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

2 votes306 views3 answers
WARNING: pip is configured with locations that require TLS/SSL, however the ssl module in Python is not available.
Python
1 vote331 views2 answers
Np.argsort reverse
Python
5 votes333 views3 answers
How to print hello in python
Python
24 votes313 views5 answers
Python sort descending
Python
0 vote319 views1 answer
Maximum number of charectors allowed for a string variable in python
Python
10 votes292 views3 answers
Pandas create new column conditional on other columns
Python
1 vote310 views1 answer
Python npr permutation calculation
Python
5 votes329 views2 answers
Code challenges python
Python
2 votes353 views1 answer
Python pandas cumulative return
Python
0 vote323 views1 answer
Python hello world jenkins
Python