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 votes218 views1 answer
Python Key–value database
Python
34 votes266 views6 answers
Py to exe
Python
0 vote220 views1 answer
Affinity propagation cosine similarity python
Python
0 vote200 views1 answer
Torch.nn.Linear(in_features, out_features, bias=True) discription
Python
33 votes217 views10 answers
Elon musk
Python
61 votes204 views6 answers
Python classes
Python
1 vote239 views1 answer
How to convert adjacency list to adjacency matrix
Python
0 vote200 views1 answer
Python calander from Programmer of empires but updated
Python
1 vote189 views1 answer
Apply format to pandas datetime column
Python
89 votes211 views4 answers
New env in conda
Python