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 vote149 views2 answers
Numpy random normal seed time
Python
1 vote167 views1 answer
Np where nan
Python
0 vote152 views1 answer
Flip a coin with array in python
Python
0 vote147 views1 answer
Python use string to get object attributes
Python
1 vote159 views1 answer
Find sum of values in a column that corresponds to unique vallues in another coulmn python
Python
0 vote151 views1 answer
Pyqt disable maximize button
Python
2 votes153 views3 answers
How to print dataframe in python without index
Python
0 vote151 views2 answers
How to display csv in pandas
Python
1 vote145 views3 answers
Char list to string python
Python
2 votes153 views1 answer
Set index in datarame
Python