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

2 votes352 views2 answers
Django template array index
Python
0 vote373 views1 answer
Python split() source code
Python
0 vote350 views1 answer
Make white image numpy
Python
0 vote365 views1 answer
Python extend vs append
Python
0 vote352 views1 answer
Email grabber python
Python
0 vote342 views1 answer
How to sort values of pandas dataframe for iqr
Python
0 vote375 views1 answer
What if init migrations run two times or by pass this migrate
Python
-1 vote430 views1 answer
ImportError: cannot import name 'FieldDoesNotExist' from 'django.db.models.fields' (C:\Users\Admin\AppData\Local\Programs\Python\Python39\lib\site-packages\django\db\models\fields\__init__.py)
Python
0 vote332 views1 answer
How to pairwise permute in python
Python
0 vote342 views1 answer
Find the Runner Up Score solution in python3
Python