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

3 votes147 views4 answers
Password generator
Python
1 vote128 views1 answer
'set' object is not reversible
Python
26 votes126 views5 answers
Python square root
Python
1 vote147 views1 answer
Import "django.core.urlresolvers" could not be resolved
Python Django
5 votes130 views1 answer
Convert jupyter notebook to python cmd line
Python
0 vote123 views1 answer
Series distict
Python
0 vote123 views1 answer
Python array set key value
Python
200 votes167 views11 answers
Pip upgrade python
Python
3 votes182 views2 answers
Pandas concat series into dataframe
Python
0 vote153 views2 answers
Pywavelets tutorial
Python