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

1 vote290 views1 answer
Python extraer primer elemento lista
Python
14 votes291 views2 answers
Two groupby pandas
Python
2 votes316 views1 answer
Flask session timeout
Python
3 votes267 views6 answers
Fizz buzz python
Python
0 vote286 views2 answers
Trace table python
Python
0 vote255 views1 answer
Sort true
Python
0 vote275 views1 answer
Pandas description of dataframe
Python
1 vote264 views1 answer
Create np nan array
Python
0 vote266 views1 answer
Détruire une variable python
Python
0 vote239 views1 answer
How to search over a notebook in python
Python