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 vote361 views1 answer
Chatbot in python github
Python
0 vote353 views1 answer
Python type hinting pandas dataframe
Python
0 vote385 views1 answer
Fetch json array from mysql django
Python
0 vote352 views1 answer
Python how to convert a list of floats to a list of strings
Python
7 votes369 views3 answers
Python download for mac
Python
0 vote346 views1 answer
Grouped bar chart with labels
Python
0 vote313 views2 answers
How to use information from env variables in python
Python
2 votes352 views1 answer
Tkinter input popup
Python
0 vote300 views1 answer
Count no of nan in a 2d array python
Python
1 vote339 views1 answer
List methods in python
Python