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 vote224 views1 answer
Python returen Thread
Python
-1 vote228 views1 answer
How to subtract dates in Python
Python
0 vote228 views1 answer
Python get text between two points
Python
0 vote242 views1 answer
Jetson nx unable to install matplotlib
Python
2 votes229 views1 answer
How to make exe from.py file
Python
0 vote235 views1 answer
Insert single value in dataframe using index
Python
0 vote224 views1 answer
Count wit for loop pthoon
Python
3 votes246 views1 answer
How to make downloadable file in flask
Python
1 vote225 views1 answer
Pandas find location of values greater than
Python
4 votes220 views4 answers
Set python3.7 as default ubuntu
Python