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 vote279 views1 answer
Dtype cannot be bool python
Python
39 votes259 views3 answers
Convert str to datetime
Python
0 vote241 views1 answer
Ex: python
Python
4 votes244 views1 answer
Dropdown in tkinter
Python
0 vote274 views1 answer
Theano_flags windows
Python
-1 vote270 views1 answer
Python get the last in dictionary
Python
1 vote259 views2 answers
Set jupyer color to dark
Python
0 vote256 views1 answer
List views django
Python
1 vote276 views1 answer
Get all classes from css file using python
Python
4 votes271 views3 answers
Gyp ERR! find Python
Python