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

18 votes30 views6 answers
ModuleNotFoundError: No module named
Python
0 vote27 views1 answer
Count repeated strings map python
Python
4 votes33 views2 answers
Iterate through directories in python
Python
0 vote24 views1 answer
Python reference to back folder
Python
1 vote27 views1 answer
Incognito mode in selenium
Python
0 vote35 views1 answer
|safe django
Python Django
6 votes25 views2 answers
How to return the derivative of a function in python
Python
0 vote29 views1 answer
Handle dict invalid key python
Python
1 vote31 views1 answer
Prevent list index out of range python
Python
0 vote29 views1 answer
Tensorflow neural network
Python