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

1 vote144 views1 answer
Mean Kurtosis of all rows pandas
Python
0 vote146 views1 answer
Python lambda with 2 variables
Python
0 vote159 views1 answer
Fakultät python
Python
0 vote151 views1 answer
Print("Default max_rows: {} and min_rows: {}".format( pd.get_option("max_rows"), pd.get_option("min_rows")))
Python
1 vote154 views2 answers
How ro have a incresing variable in python
Python
1 vote145 views1 answer
How to convert tuple into list in python
Python
8 votes90 views4 answers
Python gui
Python
0 vote192 views1 answer
Docker-compose.yml for flask celery rabbitmq
Python
0 vote147 views1 answer
Function print(text, times)
Python
2 votes135 views1 answer
Numpy array remove scientific notation
Python