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 vote132 views1 answer
How To Generate The Requirements Of Your Python Project Based On Your Imports
Python
0 vote126 views1 answer
Compute difference of all the combinations of 2 arrays
Python
10 votes158 views3 answers
Set value based on column
Python
2 votes156 views1 answer
Values of unique from dataframe with count
Python
21 votes131 views1 answer
How to plot a graph using matplotlib
Python
19 votes129 views3 answers
Python program to check whether a number is even or odd
Python
0 vote128 views1 answer
Python censoring pypi
Python
1 vote125 views1 answer
Flask authentication user without database
Python
1 vote120 views1 answer
Count how many times a value shows in python list
Python
2 votes115 views10 answers
Python turtle tutorial
Python