fourier_encode#

ivy.fourier_encode(x, max_freq, /, *, num_bands=4, linear=False, concat=True, flatten=False)[source]#

Pad an array with fourier encodings.

Parameters:

  • x (Union[Array, NativeArray]) – Input array to encode.

  • max_freq (Union[float, Array, NativeArray]) – The maximum frequency of the encoding.

  • num_bands (int) – The number of frequency bands for the encoding. (default: 4) Default is 4.

  • linear (bool) – Whether to space the frequency bands linearly as opposed to geometrically. (default: False) Default is False.

  • concat (bool) – Whether to concatenate the position, sin and cos values, or return seperately. (default: True) Default is True.

  • flatten (bool) – Whether to flatten the position dimension into the batch dimension. (default: False) Default is False.

Return type:

Union[Array, NativeArray, Tuple]

Returns:

ret – New array with the final dimension expanded, and the encodings stored in this channel.

Examples

>>> x = ivy.array([1,2,3])
>>> y = 1.5
>>> z = ivy.fourier_encode(x,y)
>>> print(z)
ivy.array([[ 1.0000000e+00, 1.2246468e-16, 0.0000000e+00, 0.0000000e+00,
             0.0000000e+00, -1.0000000e+00, 1.0000000e+00, 1.0000000e+00,
             1.0000000e+00],
           [ 2.0000000e+00, -2.4492936e-16, 0.0000000e+00, 0.0000000e+00,
             0.0000000e+00, 1.0000000e+00, 1.0000000e+00, 1.0000000e+00,
             1.0000000e+00],
           [ 3.0000000e+00, 3.6739404e-16, 0.0000000e+00, 0.0000000e+00,
             0.0000000e+00, -1.0000000e+00, 1.0000000e+00, 1.0000000e+00,
             1.0000000e+00]])

>>> x = ivy.array([3,10])
>>> y = 2.5
>>> z = ivy.fourier_encode(x, y, num_bands=3)
>>> print(z)
ivy.array([[ 3.0000000e+00,  3.6739404e-16,  3.6739404e-16, 3.6739404e-16,
            -1.0000000e+00, -1.0000000e+00, -1.0000000e+00],
           [ 1.0000000e+01, -1.2246468e-15, -1.2246468e-15, -1.2246468e-15,
             1.0000000e+00,  1.0000000e+00,  1.0000000e+00]])
Array.fourier_encode(self, max_freq, /, *, num_bands=4, linear=False, concat=True, flatten=False)#

ivy.Array instance method variant of ivy.fourier_encode. This method simply wraps the function, and so the docstring for ivy.fourier_encode also applies to this method with minimal changes.

Parameters:

  • self (Array) – input array to encode

  • max_freq (Union[float, Array, NativeArray]) – The maximum frequency of the encoding.

  • num_bands (int) – The number of frequency bands for the encoding. Default is 4. (default: 4)

  • linear (bool) – Whether to space the frequency bands linearly as opposed to geometrically. (default: False) Default is False.

  • concat (bool) – Whether to concatenate the position, sin and cos values, or return (default: True) seperately. Default is True.

  • flatten (bool) – Whether to flatten the position dimension into the batch dimension. (default: False) Default is False.

Return type:

Union[Array, NativeArray, Tuple]

Returns:

ret – New array with the final dimension expanded, and the encodings stored in this channel.

Examples

>>> x = ivy.array([1, 2, 3])
>>> y = 1.5
>>> z = x.fourier_encode(y)
>>> print(z)
ivy.array([[ 1.0000000e+00, 1.2246468e-16, 0.0000000e+00, 0.0000000e+00,
             0.0000000e+00, -1.0000000e+00, 1.0000000e+00, 1.0000000e+00,
             1.0000000e+00],
           [ 2.0000000e+00, -2.4492936e-16, 0.0000000e+00, 0.0000000e+00,
             0.0000000e+00, 1.0000000e+00, 1.0000000e+00, 1.0000000e+00,
             1.0000000e+00],
           [ 3.0000000e+00, 3.6739404e-16, 0.0000000e+00, 0.0000000e+00,
             0.0000000e+00, -1.0000000e+00, 1.0000000e+00, 1.0000000e+00,
             1.0000000e+00]])

>>> x = ivy.array([3, 10])
>>> y = 2.5
>>> z = x.fourier_encode(y, num_bands=3)
>>> print(z)
ivy.array([[ 3.0000000e+00,  3.6739404e-16,  3.6739404e-16,  3.6739404e-16,
            -1.0000000e+00, -1.0000000e+00, -1.0000000e+00],
           [ 1.0000000e+01, -1.2246468e-15, -1.2246468e-15, -1.2246468e-15,
             1.0000000e+00,  1.0000000e+00,  1.0000000e+00]])
Container.fourier_encode(self, max_freq, /, *, num_bands=4, linear=False, flatten=False, key_chains=None, to_apply=True, prune_unapplied=False, map_sequences=False)#

ivy.Container instance method variant of ivy.fourier_encode. This method simply wraps the function, and so the docstring for ivy.fourier_encode also applies to this method with minimal changes.

Parameters:

  • self (Container) – Input container to apply fourier_encode at leaves.

  • max_freq (Union[float, Array, NativeArray]) – The maximum frequency of the encoding.

  • num_bands (int) – The number of frequency bands for the encoding. Default is 4. (default: 4)

  • linear (bool) – Whether to space the frequency bands linearly as opposed to geometrically. (default: False) Default is False.

  • flatten (bool) – Whether to flatten the position dimension into the batch dimension. (default: False) Default is False.

  • key_chains (Optional[Union[List[str], Dict[str, str]]]) – The key-chains to apply or not apply the method to. Default is None. (default: None)

  • to_apply (bool) – If True, the method will be applied to key_chains, otherwise key_chains (default: True) will be skipped. Default is True.

  • prune_unapplied (bool) – Whether to prune key_chains for which the function was not applied. (default: False) Default is False.

  • map_sequences (bool) – Whether to also map method to sequences (lists, tuples). (default: False) Default is False.

  • dtype – Data type of the returned array. Default is None.

  • out – Optional output container. Default is None.

Return type:

Container

Returns:

ret – New container with the final dimension expanded of arrays at its leaves, and the encodings stored in this channel.

Examples

>>> x = ivy.Container(a = ivy.array([1,2]),
...                   b = ivy.array([3,4]))
>>> y = 1.5
>>> z = x.fourier_encode(y)
>>> print(z)
{
    a: (<classivy.array.array.Array>shape=[2,9]),
    b: (<classivy.array.array.Array>shape=[2,9])
}

>>> x = ivy.Container(a = ivy.array([3,10]),
...                   b = ivy.array([4,8]))
>>> y = 2.5
>>> z = x.fourier_encode(y,num_bands=3)
>>> print(z)
{
    a: ivy.array([[ 3.0000000e+00, 3.6739404e-16, 3.6739404e-16,
            3.6739404e-16,-1.0000000e+00, -1.0000000e+00, -1.0000000e+00],
            [ 1.0000000e+01, -1.2246468e-15, -1.2246468e-15,
            -1.2246468e-15, 1.0000000e+00,  1.0000000e+00,  1.0000000e+00]]),
    b: ivy.array([[4.00000000e+00, -4.89858720e-16, -4.89858720e-16,
            -4.89858720e-16, 1.00000000e+00,  1.00000000e+00,  1.00000000e+00],
            [ 8.00000000e+00, -9.79717439e-16, -9.79717439e-16, -9.79717439e-16,
            1.00000000e+00,  1.00000000e+00,  1.00000000e+00]])
}