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 vote111 views3 answers
Pow
Python
0 vote92 views1 answer
How to make a new key in a dictionary python
Python
0 vote110 views1 answer
Pip install arcpy python 3
Python
1 vote102 views1 answer
Deleting an object in python
Python
1 vote97 views1 answer
Missingpy No module named 'sklearn.neighbors.base'
Python
1 vote97 views1 answer
Simple imputer python
Python
0 vote92 views1 answer
How to open cmd and run code using python
Python
4 votes99 views4 answers
Flash messages django
Python
0 vote110 views1 answer
How can space be bent
Python
2 votes97 views1 answer
Python checking if something is equal to NaN
Python