Numpy softmax

>>> from scipy.special import softmax
>>> np.set_printoptions(precision=5)
>>> x = np.array([[1, 0.5, 0.2, 3],
              [1,  -1,   7, 3],
              [2,  12,  13, 3]])
>>> m = softmax(x)
>>> m
array([[  4.48309e-06,   2.71913e-06,   2.01438e-06,   3.31258e-05],
       [  4.48309e-06,   6.06720e-07,   1.80861e-03,   3.31258e-05],
       [  1.21863e-05,   2.68421e-01,   7.29644e-01,   3.31258e-05]])

Source: docs.scipy.org

Softmax function python

def softmax(x):
    return np.exp(x) / np.sum(np.exp(x), axis=0)

Source: stackoverflow.com

Similar codes

0 vote130 views1 answer
Python - oordinated universal time
Python
0 vote135 views1 answer
What is the use of extend in python
Python
10 votes157 views2 answers
Update anaconda from cmd
Python
12 votes130 views4 answers
Python join dict
Python
3 votes141 views1 answer
Change plot size matplotlib python
Python
0 vote137 views1 answer
How to increment date by one in python
Python
0 vote125 views1 answer
Get all functions from a module as string list python
Python
6 votes130 views1 answer
Python exit for loop
Python
10 votes140 views5 answers
Pandas to list of dicts
Python
0 vote94 views2 answers
Python remove empty lines
Python