need to implement it elementwise:

import math

def soft_max(x):
    exponents = []
    for element in x:
        exponents.append(math.exp(element))
    summ = sum(exponents)
    for i in range(len(exponents)):
        exponents[i] = exponents[i] / summ 
    return exponents 

if __name__=="__main__":
    arr = [0.844521, 0.147048]
    output = soft_max(arr)
    print(output)

However I still want to emphasise, that using numpy would solve the problem a lot easier:

import numpy as np

def soft_max(x):
    e = np.exp(x)
    return e / np.sum(e)

if __name__=="__main__":
    arr = [0.844521, 0.147048]
    output = soft_max(arr)
    print(output)