hard_quantize

torchhd.hard_quantize(input: Tensor)[source]

Applies binary quantization to all elements of the input tensor.

Warning

This function does not take the VSA model class into account.

Parameters:: input (Tensor) – input tensor

Shapes:

Input: \((*)\)
Output: \((*)\)

Examples:

>>> x = torchhd.random(2, 6)
>>> x
tensor([[ 1.,  1., -1.,  1.,  1.,  1.],
    [ 1., -1., -1., -1.,  1., -1.]])
>>> y = torchhd.bundle(x[0], x[1])
>>> y
tensor([ 2.,  0., -2.,  0.,  2.,  0.])
>>> torchhd.hard_quantize(y)
tensor([ 1., -1., -1., -1.,  1., -1.])