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 vote360 views1 answer
Save image to file from URL
Python
0 vote389 views1 answer
Python Hewwo wowwd
Python
1 vote364 views1 answer
Def speak("audio"):
Python
0 vote332 views1 answer
Convert ascii to binary python
Python
0 vote331 views1 answer
Data where values in column starts with particular value
Python
0 vote360 views1 answer
How to add new column in django
Python
3 votes367 views2 answers
Extract one column from dataframe python
Python
35 votes346 views2 answers
How to do the sum of list in python
Python
4 votes352 views2 answers
Best python compilers
Python
0 vote349 views1 answer
Ppcm python
Python