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 vote228 views1 answer
Dataframe python diplay 2 tables on same line
Python
0 vote176 views1 answer
Timedelta days to year pandas
Python
0 vote178 views1 answer
Function continuity python
Python
2 votes178 views1 answer
Get local timezone python
Python
0 vote192 views1 answer
Openpyxl read cell value
Python
0 vote190 views1 answer
Get value of 1 field in model django
Python
2 votes170 views2 answers
Convert pdf to csv python
Python
0 vote178 views1 answer
If number Of Players == >=4 python
Python
0 vote132 views1 answer
Ros python service client
Python
2 votes188 views3 answers
Python grid
Python