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 vote299 views2 answers
Smooth interpolation python
Python
3 votes321 views1 answer
Tkinter draw circle
Python
0 vote367 views1 answer
Max length of characters in dataframe's columns
Python
0 vote328 views1 answer
What is the difference between accuracy and loss
Python
1 vote333 views1 answer
How to find magnitude of complex number in python
Python
1 vote342 views1 answer
Classification cross validation
Python
0 vote326 views1 answer
Line continutation in r string python
Python
8 votes335 views2 answers
Django create empty migration
Python
1 vote306 views1 answer
Knowing the sum null values in a specific row in pandas dataframe
Python
24 votes367 views1 answer
Python hour from date
Python