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 vote176 views1 answer
Save model history keras
Python
1 vote175 views1 answer
Set pop in python
Python
0 vote189 views1 answer
Find the path of python executable
Python
0 vote191 views4 answers
Randome Word generator from consonant, vowel and specific string
Python
26 votes179 views5 answers
How to square root in python
Python
0 vote192 views2 answers
Update a package with pip in django
Python
0 vote251 views1 answer
Flask mongoengine configuration
Python Flask
2 votes195 views2 answers
Np float to int
Python
0 vote193 views1 answer
How to sort dataframe in python by length of groups
Python
1 vote183 views2 answers
.fill pygame
Python