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

2 votes153 views3 answers
Set axis ticks matplotlib
Python
0 vote232 views2 answers
Radix sort python
Python
14 votes178 views3 answers
Create channel
Python
1 vote188 views1 answer
Can you print to multiple output files python
Python
0 vote170 views1 answer
Pandas read csv read all columns except few columns
Python
0 vote226 views1 answer
MULTIPLE Model Search in Django rest framework
Python Django
5 votes164 views1 answer
Python check if class has function
Python
0 vote178 views1 answer
Python import module with minus in its name
Python
0 vote177 views1 answer
Django insert bulk data
Python
0 vote133 views1 answer
How to extract keys from dictreader python
Python