Np one hot encoding

One hot encoding numpy

  labels = (np.arange(num_labels) == labels[:,None]).astype(np.float32)

Np one hot encoding

>>> a = np.array([1, 0, 3])
>>> b = np.zeros((a.size, a.max()+1))
>>> b[np.arange(a.size),a] = 1
>>> b
array([[ 0.,  1.,  0.,  0.],
       [ 1.,  0.,  0.,  0.],
       [ 0.,  0.,  0.,  1.]])

Source: stackoverflow.com

Similar codes

32 votes294 views6 answers
Else if python
Python
0 vote310 views1 answer
"Token" is not defined Pylance
Python
0 vote319 views1 answer
Pandas show full columns
Python
0 vote303 views1 answer
Spevify datatype of column
Python
0 vote293 views1 answer
Pandas normalize rows to max value
Python
0 vote283 views1 answer
Pytorch get non diag element
Python
1 vote289 views2 answers
Beautiful soup get class name
Python
8 votes322 views6 answers
Python functions
Python
1 vote291 views1 answer
Cprofile usage python
Python
0 vote285 views1 answer
Find root of the path of file os package
Python