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 vote137 views1 answer
Python - from most_similar to ldictionary
Python
0 vote133 views2 answers
Bar Charts bokeh
Python
2 votes169 views1 answer
Python sympy symbols
Python
0 vote142 views1 answer
Pip install mod_wsgi error
Python
0 vote139 views1 answer
Python flatten one liner
Python
0 vote151 views2 answers
Pyttsx3 save to file
Python
0 vote179 views2 answers
Convert python code to C code
Python
2 votes131 views2 answers
Choice random word in python from a text file
Python
0 vote96 views1 answer
Scipy.arange is deprecated and will be removed
Python
0 vote144 views1 answer
Picture plot
Python