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 vote106 views1 answer
Python get portion of dictionary
Python
0 vote116 views2 answers
Messagebox python pyqt
Python
0 vote122 views1 answer
Flip pyplot python
Python
57 votes110 views3 answers
How to add an item to a dictionary in python
Python
1 vote126 views1 answer
Discord.py commands.group
Python
-1 vote148 views2 answers
If __name__=='__main__':
Python
2 votes124 views1 answer
Termcolor python
Python
0 vote145 views1 answer
First n lis tpython
Python
0 vote110 views1 answer
Pandas to_csv append
Python
12 votes113 views6 answers
Print variable python
Python