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 vote281 views1 answer
Tusha
Python
0 vote285 views1 answer
Simple graph in matplotlib categorical variables
Python
1 vote301 views2 answers
Pytorch view -1 meaning
Python
0 vote272 views1 answer
Spreadsheet worksheet counter
Python
3 votes321 views1 answer
Python open each file in directory
Python
1 vote273 views3 answers
Py random list integers
Python
0 vote288 views1 answer
Replace string using regex
Python
4 votes273 views2 answers
Finding median on python
Python
0 vote277 views2 answers
Icpc preliminary 2018 problem
Python
3 votes288 views1 answer
Jinja2 datetime format
Python