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 vote282 views1 answer
Create pytorch zeros
Python
1 vote299 views1 answer
Python use cases
Python
0 vote292 views2 answers
How to get current user info in odoo 8 in a controller
Python
3 votes325 views1 answer
Change figure size pandas
Python
1 vote294 views1 answer
Discord get bot profile picture
Python
1 vote303 views1 answer
Mysql Unread result found
Python
16 votes298 views6 answers
Python how to print
Python
0 vote317 views1 answer
Plotly dash datatable column width
Python
0 vote312 views1 answer
Specificity formula python
Python
0 vote291 views1 answer
Java sript
Python