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

3 votes306 views2 answers
Import file in parent directory python
Python
0 vote301 views2 answers
Numpy np sign change in df pandas zero crossing
Python
1 vote327 views1 answer
Flask blueprints
Python
96 votes327 views6 answers
If substring not in string python
Python
36 votes310 views1 answer
Py sleep function
Python
0 vote276 views0 answer
Python
0 vote311 views2 answers
How to access a variable from another py file in vs code
Python
0 vote310 views1 answer
Python to c++ compiler
Python
3 votes351 views2 answers
Df.loc
Python
1 vote309 views2 answers
Get definition of word python
Python