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

30 votes242 views6 answers
Get python version in code
Python
0 vote262 views1 answer
Dict .get none replace
Python
0 vote214 views1 answer
Torch split classes stratified
Python
8 votes213 views4 answers
Remove nans from array
Python
5 votes217 views3 answers
Pygame quit
Python
0 vote215 views1 answer
Brython implemantation
Python
4 votes229 views4 answers
Filter django or
Python
0 vote204 views1 answer
Spotify python bot
Python
1 vote228 views1 answer
Print only small Latin letters a found in the given string.
Python
0 vote217 views1 answer
Python numpy bbox
Python